M. Brandon Westover, MD, PhD

All Publications

• Electrographic Features of Catatonia With or Without Comorbid Delirium. The Journal of neuropsychiatry and clinical neurosciences Luccarelli, J., Smith, J. R., Turley, N., Rogers, J. P., Sun, H., Kohrman, S. I., Fricchione, G., Westover, M. B. 2026; 38 (1): 61-67

  Abstract

  Catatonia is an underdiagnosed disorder characterized by speech and motor abnormalities. EEG examinations may improve the accuracy of a catatonia diagnosis, but clinical and electrographic correlations have not been established. The authors describe catatonic features and EEG findings in a large multisite retrospective cohort.The clinical records in two health care systems were searched for patients with an EEG recording and a catatonia assessment with the Bush-Francis Catatonia Rating Scale conducted within 24 hours of each other. Included patients were retrospectively screened for delirium through a chart-based assessment. Augmented inverse propensity weighting (AIPW) was used to estimate the causal effects of delirium and catatonia on the presence of an abnormal EEG finding.Overall, 178 patients met inclusion criteria, 144 (81%) of whom had catatonia. Among the patients with catatonia, 43% also had delirium. EEG abnormalities were present among 43% of patients with catatonia, including 28% of patients with catatonia without delirium and 69% of the patients with co-occurring catatonia and delirium. Individual catatonic signs and EEG abnormalities showed only a weak correlation. In AIPW models, a delirium diagnosis was associated with significantly higher odds for an abnormal EEG finding (OR=6.75; 95% CI=2.83-16.14), whereas a diagnosis of catatonia was not (OR=1.83, 95% CI=0.79-4.24).EEG abnormalities are common among individuals with catatonia, but these are difficult to disentangle from abnormalities resulting from co-occurring delirium. Further research is needed to define the role of EEG examinations in the assessments of catatonia and delirium.

  View details for DOI 10.1176/appi.neuropsych.20240215

  View details for PubMedID 40509792

  View details for PubMedCentralID PMC12357770

• Late-Onset Seizures: Etiology and Demographics in US Tertiary Care Epilepsy Centers NEUROLOGY Blank, L. J., Johnson, E. L., Pellerin, K. R., Sarkis, R. A., Gaston, T. E., Shafi, M. M., Zepeda, R., Camitan, M., Anderson, T., Hankerson, A., Jan, A., Jung, K., Leake, M., Westover, M., Lam, A. D. 2026; 106 (11): e214948

  Abstract

  Adults older than age 55 years have the highest incidence rate and are the fastest-growing population among people with epilepsy. The aim of this study was to characterize the etiologies of new-onset seizures in older adults and to examine how seizure etiology varies across demographic groups. We used data from 7 US epilepsy centers from 2021 to 2025 and compared findings with those of previous population-based studies, providing an updated view and highlighting opportunities for prevention and improved risk stratification.We retrospectively reviewed medical charts of 2,052 patients aged ≥55 years at the time of a first seizure, who were evaluated at 7 epilepsy centers between 2021 and 2025. We categorized seizures by etiology as follows: ischemic stroke, hemorrhagic stroke, tumor, neurodegeneration, provoked seizures, traumatic brain injury, and unknown. We examined differences in etiology by demographic strata (age, sex, race, and primary language) using chi-square tests, Kruskal-Wallis tests, analysis of variance, and Cuzick tests.The most frequent seizure etiologies among older adults were unknown (29.9%), ischemic stroke (15.4%), and provoked seizures (14.9%). Neurodegenerative disease was the etiology for 5.3% of cases overall but increased in prevalence with age, accounting for 18.5% among patients aged 85-89 years. Seizure etiologies also differed by sex and race. Men more commonly had seizures caused by cerebrovascular disease and traumatic brain injury, while women more commonly had seizures due to neurodegenerative disease. Black patients had higher proportions of ischemic stroke and neurodegenerative disease, while unexplained epilepsy was more common among White patients.The causes of late-onset seizures vary based on age, sex, and race. Nearly one-third of cases of epilepsy in older adults remain unexplained despite advances in imaging techniques, underscoring the need for further research on the mechanisms and health implications of late-onset unexplained epilepsy. Improved prevention of cerebrovascular disease and optimized management of provoked seizures may reduce the growing burden of epilepsy in older adults.

  View details for DOI 10.1212/WNL.0000000000214948

  View details for Web of Science ID 001763064200001

  View details for PubMedID 42096671

• The Brain Imaging and Neurophysiology Dataset of large-scale multimodal neural data. Scientific data Maschke, C., Hadar, P. N., Zhang, Y., Li, J., Ganjoo, G., Hoopes, A., Guazzo, A., Gupta, A., Ghanta, M., Nearing, B., Silvers, C. T., Gunapati, B., Thomas, R., Kim, J. A., Mukerji, S. S., Dalca, A., Zafar, S., Lam, A. D., Mignot, E., Westover, M. B. 2026

  Abstract

  The Brain Imaging and Neurophysiology Dataset (BIND) represents one of the largest multi-institutional, multimodal, clinical neuroimaging repositories, comprising 1.8 million brain scans from 38,942 patients, linked to full-text reports and neurophysiological recordings. This comprehensive dataset addresses critical limitations in neuroimaging research by providing a rich and diverse set of large-scale multimodal data. BIND integrates de-identified data from Massachusetts General Hospital, Brigham and Women's Hospital, and Stanford University, including 1,723,699 MRI scans (1.5, 3 and 7 Tesla), 54,137 CT scans, 5,093 PET scans, and 526 SPECT scans, converted to standardized NIfTI format following BIDS organization. The dataset spans the full age spectrum and encompasses diverse neurological conditions alongside healthy subjects. We deployed Large Language Models to extract structured clinical metadata from 84,960 reports to extract standardized clinical information. All imaging data are linked to previously published EEG and polysomnography recordings, facilitating future multimodal analyses. BIND is freely accessible for academic research through the Brain Data Science Platform (https://bdsp.io/). This resource facilitates large-scale neuroimaging studies, machine learning applications, and multimodal brain research to accelerate discoveries in clinical neuroscience.

  View details for DOI 10.1038/s41597-026-07421-x

  View details for PubMedID 42168237

• Delirium and Increased Risk of Developing Dementia: An Emulated Target Trial Analysis. medRxiv : the preprint server for health sciences Rathmell, C. S., Sun, H., Ge, W., Magdamo, C., Das, S., Moura, L. M., Zafar, S. F., Akeju, O., Mukherji, S. S., Shaw, K. M., Westover, M. B. 2026

  Abstract

  Multiple studies suggest bidirectional links between delirium and Alzheimer's Disease and Related Dementias (ADRD). Although they establish a strong association between delirium and subsequent ADRD, it has not been explored using statistical causal inference which makes the best use of observational data to minimize biases.We conducted an emulated clinical trial to estimate the effect of experiencing delirium during hospitalization between April 2017 and September 2019 on the cumulative incidence of ADRD over two years following hospital admission in patients 65 and older. The emulated trial used observational data from individuals in the Mass General Brigham Electronic Medical Record (EMR). We carried out statistical causal survival analysis using methods that adjust for confounding, censoring, competing risks, and immortal-time bias, including inverse propensity weighting (IPW) and g-formula approaches.Of the 6029 patients hospitalized in this time frame who were 65 or older with evidence of a PCP in the EMR, 5901 were included in the analysis based on no history of dementia diagnosis or medications 12 months prior to admission. At two years post-admission, the adjusted cumulative incidence of ADRD in individuals who did not experience delirium was 7.6% (95% Confidence Interval [CI] 4.0-12.1%) while it was 20.2% (95% CI 13.2-27.9%) for those who did experience delirium when calculated using the IPW method.Our emulated trial results argue for a strong association between delirium during hospitalization and the risk of developing ADRD in the two years following hospital admission in individuals 65 and older.

  View details for DOI 10.64898/2026.05.11.26352925

  View details for PubMedID 42180382

  View details for PubMedCentralID PMC13193019

• Video-based Detection of Delirium in Hospitalized Adults. medRxiv : the preprint server for health sciences Mendu, M., Tesh, R. A., Pellerin, K., Steward, G. E., Cerda, I. H., Williams, M., Colman, M., Shah, S., Lam, A. D., Cash, S. S., Westover, M. B., Kimchi, E. Y. 2026

  Abstract

  Delirium, a dynamic neuropsychiatric condition associated with morbidity and mortality, remains underdiagnosed due to reliance on subjective, intermittent screening tools. Objective and potentially continuous identification is needed to improve clinical care. We developed and validated an analytic framework for delirium classification based on automatically extracted video features. In this prospective cohort study, patients (≥ 18 years) admitted to the inpatient medical or neurological ward of a tertiary academic center between August 2020 and March 2022 with an expected stay longer than one night were enrolled. Daily structured delirium assessments and brief video recordings were performed in consenting patients. Videos were analyzed using deep learning pose estimation to extract keypoints and calculate behavioral features based on eye, face, and limb postures and movements. Four machine learning models (logistic regression, gradient boosting, support vector machines, and random forests) were trained to predict delirium status from extracted features. Model performance was evaluated on 20 repetitions of three-fold cross-validation using the area under the curve of the receiver operating characteristics curve (AUC ROC). The cohort included 109 videos from 25 male and 25 female participants (median age: 72, IQR: 63.25-78). Twenty videos (18%) were from patients with delirium. Keypoints for this dataset were more accurately extracted using a customized ResNet-101 model developed with DeepLabCut (sensitivity 0.94, specificity 0.89, compared to human-labeled gold standards) than using off-the-shelf models. Keypoints were then used to generate behavioral features summarizing movement and postures throughout the video. A support vector machine model achieved an average delirium classification AUC ROC of 0.79 (SD ± 0.09), sensitivity of 0.71 (SD ± 0.16), and specificity of 0.78 (SD ± 0.07). This study demonstrates the feasibility of identifying delirium using brief videos in clinically heterogeneous cohorts and reveals novel features for objective identification.Delirium is a sudden change in attention and awareness that commonly affects hospitalized patients. It is linked with longer hospital stays, cognitive decline, and death. Patients with delirium often show changes in movements and behaviors such as slowed movement, restlessness, or excessive scanning of the environment. Since current screening tools rely on intermittent human interactions, they can be subjective and miss the fluctuating nature of delirium, leading to underdiagnosis. We sought to explore whether short video recordings could be used to detect delirium automatically. In our study, we enrolled 50 hospitalized patients and conducted daily delirium assessments and video recordings. We used a machine learning model to analyze patients' eye movements, facial expressions, and body postures. We found that video-derived features could be used to identify delirium in a small clinical cohort. While needing further validation in outside cohorts, this study shows an important proof-of-concept for objective delirium monitoring in heterogeneous clinical contexts without adding burden to clinical staff.

  View details for DOI 10.64898/2026.05.11.26352902

  View details for PubMedID 42180362

  View details for PubMedCentralID PMC13193048

• Better sleep now, better cognition later? Predicting cognitive function using a machine learning-based sleep EEG brain health score SLEEP Marino, F. R., Ganglberger, W., Sun, H., Liu, Y., Ding, H., Thomas, R. J., Au, R., Westover, M. 2026

  Abstract

  Sleep state electrocortical activity measured using electroencephalograms (EEG) is linked with cognitive function and dementia risk. The rich information in overnight EEG can be condensed into integrated scores using machine learning. The Brain Health Score (BHS) was derived in prior work using an end-to-end deep learning model trained to jointly optimize higher cognitive function and lower disease risk from raw EEG. However, it is unknown whether the BHS predicts future neuropsychological (NP) performance.This study included 426 Framingham Heart Study (FHS) Generation 2 or Omni 1 participants with BHS values from in-home polysomnography in mid-to-late life, and subsequent digital clock drawing (dCDT) and NP testing an average of 12.6 years later. Linear regression models estimated associations between BHS and dCDT, memory, language, or executive function scores, adjusting for age, sex, race, education, smoking, body mass index, and FHS cohort. To enable comparisons across outcomes, the independent variables were centered and rescaled, and then the model was refitted to generate standardized estimates.Participants were on average 56 years at sleep assessment, 55% female, and 86% non-Hispanic White. Each 1-SD higher BHS was associated with higher dCDT, memory, language, and executive function scores (dCDT: β=0.16, 95% CI=0.06-0.26; memory: β=0.13, 95% CI=0.03-0.23; language: β=0.13, 95% CI=0.03-0.23; executive: β=0.10, 95% CI=0.01-0.19).Higher BHS in mid-to-late life was associated with better digital and traditional NP performance more than a decade later. These findings support the potential of EEG-derived, data-driven scores as a biomarker of future cognitive health.

  View details for DOI 10.1093/sleep/zsag100

  View details for Web of Science ID 001756243900001

  View details for PubMedID 41964500

• Facility-measured sleep electroencephalographic microstructures in long COVID SLEEP Sun, H., Dang, R., Li, P., Xiao, W., Scott-Sutherland, J., Sassower, K. C., Westover, M., Felsenstein, D., Thomas, R. J., Haack, M., Mullington, J. M. 2026

  Abstract

  Sleep electroencephalographic (EEG) microstructures are related to brain functions, providing a window into the unrefreshing, non-restorative sleep and daytime fatigue symptoms in long COVID (LC) and myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS). We aim to characterize sleep EEG microstructural differences in individuals with LC and age-sex-matched healthy controls (HC), and also ME/CFS, using overnight in-lab facility-measured polysomnography (PSG).28 LC and 28 HC participants came from a single-center research study. 19 ME/CFS participants came from a single clinical center. Sleep EEG was processed to extract spectral band powers, spindles, slow oscillations (SO, 0.5-1 Hz), spindle-SO coupling, brain age index (BAI), alpha-delta patterns, and infraslow oscillation relative band power (ISO, 0.005-0.03 Hz).Compared to HC, LC had higher SO power during wake before sleep and REM sleep. In N2 and N3, LC showed a faster within-spindle frequency drop (chirp) and shorter SO peak duration in the frontal region. LC showed widespread, early spindle-SO coupling phase at SO trough for both fast and slow spindles, with early fast spindle-SO coupling associated with worse sleep quality. ME/CFS shared some differences with LC but had higher SO-uncoupled slow spindle densities in frontal and central regions, more alpha-delta patterns in the first half of the night, and widespread elevated ISO power in the slow sigma band (11-13 Hz).These findings suggest that LC and ME/CFS are associated with plausibly pathological sleep EEG microstructure changes, illuminating the pathobiology of post-infectious processes on brain activity.CLINICAL TRIAL INFORMATIONTrial 1: Sleep and Inflammatory Resolution Pathway, https://clinicaltrials.gov/study/NCT03377543, NCT03377543.Trial 2: Pain in Long COVID-19: the Role of Sleep, https://clinicaltrials.gov/study/NCT05606211, NCT05606211.

  View details for DOI 10.1093/sleep/zsag090

  View details for Web of Science ID 001754038800001

  View details for PubMedID 42017829

• IFCN position statement: use of artificial intelligence in clinical neurophysiology. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Husain, A. M., Beniczky, S., Bensalem-Owen, M., Bland, J., Brinkman, B. H., Hanajima, R., Holub, M., Jehi, L., Nandedkar, S., Shahrizaila, N., Tankisi, H., Tannemaat, M. R., Westover, M. B., Paulus, W. 2026: 2111893

  Abstract

  In recent years, artificial intelligence (AI) has made significant strides, gaining traction across various domains, including clinical medicine. The integration of AI as a decision-support tool introduces complexities, particularly in ensuring patient safety and upholding clinical accountability. This is especially pertinent in clinical neurophysiology (CNP), where AI shows promise in enhancing the interpretation of neurophysiologic data from modalities such as electroencephalography, electromyography, and others. Recognizing the potential and inherent challenges of AI integration, the International Federation of Clinical Neurophysiology (IFCN) has set forth guidelines to steer the responsible development, evaluation, and application of AI technologies in CNP. The IFCN's core position on AI in CNP emphasizes improving healthcare outcomes, prioritizing patient-centered care, maintaining transparency in AI-generated interpretations, and supporting, rather than replacing, clinical expertise. As AI technology evolves, the IFCN stresses that models implemented in clinical practice, especially when lacking supervision by experts must meet stringent standards for accuracy, safety, and quality control, and that AI cannot substitute expert care without adequate oversight. The successful integration of AI in CNP hinges on dataset diversity, transparent and ethical training practices, and balancing model complexity with real-world validation. Continuous performance monitoring and clinician feedback are vital to maintaining AI system reliability over time. The IFCN envisions a future where AI ethically enhances CNP practice through multidisciplinary collaboration, focusing on patient safety, clinical integrity, and scientific rigor. Properly implemented, AI can revolutionize CNP by offering real-time decision support, personalized interventions, and remote monitoring, thus advancing the quality of care in CNP.

  View details for DOI 10.1016/j.clinph.2026.2111893

  View details for PubMedID 42067415

• Connectome disruptions after hypoxic-ischaemic injury associate with consciousness disorder severity. Brain communications Hilger, S. G., Rosenthal, E. S., Kulpanowski, A. M., Dodelson, J. A., Cudemus-Deseda, G., Villien, M., Edlow, B. L., Januzzi, J. L., Ning, M., Kimberly, W. T., Amorim, E., Westover, M. B., Copen, W. A., Schaefer, P. W., Giacino, J. T., Greer, D. M., Wu, O. 2026; 8 (2): fcag117

  Abstract

  Accurate neuroprognostication of cardiac arrest survivors who are initially comatose after restoration of spontaneous circulation is crucial for guiding patient management. Because hypoxic-ischaemic injury is typically diffuse, damage to a network of brain regions is likely involved in the patient's disorder of consciousness. To quantify these complex brain network changes, graph theoretical methods were applied. We hypothesize that structural connectivity metrics may provide insights into which patients will likely recover consciousness. Eighteen comatose patients (50 ± 22 years, 44% male) and four healthy participants (40 ± 20 years, 50% male) underwent multi-shell high angular diffusion MRI as part of a prospective study. Structural connectivity matrices were constructed using probabilistic tractography to measure the likelihood of connections between anatomical regions. Network topology alterations were quantified using clustering coefficient, global efficiency and degree. Hub index analysis was performed to explore the impact of anoxic injury on high-degree hubs. Network parameters were compared between patients with arousal recovery (AR, eye-opening to auditory or noxious stimulation) and without arousal recovery (No AR). Analyses were repeated for AR patients who achieved emergence from the minimally conscious state (EMCS) within one-year post-cardiac arrest and AR patients who did not achieve EMCS (AR'). Significant differences were observed between the Controls, AR and No AR for all four metrics (Kruskal-Wallis Tests, P < 0.05). Worsening disorders of consciousness were associated with decreasing brain complexity (Kendall's tau, P<0.01). Post-hoc testing showed Control values were significantly greater than No AR for all metrics (Wilcoxon rank sum, P < 0.05). Control values were greater than AR for all metrics (P < 0.05), except the clustering coefficient (P = 0.36). AR was significantly greater than No AR for all metrics (P < 0.05), except for the hub index (P = 0.12). Notable differences between AR' and Controls were observed for all metrics (P < 0.05), except clustering coefficient (P = 0.11). No significant differences were found between AR' and No AR groups. In contrast, for all metrics, EMCS values were not significantly different compared with the Controls but were significantly different than the No AR cohort values (P < 0.05). The hub index analysis revealed disproportionate damage to high-degree nodes such as the thalamus, putamen and precuneus, further linking topological disruption to the severity of outcomes. This study highlights the potential of graph theoretical measures of structural connectivity to guide decisions in the care of comatose cardiac arrest patients. By bridging structural connectivity with clinical outcomes, this research provides valuable insights into the neural mechanisms underlying consciousness and recovery after cardiac arrest.

  View details for DOI 10.1093/braincomms/fcag117

  View details for PubMedID 42051852

  View details for PubMedCentralID PMC13111490

• EEG in patients with altered mental status in the emergency department. International journal of emergency medicine Runcie, M., Nolan, N., Yoo, O., Silbergleit, R., Nascimento, F. A., Kennedy, M., Westover, M. B., Goldstein, J. N. 2026; 19 (1)

  Abstract

  Altered mental status is a common chief complaint in the emergency setting, and the initial evaluation often fails to find an etiology. Subclinical (electrographic) seizures and nonconvulsive status epilepticus (NCSE) are potential causes of delirium and altered mental status, but require electroencephalogram (EEG) for diagnosis. It is not clear how often subclinical seizure or NCSE is present in those with undifferentiated altered mental status, nor which patients are most likely to benefit from emergent EEG.We performed a retrospective review of patients presenting to a single academic medical center emergency department (ED) over a one-year period with the chief complaint of “altered mental status” who had an order placed for EEG while in the ED.During the study period 112 patients met inclusion criteria. Of the 112 patients, 10 (8.9%) had seizures observed on EEG. Of these patients with EEG-observed seizure, 4 (40%) had clinical correlates, whereas the remaining 6 (60%) had no clinical manifestation of seizure. Five (50%) had a final diagnosis of status epilepticus, all of which had subtle or absent clinical correlates qualifying for NCSE. Eighty-one (72%) patients had abnormal EEG findings, 27 (24%) of whom had epileptiform EEG findings without definitive seizure. The median times from ED presentation to EEG being ordered and completed were 6.4 and 20.9 h, respectively.EEGs obtained in patients with undifferentiated altered mental status are typically abnormal and are frequently of clinical importance. Seizure was observed in a substantial portion of these, often without clinical signs. The average time until EEGs were ordered and completed were about 6 and 20 h respectively; as a result, time sensitive clinical decisions that need to be made within 20 h may often be made without information from the EEG. More urgent EEG may benefit patients with altered mental status of unclear etiology in the ED.

  View details for DOI 10.1186/s12245-026-01200-6

  View details for PubMedID 41928084

  View details for PubMedCentralID PMC13173918

• Does Missing Medication Acutely Change Seizure Risk? A Prospective Study. Annals of neurology Goldenholz, D. M., Cheng, J. C., Chang, C. Y., Moss, R., Westover, M. B. 2026; 99 (4): 1076-1082

  Abstract

  The objective of this study was to determine whether missing individual doses of anti-seizure medications (ASMs) elevate short-term seizure risk in people with drug-resistant epilepsy.In a prospective, community-based cohort, adults with drug-resistant epilepsy (≥ 3 seizures/month) or their caregivers recorded seizures and ASM intake with smartphone applications for 10 months each. Individual level analysis modeled the relationships between ASM adherence with seizure occurrence, as well as with a simplified seizure forecast via a 90-day moving average ("Napkin method"). Group-level analysis with a mixed-effects model was performed to examine the relationship between ASM adherence and simplified forecasts, while controlling for differences in individual seizure frequency via random effects.Twenty-seven participants (median age = 29 years) contributed 7,853 person-days. Individual analysis showed that only a small (n = 2) number of participants had a weak relationship between ASM adherence with seizure occurrence. Group-level analysis showed that seizure occurrence was highly linked to the Napkin method, but not ASM adherence.Among individuals with frequent, drug-resistant epilepsy, occasional missed ASM doses did not measurably raise immediate seizure risk. Whereas sustained nonadherence remains a clinical concern, clinicians may reassure patients that infrequent brief lapses are unlikely to trigger seizures acutely, yet they should continue emphasizing overall adherence for long-term seizure control. ANN NEUROL 2026;99:1076-1082.

  View details for DOI 10.1002/ana.78134

  View details for PubMedID 41489031

  View details for PubMedCentralID PMC12782288

• Electroencephalogram Monitoring in Critical Care: Multicenter Analysis of Timing, Duration, and Readmissions. Critical care explorations Tăuțan, A. M., Sarami, M., Sartipi, S., Turley, N., Gupta, A., Ghanta, M., Fernandes, M. P., Mitra, A., Kim, J., Struck, A. F., Westover, M. B., Zafar, S. F. 2026; 8 (4): e1402

  Abstract

  Gaining insights into acute and critical care electroencephalogram (EEG) practice patterns can enable more efficient resource utilization without compromising care quality.We aimed to identify factors associated with the timing of EEG initiation during acute care hospitalizations, the duration of EEG monitoring, and hospital readmissions with EEG monitoring.This is a retrospective cohort study of inpatient admissions to three academic medical centers between 2009 and 2024. Patients were included if older than 18 years and underwent EEG monitoring (routine or long-term) during the hospitalization. Demographic and clinical variables were extracted, along with admission information, primary diagnosis defined by the International Classification of Diseases (ICD), 9th Edition and 10th Edition codes, drug administration, and characteristics of EEG use: timing of EEG initiation during hospitalization, duration of monitoring, presence of seizures, and rhythmic and periodic patterns (RPPs). Descriptive statistics and regression analysis were performed.Our outcome measures were: 1) time to EEG monitoring relative to the day of admission (hr), 2) duration of monitoring (hr), and 3) readmissions with EEG monitoring within 12 months of the first admission.A total of 34,773 patients met the inclusion criteria. The most frequent primary neurologic admission diagnosis based on ICD codes were seizures/status epilepticus (n = 3219, 9.26%), traumatic brain injury (n = 1825, 5.25%), and ischemic stroke (n = 1787, 5.14%). The most frequent nonneurologic primary diagnostic category was toxic-metabolic disease and altered mental status (n = 6798, 19.55%). Key covariates associated with earlier EEG monitoring during the index admission were primary diagnostic categories of cardiac arrest/anoxic brain injury and seizures/status epilepticus. A diagnosis of aneurysmal subarachnoid hemorrhage, electrographic seizures, and lateralized periodic discharges were associated with longer durations of monitoring. Patients with a diagnosis of sepsis had later and shorter duration of monitoring. Factors associated with readmissions with EEG monitoring included a primary index admission diagnosis of seizures/status epilepticus and brain tumors. Presence of electrographic seizures, RPPs was associated with longer monitoring duration (29.03 hr; interquartile range [IQR], 3.43-73.80 hr). However, even among patients without seizures or RPPs, the median duration of monitoring was 16.78 hours (IQR, 0.82-37.34 hr).Characterizing EEG utilization patterns in critically ill patients allows identification of potential areas for practice optimization. Patients admitted with primary nonneurologic diagnoses underwent EEG monitoring later and for shorter durations compared with those admitted with primary neurologic conditions. These findings suggest opportunities to refine EEG triage and resource allocation, including earlier initiation of monitoring in nonneurologic patients at elevated seizure risk (e.g., sepsis) and timely discontinuation of EEG in patients without seizures or RPPs.

  View details for DOI 10.1097/CCE.0000000000001402

  View details for PubMedID 42012873

  View details for PubMedCentralID PMC13102442

• Multicenter evaluation of the Waveband System for automated sleep assessment in patients with insomnia symptoms. Sleep Savietto, S. F., Guillot, A., Harris, M., Pathmanathan, J., Chan, A. M., Westover, M. B., Hill, D., Bertaina-Anglade, V., Viardot, G., Arnal, P., Donoghue, J. 2026

  Abstract

  This study (Octave-3) aimed to validate the performance of the Waveband dry-EEG sensor device for automatic sleep staging and sleep parameter estimation as compared to gold-standard in-lab polysomnography (PSG).45 participants were enrolled and 38 completed simultaneous PSG and Waveband recordings. PSG data was scored by 6 human technologists while Waveband data was scored algorithmically. Agreement between sleep staging results and derived sleep parameters (total sleep time (TST), sleep efficiency (SE), sleep onset latency (SOL), wake after sleep onset (WASO), and time spent in each sleep stage) was measured using the Intraclass Correlation Coefficient (ICC) and Overall Agreement (OA). Waveband OA was compared to each human rater using the leave one out consensus of the remaining 5 human experts.Average OA between Waveband vs the leave one out consensuses was 87.3+/-5.4%, equivalent to the average OA for individual human experts of 85.9+/-7.6% (p>.1). Waveband and humans had better OA over the second half of the night, but Waveband had superior OA. ICCs for TST, SE, LPS, and WASO exceeded 0.9, indicating excellent agreement between automated Waveband and human PSG scoring. Lower agreement was found for time spent in N1, N3, and REM, with ICCs ranging from 0.65 to 0.73.Waveband provides accurate sleep staging and estimation of TST, SE, SOL, LPS, and WASO, with comparable performance to human expert staging of PSG. Its reduced form-factor and good performance should make it a valuable tool for automated assessment of sleep in patients with disturbed sleep.

  View details for DOI 10.1093/sleep/zsag069

  View details for PubMedID 41903179

• Pediatric SleepNet: A Deep Learning Network for Reliable Pediatric Sleep Staging Across Developmental Stages. Sleep Tripathi, A., Gupta, A., Ganglberger, W., Waters, S., Sun, H., Nasiri, S., Mitra, A., Stone, K. L., Mignot, E., Hwang, D., Reyna, M. A., Trotti, L. M., Clifford, G. D., Maski, K., Katwa, U., Thomas, R. J., Westover, M. B. 2026

  Abstract

  Manual sleep staging in pediatric populations is challenging due to developmental variability and limited scoring consistency, especially in infants and toddlers. We developed a multimodal deep learning model for pediatric sleep staging and evaluated its performance across a broad age range and diverse clinical subgroups.We trained a U-Net-inspired encoder-decoder model (pediatric SleepNet) using 9-channel input signals: Electroencephalography (EEG), Electrooculography(EOG), and chin Electromyography (EMG) using 35-epoch segments from clinical pediatric polysomnograms (PSGs). Models were trained separately on three age groups (<6 months, 6-12 months, >1 year) using 9,150 PSGs, with 2,455 PSGs reserved for validation. Evaluation was conducted on 3,804 held-out test recordings. Performance was compared with U-Sleep and the Complete Artificial Intelligence Sleep Report (CAISR), and stratified analyses were performed across ages, sexes, and seven ICD-10-based disease categories. External validation was conducted on two independent datasets, CHAT and PATS.pediatric SleepNet achieved robust performance across all age groups, with mean Cohen's Kappa increasing from 0.49 (0-6 months) to 0.72 (>12 years). It significantly outperformed U-Sleep and CAISR across early developmental stages. 3-class staging yielded mean Cohen's Kappa increasing from 0.66 (0-6 months) to 0.79 (>12 years). Sex-based differences were negligible. However, significant reductions in performance were observed in children with epilepsy, Down syndrome, hydrocephalus, and other neurodevelopmental conditions. External validation yielded Kappa values >0.69 comparable to the internal test set.pediatric SleepNet demonstrates reliable sleep staging across pediatric development. Its robust performance across age, disease, and external datasets supports its potential for clinical and research use in pediatric sleep medicine.

  View details for DOI 10.1093/sleep/zsag064

  View details for PubMedID 41804802

• Inferring preoperative cognitive function from intraoperative electroencephalography in elderly patients using machine learning. IEEE transactions on bio-medical engineering Pedemonte, J. C., Sun, H., Freedman, I. G., Turco, I., Wiredu, K., Penna, A., Egana, J. I., Gutierrez, R., Ibacache, M., Cortinez, L. I., Westover, M. B., Akeju, O., Boncompte, G. 2026; PP

  Abstract

  To develop and evaluate machine learning (ML) models that infer preoperative cognitive function from intraoperative electroencephalography (EEG). This was a retrospective ML study that used a training dataset derived from the MINDDS study (306 patients, USA), and an external testing dataset from the Electroencephalographic Biomarker to Predict Acute Post-Operatory Cognitive Dysfunction study (92 patients, Chile). Both contained patients older than 60 years undergoing either cardiac (training dataset) or non-cardiac (testing dataset) surgery under general anesthesia. Preoperative cognitive function was assessed using the Montreal Cognitive Assessment (MoCA) in both cohorts. Four types of ML models were used: logistic regression with L2 penalty, random forest, gradient boosting tree, and extreme gradient boosting. Models were evaluated in terms of weighted root mean square error (WRMSE) and monotonic correlations towards actual MoCA scores (Spearman's rho). A logistic regression model with L2 regularization performed best in the training dataset (WRMSE 2.82 [2.60 - 3.03 95%CI], Spearman's rho 0.18 [0.06 - 0.29], p 0.0015). This performance mostly generalized to the test dataset (WRMSE 2.72 [2.51 - 2.94], Spearman's rho 0.14 [-0.05 - 0.31], p 0.18). This study shows that ML models trained on intraoperative EEG can effectively infer preoperative cognitive function in older patients, with generalizability across distinct populations and relatively low error (<3 MoCA points). However, the correlations were weak, indicating limited ability to capture consistent monotonic relationships. Incorporating this approach into perioperative care could enable early detection and mitigation of neurocognitive disorders, improving surgical outcomes through tailored interventions. Further refinement and validation are required before clinical implementation.

  View details for DOI 10.1109/TBME.2026.3671187

  View details for PubMedID 41790820

• Inter-Rater Reliability of EEG-Based Encephalopathy Grading JOURNAL OF CLINICAL NEUROPHYSIOLOGY Tesh, R. A., Zahoor, A., Banks, J., Gallagher, K., Eckhardt, C. A., Sun, H., Karakis, I., Katyal, R., Williams, J., Nayak, C., Herlopian, A., Ng, M. C., Greenblatt, A. S., Meyers, E., Westmeijer, M., Harrison, D. S., Ganglberger, W., Gheihman, G., Fan, T., Struck, A. F., Sheikh, I. S., Nascimento, F. A., Westover, M. 2026; 43 (3): 237-244

  Abstract

  Visual EEG Confusion Assessment Method-Severity (VE-CAM-S) quantifies encephalopathy severity based on electroencephalography features. This study evaluated inter-rater reliability among experts using the VE-CAM-S scale.Nine experts from six institutions independently reviewed 32 15-second electroencephalography samples in an online test, assessing 29 features (16 in the VE-CAM-S and 13 additional, or "VE-CAM-S+"). A consensus of three experts served as the gold standard. Performance was measured by the median Matthews correlation coefficient between expert and gold-standard VE-CAM-S+ scores, along with average sensitivity and specificity. Qualitative analysis identified common feature-recognition errors affecting scores.Experts achieved a median Matthews correlation coefficient of 0.82 [95% CI: 0.74-0.99]. Specificity exceeded 90% for most features except background β (87%) and generalized delta (71%). Sensitivity was ≥65% except for burst suppression with epileptiform activity (61%), extreme delta brush (EDB; 61%), posterior dominant rhythm (50%), background α (59%) and β (42%). Common errors included missing subtle findings, confusing features, and misidentifying extreme delta brush.This pilot study offers some initial support for the reliability of VE-CAM-S+ scoring. The largest errors occurred when experts missed or falsely identified features with higher weight in the VE-CAM-S. Encephalopathy grading through VE-CAM-S may be improved by breaking high-stakes features into smaller parts, creating a "cheat sheet" with scored examples, and designing teaching materials.

  View details for DOI 10.1097/WNP.0000000000001185

  View details for Web of Science ID 001705177000010

  View details for PubMedID 40601962

  View details for PubMedCentralID PMC12335890

• Brain Health from Sleep EEG: A Multicohort, Deep Learning Biomarker for Cognition, Disease, and Mortality. NEJM AI Ganglberger, W., Sun, H., Turley, N., Tripathi, A., Hadar, P., Gupta, A., Gallagher, K., Tesh, R., Kim, S., Nasiri, S., Leng, Y., Harrison, S., Stone, K. L., Hughes, T., Redline, S., Au, R., Manoach, D. S., Landolt, H. P., Huber, R., Mignot, E., Shin, C., Cash, S. S., Thomas, R. J., Westover, M. B. 2026; 3

  Abstract

  Sleep underpins cognition, disease prevention, and overall brain health, yet objective, integrative biomarkers of brain health remain lacking. We hypothesized that overnight sleep electroencephalography (EEG) could provide a substrate for such a biomarker. We asked whether a newly developed, end-to-end, data-driven deep learning framework for sleep EEG can learn a latent representation of brain health and distill it into a single score relevant to cognition, disease status, and mortality.We analyzed 36,000 polysomnography recordings from 27,000 subjects from six cohorts. EEG data were represented as one-dimensional time series or a two-dimensional time-frequency spectrogram. A multitask deep neural network, trained end-to-end without expert-defined features, learned a 1024-dimensional brain health latent space and jointly predicted cognitive performance, disease status, and sleep metrics. The latent representation was additionally distilled into a single brain health score. We compared performance with demographic baselines, conventional EEG metrics (e.g., rapid eye movement fraction, spindle density), and classic multivariate machine learning approaches.The deep learning-derived brain health scores consistently surpassed demographic and expert-defined EEG feature models. For cognitive outcomes, correlations (r) rose from small (demographic-only) to moderate (up to r=0.40), while disease classification areas under the receiver operator curve improved from 0.50-0.55 at baseline to 0.65-0.75. In age-adjusted Cox models, a one-standard-deviation increase in the brain health score was associated with a 31%-35% reduced risk of mortality (hazard ratio 0.65 to 0.69; P<0.0001), topping conventional EEG metrics. Gains over classic machine learning, plus latent space visualization, indicated that both established physiological markers and novel EEG features drove enhanced performance.A multitask, end-to-end deep learning approach generated an interpretable, sleep-derived brain health biomarker. By modeling cognition, disease, and mortality, this framework provides a robust index of brain health and may be extended to additional modalities, further enhancing its clinical utility. (Funded by the National Institutes of Health and others.).

  View details for DOI 10.1056/aioa2500487

  View details for PubMedID 41953210

  View details for PubMedCentralID PMC13055923

• The Harvard-Emory ECG Database. Scientific data Koscova, Z., Li, Q., Robichaux, C., Junior, V. M., Ghanta, M., Gupta, A., Rosand, J., Aguirre, A. D., Reinertsen, E., Song, S., Hong, S., Albert, D. E., Xue, J., Parekh, A., Sameni, R., Reyna, M. A., Westover, M. B., Clifford, G. D. 2026; 13 (1)

  Abstract

  The Harvard-Emory ECG Database (HEEDB) is currently the largest open-access collection of 12-lead electrocardiogram (ECG) recordings, developed through a collaboration between Harvard and Emory University. The database consists of 10,608,417 ECG recordings from 1,818,247 patients from Massachusetts General Hospital (MGH) and 998,844 recordings from 349,548 patients from Emory University Hospital (EUH) collected between 1980 and 2022 in clinical settings as part of routine patient care. The ECGs are 10-second, 12-lead recordings sampled at either 250 or 500 Hz, and stored in WFDB format. Each ECG is linked to demographic metadata (age, sex, race, ethnicity, education), along with deidentified acquisition dates, last visit dates, and death dates, when available. The dataset includes three forms of MarquetteTM 12SL Analysis Software annotations: (1) batch-reprocessed diagnostic labels generated using the latest available 12SL software (version 24); (2) the original 12SL outputs from the time of ECG acquisition; and (3) the corresponding physician overreads. Additionally, the dataset includes associated ICD-9 and ICD-10 codes with the corresponding diagnosis dates. This database represents a large, diverse multi-center collection on which machine learning algorithms can be trained and tested for performance and bias.

  View details for DOI 10.1038/s41597-026-06861-9

  View details for PubMedID 41741499

  View details for PubMedCentralID PMC13046864

• An Electroencephalographic Study of Sleep Spindle and Infraslow Oscillation in Children With Autism Spectrum Disorder JOURNAL OF SLEEP RESEARCH Liu, K., Sun, B., Wang, B. K., Chen, J., Westover, M., Tian, F., Sun, H., Kong, X. 2026: e70309

  Abstract

  We investigated whether sleep microstructures show spatial differences in young children with autism compared with typically developing peers. 32-channel electroencephalography (EEG) during natural sleep after 5-6 h of partial sleep deprivation was recorded from 53 children (26 with autism, 27 typically developing; 1.1-5.1 years). Quantified EEG features included spindle density, frequency, morphology, slow oscillations and the relative power of infraslow oscillations (0.005-0.03 Hz). Clinical associations were examined using the Autism Diagnostic Observation Schedule, the Childhood Autism Rating Scale and the Gesell Developmental Schedules. Children with autism showed greater modulation of spindle frequency by the phase of slow oscillations at a right frontal scalp electrode (F8). An infraslow peak slightly below 0.02 Hz was present in both groups. Although group differences in infraslow power did not remain significant after correction for multiple comparisons, infraslow power correlated positively with autism severity in males, over posterior and temporal regions. These findings indicate that sleep microstructures in early childhood reflect thalamocortical and cortical dysfunction with sex-specific clinical associations.

  View details for DOI 10.1111/jsr.70309

  View details for Web of Science ID 001685952100001

  View details for PubMedID 41668405

• Health-oriented sleep states: making sleep states reflect health conditions. Sleep Sun, H., Ganglberger, W., Nasiri, S., Nassi, T. E., Meulenbrugge, E. J., Lam, A. D., Zafar, S., Gupta, A., Ghanta, M., Moura Junior, V. F., Shin, C., Au, R., Cash, S. S., Thomas, R. J., Westover, M. B. 2026; 49 (2)

  Abstract

  The rich information in sleep offers insights into brain function and overall health. The current guidelines for sleep staging by the American Academy of Sleep Medicine rely on relatively broad categorizations. These traditional sleep stages are not optimized to reflect health status. Here, we propose health-oriented sleep states to better associate with pre-existing health conditions.This observational retrospective cohort study involved 8673 participants from the Massachusetts General Hospital sleep laboratory. We examined seven pre-existing conditions: mild cognitive impairment, ischemic stroke, atrial fibrillation, myocardial infarction, type 2 diabetes, hypertension, and depression. We clustered a sleep staging model's hidden layer within each stage, where clusters represent sleep states. The number of sleep states was selected to maximize the average association with the health conditions, using the average area under the receiver operating characteristic curve across outcomes based on time spent in these states. We also assessed the area under the precision-recall curve.We identified three states within N3, 14 in N2, 6 in N1, 3 in R, and 9 in W. Average area under the receiver operating characteristic curve ranged from 0.608 to 0.723 across the seven outcomes, and area under the precision-recall curve from 0.064 to 0.524. Among these outcomes, mild cognitive impairment/dementia, atrial fibrillation, myocardial infarction, and hypertension demonstrated significantly stronger associations with the health conditions compared to conventional American Academy of Sleep Medicine sleep stages.Novel sleep states are linked to health conditions. A better understanding of the physiology behind these sleep states may further enhance the concept of using sleep as a window into overall health. Statement of Significance The conventional sleep staging describes sleep physiology rather than indicating health conditions. In contrast to the macrostructure (i.e. sleep stages), the microstructure of sleep, as reflected in multi-organ physiological signals during sleep, contains profound information about health. It would be a conceptual innovation to summarize the multi-organ microstructure of sleep into novel sleep states that better reflect health conditions than the current sleep stages. These sleep states should still align with the conventional sleep stages. We propose health-oriented sleep states, which are data-driven states optimized to associate with health conditions. This approach directly links health to sleep states and interprets them similarly to sleep stages, marking a significant step toward a more comprehensive understanding of the clinical relevance of sleep.

  View details for DOI 10.1093/sleep/zsaf229

  View details for PubMedID 40795277

• Unraveling sleep apnea dynamics: quantifying loop gain using dynamical modeling of ventilatory control. Sleep Nassi, T., Amidi, Y., Oppersma, E., Donker, D. W., Redeker, N. S., Westover, M. B., Thomas, R. J. 2026; 49 (2)

  Abstract

  Loop gain (LG) is a critical parameter for assessing ventilatory control stability in sleep apnea, with implications for personalized treatment. Existing LG estimation methods are hindered by complex processing and specialized equipment, limiting clinical applicability. This study aims to develop an automated method to quantify LG from respiratory inductance plethysmography (RIP) signals to enhance precision management of sleep apnea.Polysomnography data from Massachusetts General Hospital, high-altitude studies at Beth Israel Deaconess Medical Centre, and patients with heart failure were analyzed. Cases included an apnea-hypopnea index greater than 15 and greater than 4 h of recorded sleep. RIP signals were filtered, normalized, and segmented into 8-min windows. LG estimation employed an augmented Mackey-Glass equation and an expectation-maximization algorithm. Simulation experiments on synthetic breathing data with known parameter values quantified the accuracy of our parameter estimates.Data from 465 patients were analyzed, including 400 patients from the Massachusetts General Hospital dataset and 65 patients with heart failure. The method accurately estimated LG across diverse apnea phenotypes. Patients with a higher central apnea index, high self-similarity, or heart failure exhibited significantly higher median LG values (0.19, 0.27, and 0.41 respectively) compared to those with obstructive apnea (median LG = 0.11-0.14; p<.001). In addition, LG was significantly elevated during non-rapid eye movement sleep and at higher altitudes.The automated LG estimation method developed in this study provides a scalable, non-invasive tool for endotyping in sleep apnea. By accurately modeling patient-specific ventilatory control, this approach supports personalized management strategies in apnea and broader clinical contexts. Statement of Significance This study presents an innovative method for estimating ventilatory control stability using respiratory inductance plethysmography signals, offering a practical, scalable solution for routine clinical use. By enabling detailed characterization of ventilatory control dynamics, the method can differentiate sleep apnea phenotypes and identify patients at elevated risk of ventilatory instability. This has direct clinical implications, such as guiding personalized treatment strategies, predicting continuous positive airway pressure tolerance, and flagging patients for possible adjunctive therapies like oxygen supplementation or carbonic anhydrase inhibitors. Furthermore, the fully automated nature of our approach enables repeated assessments over time, facilitating longitudinal monitoring of treatment efficacy and disease progression. By advancing diagnostic precision and treatment tailoring, this innovation has the potential to improve the management of sleep-disordered breathing and related conditions.

  View details for DOI 10.1093/sleep/zsaf213

  View details for PubMedID 40704699

  View details for PubMedCentralID PMC12398341

• Strategies for Safer Cefepime Use to Prevent Neurotoxicity Using the Electronic Health Record. Critical care explorations Zafar, S. F., Park, H., Letourneau, A. R., Rock, A. E., Westover, M. B., Mukerji, S. S. 2026; 8 (2): e1380

  Abstract

  Cefepime, a cornerstone antibiotic in critical care, is associated with underrecognized cefepime-induced neurotoxicity (CIN), particularly in patients 65 years old and older. The true incidence is unknown due to inconsistent monitoring and a lack of diagnostic criteria. The recent Antibiotic Choice on Renal Outcomes (ACORN) trial underscored CIN's clinical significance, finding that cefepime recipients experienced 21% fewer delirium- and coma-free days than those on piperacillin-tazobactam. Current guidelines lack active surveillance recommendations, leading to delayed diagnosis and intervention. We propose three informatics-based strategies to address these challenges: 1) electronic health record (EHR)-integrated datasets utilizing machine learning and natural language processing to identify CIN at scale, 2) automated electroencephalogram tools to provide real-time alerts to clinicians, and 3) dynamic risk scores that continuously update from EHR data to guide prescribing. Implementing these safeguards to optimize CIN prevention, which may be relevant for other antibiotics with neurotoxicity risk, can improve neurologic outcomes and patient safety in critically ill populations.

  View details for DOI 10.1097/CCE.0000000000001380

  View details for PubMedID 41670408

  View details for PubMedCentralID PMC12900184

• The indispensable human factor in EEG-based artificial intelligence EPILEPSIA Nascimento, F. A., Westover, M. 2026; 67 (3): 1517-1518

  View details for DOI 10.1002/epi.70085

  View details for Web of Science ID 001669650900001

  View details for PubMedID 41579049

• Noise in the diagnosis of epilepsy by experts EPILEPTIC DISORDERS Nascimento, F. A., McLaren, J. R., Zhao, W., Katyal, R., Sheikh, I. S., Kong, W., Aljaafari, D., Barot, N., Benbadis, S., Friedman, D., Gavvala, J. R., Halford, J., Hogan, R., Kaplan, P. W., Karakis, I., Maheshwari, A., Matthews, R., O'donovan, C., Rampp, S., Schuele, S., Sirven, J., Tatum, W. O., Williams, J., Yacubian, E., Yuan, D., Beniczky, S., Sibony, O., Westover, M. 2026; 28 (2): 457-469

  Abstract

  To measure the relative levels of signal and noise in expert diagnosis of epilepsy.Twenty multinational epileptologists independently reviewed 50 vignettes of adult and pediatric patients presenting with suspected seizure(s) on two separate occasions with a ≥30-day washout period. Experts provided a diagnosis of epilepsy or non-epilepsy based on clinical information and, if requested, routine EEG and neuroimaging data. Cases had an established clinical diagnosis of epilepsy or non-epilepsy based on capture of habitual paroxysmal events on video-EEG or long-term clinical follow-up. Experts' judgments were analyzed to decompose variability into different sources: signal (objective differences between cases), level noise (experts' bias toward over/under-diagnosis), pattern noise (experts' idiosyncratic reactions to specific case features), and occasion noise (inconsistency across occasions).The probability of an expert making a different diagnosis for a given case on two different occasions was 16%. The probability of two different experts making a different diagnosis for the same case was 26%. Signal (case "difficulty") accounted for 66-69% of total variation, with 31-34% attributable to noise. Level noise was the largest contributor in the absence of EEG/neuroimaging results (23%), while pattern noise dominated when test results were available (24%). Occasion noise contributed relatively little (1%) but was still sufficient to cause diagnostic reversals in 16-22% between occasions.The degree of noise in expert diagnosis of epilepsy is substantial, stemming primarily from physicians' idiosyncratic interpretations of case features and variable dispositions toward over- or under-diagnosis. Strategies to improve reliability are needed, including standardized data collection protocols and structured decision algorithms. For "difficult cases," where expert reliability and accuracy are lowest, our findings support current clinical practice which favors early referral for video-EEG monitoring over reliance on diagnostic anchoring. This diagnostic pathway may become more accessible with advances in EEG technology (e.g., wearable devices) and artificial intelligence.

  View details for DOI 10.1002/epd2.70181

  View details for Web of Science ID 001665050300001

  View details for PubMedID 41556879

• A multimodal sleep foundation model for disease prediction. Nature medicine Thapa, R., Kjaer, M. R., He, B., Covert, I., Moore Iv, H., Hanif, U., Ganjoo, G., Westover, M. B., Jennum, P., Brink-Kjaer, A., Mignot, E., Zou, J. 2026

  Abstract

  Sleep is a fundamental biological process with broad implications for physical and mental health, yet its complex relationship with disease remains poorly understood. Polysomnography (PSG)-the gold standard for sleep analysis-captures rich physiological signals but is underutilized due to challenges in standardization, generalizability and multimodal integration. To address these challenges, we developed SleepFM, a multimodal sleep foundation model trained with a new contrastive learning approach that accommodates multiple PSG configurations. Trained on a curated dataset of over 585,000hours of PSG recordings from approximately 65,000 participants across several cohorts, SleepFM produces latent sleep representations that capture the physiological and temporal structure of sleep and enable accurate prediction of future disease risk. From one night of sleep, SleepFM accurately predicts 130 conditions with a C-Index of at least 0.75 (Bonferroni-corrected P<0.01), including all-cause mortality (C-Index, 0.84), dementia (0.85), myocardial infarction (0.81), heart failure (0.80), chronic kidney disease (0.79), stroke (0.78) and atrial fibrillation (0.78). Moreover, the model demonstrates strong transfer learning performance on a dataset from the Sleep Heart Health Study-a dataset that was excluded from pretraining-and performs competitively with specialized sleep-staging models such as U-Sleep and YASA on common sleep analysis tasks, achieving mean F1 scores of 0.70-0.78 for sleep staging and accuracies of 0.69 and 0.87 for classifying sleep apnea severity and presence. This work shows that foundation models can learn the language of sleep from multimodal sleep recordings, enabling scalable, label-efficient analysis and disease prediction.

  View details for DOI 10.1038/s41591-025-04133-4

  View details for PubMedID 41495409

• The Predictive Power of Intraoperative EEG and Clinical Characteristics for Postoperative Delirium Following Cardiac Surgery. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Wiredu, K., Sun, H., Boncompte, G., Westover, M. B., Pedemonte, J. C., Akeju, O. 2026; 43 (1): 32-38

  Abstract

  Postoperative delirium is common and associated with poor postoperative outcomes. However, the predictive power of intraoperative electroencephalogram (EEG) features for postoperative delirium has not yet been well studied.Intraoperative EEG data from 261 patients who underwent major cardiac surgery were analyzed. Cases were identified using the Confusion Assessment Method. Predictive analytics for delirium outcome were performed using (1) only clinical data, (2) only EEG data, and (3) a combined list of important features from the first two stages.Eleven percentage of participants experienced postoperative delirium. The patients were generally older and had lower physical and cognitive function. EEG models were found to be highly specific but less sensitive in identifying delirium cases. The combined EEG-clinical model performed comparably to the clinical-only model (AUC = 80%) but outperformed the EEG-only model (AUC = 56%). After adjusting for clinical covariates, only interhemispheric mutual information remained significantly associated with delirium (OR = 2.29, p = 0.03), with a positive correlation with delirium severity (ρ = 0.18, P ≤ 0.01).This study enhances our understanding of delirium neurophysiology by emphasizing the role of intraoperative EEG as a marker of brain vulnerability. Although EEG may not constitute a standalone biomarker of delirium, it holds promise for delirium risk stratification.

  View details for DOI 10.1097/WNP.0000000000001146

  View details for PubMedID 41481100

• Association of Time to Continuous EEG Initiation With Outcomes in Critically Ill Patients. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Haider, M. A., Khalil, M. H., Fernandes, M. B., Westover, M. B., Zafar, S. F. 2026; 43 (1): 17-22

  Abstract

  Continuous electroencephalography (cEEG) is used in the critical care setting for seizure detection and treatment, sedation management, and ischemia detection. Further evidence is needed to support whether early cEEG use can improve outcomes. We examined whether time from admission to cEEG initiation affects outcomes.This is a single-center cohort study of critically ill adults (age > 18 years) who underwent cEEG monitoring within 7 days of admission from January to December 2019. Patients with anoxic brain injury were excluded. Time (hours) from admission to cEEG was recorded. Outcomes were in-hospital mortality and poor discharge modified Rankin Score (4-6). Results are reported as median [quartile range] and odds ratio (OR) [confidence intervals, CI].In total, 464 patients met eligibility. Median time to cEEG was 23 hours [13, 52]. On multivariable analysis, increasing time to cEEG was associated with discharge mortality (OR, 1.006 [CI, 1.0002-1.013], 0.1%/hour [CI, 0.02-0.2]) and poor outcome (OR, 1.013 [CI, 1.005-1.020], 0.2%/hour [CI, 0.07-0.3]). Median time to cEEG initiation in patients with clinical concern for seizures/status at presentation ( n = 121) was 12 hours [6, 17] and in patients without clinical concern for seizures at presentation ( n = 343) was 31 hours [18, 66]. In patients without clinical concern for seizures/status epilepticus at presentation, time to cEEG continued to be associated with mortality (OR, 1.007 [CI, 1.001-1.014)] and poor outcome (OR, 1.012 [CI, 1.003-1.021]).Increasing time to cEEG initiation was associated with higher mortality and worse outcomes. We hypothesize earlier cEEG results in timely interventions including treatment escalation and de-escalation that may improve outcomes.

  View details for DOI 10.1097/WNP.0000000000001161

  View details for PubMedID 40237584

• A Quantitative Electroencephalographic Index for Stroke Detection in Adults. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Caffarelli, M., Simmons, R., Tolokh, I., Karukonda, V., Guterman, E. L., Smith, W., Fox, C. K., Westover, M. B., Amorim, E. 2026; 43 (1): 23-31

  Abstract

  Electroencephalography (EEG) remains underutilized for stroke characterization. We sought to assess the performance of the EEG Correlate Of Injury to the Nervous system (COIN) index, a quantitative metric designed for stroke recognition in children, in discriminating large from small ischemic strokes in adults.Retrospective, single-center cohort of adults with acute (within 7 days) ischemic stroke who underwent at least 8 hours of continuous EEG monitoring in hospital. Stroke size was categorized as large or small based on a threshold of 100 mL using the ABC/2 approach. EEG data were processed on MATLAB. COIN was independently calculated from consecutive 4-second EEG epochs. Student t-test and logistic regression were used to assess COIN performance in stroke size discrimination across the entire recording; random forest classification was used to determine COIN performance in limited EEG time windows ranging from 5 to 30 minutes in duration.Thirty-five patients with mean age 67 (SD ± 17) years were analyzed with mean 4.5 ± 1.3 hours of clean EEG per patient. Ten patients had large stroke and 25 had small stroke. Participants with large strokes had larger COIN values than those with small strokes (-53 vs. -16, P = 0.0001). Logistic regression for stroke size classification model showed accuracy 83% ± 8%, sensitivity 70%±15%, specificity 88%±8%, and area under the receiver operator curve 0.75±0.10. Random Forest Classification performance was similar using 5 or 30 minutes of EEG data with accuracy 81% to 82%, specificity 91% to 92%, and sensitivity 55% to 58%, respectively.COIN differentiated large from small acute ischemic strokes in this single-center cohort. Prospective evaluation in larger multicenter data sets is necessary to determine COIN utility as an aid for bedside detection of large ischemic strokes in contexts where neuroimaging cannot be easily obtained or when neurologic examination is limited by sedation or neuromuscular blockade.

  View details for DOI 10.1097/WNP.0000000000001151

  View details for PubMedID 40048377

  View details for PubMedCentralID PMC12360042

• Large-scale automated phenotyping of cardiac arrest and withdrawal of life-sustaining therapy using electronic health record data. Resuscitation Clive, C., Singh, A., Overmeer, B., Boris, S., Peterson, L., Searle, J., Hooke, G., Turley, N., Fernandes, M., Gupta, A., Ghanta, M., Junior, V. M., Mukeriji, S., Zafar, S., Amorim, E., Westover, M. B., Sun, H. 2026; 218: 110919

  Abstract

  Anoxic brain injury following cardiac arrest is a leading cause of death in the United States. Withdrawal of life-sustaining therapy (WLST) is a common end-of-life decision in these patients, but its contributing factors and outcomes remain poorly understood. We developed machine learning models to enable large-scale, automated phenotyping to identify patients who died following WLST.We used structured and unstructured EHR (Electronic Health Record) data from two major hospitals to train models that identify (1) patients with cardiac arrest and coma, and (2) patients who died after WLST. Performance was evaluated using the area under the receiver operating characteristic (AUROC) and precision-recall (AUPRC) curves, as well as other precision metrics.On holdout (internal) testing the models achieved AUROC/AUPRC values of 0.984/0.968 (cardiac arrest) and 0.992/0.991 (WLST). Cross-hospital evaluation showed strong performance for the cardiac arrest phenotype but variable generalizability for the WLST phenotype, with sensitivity depending on the training site. Population-level error rates were low (<0.5 %) for the cardiac arrest phenotype; estimates for WLST varied by hospital.These models establish a reproducible framework for automated cohort identification. Nearly half of comatose post-arrest patients died following WLST, with 42 % of these deaths occurring within 72 h, highlighting the impact of early prognostication decisions. The models enable rapid cohort identification for research on neuroprognostication, including how WLST decisions may perpetuate self-fulfilling prophecies. Broader validation across health systems and larger cohorts will improve generalizability and inform evidence-based end-of-life decision-making. Institutional review board approval: Mass General Brigham IRB BIDMC: 2022P000481; MGB: 2013P001024. All procedures complied with institutional and national ethical standards; informed consent was waived for use of de-identified data.

  View details for DOI 10.1016/j.resuscitation.2025.110919

  View details for PubMedID 41371332

• Deployable seizure forecasting requires clinically meaningful performance: Response to Stirling et al. EPILEPSIA Chang, C., Moss, R., Westover, M., Goldenholz, D. M. 2026; 67 (4): 1587-1588

  View details for DOI 10.1002/epi.70083

  View details for Web of Science ID 001651894300001

  View details for PubMedID 41474369

  View details for PubMedCentralID PMC12854151

• Is it possible to vaccinate AI against bias? An exploratory study in epilepsy. medRxiv : the preprint server for health sciences Bhansali, R. M., Westover, M. B., Goldenholz, D. M. 2025

  Abstract

  Large language models are increasingly used for clinical decision support yet may perpetuate socioeconomic biases. Whether simple prompt-based interventions can mitigate such biases remains unknown.To determine whether a prompt-based 'inoculation' instructing large-language-models (LLMs) to disregard clinically irrelevant information can reduce bias and improve accuracy in recommendations.Experimental study conducted November 21 to December 11, 2025. Each clinical vignette was presented 10 times per condition to account for stochastic variance.Publicly available web interfaces of six frontier LLMs with memory features disabled.No real patients were involved. Two fictional epilepsy vignettes (diagnostic and therapeutic) were created with identical clinical features but differing socioeconomic (SES) descriptors.Accuracy (proportion of responses concordant with guidelines) and bias (accuracy difference between high and low SES vignettes), assessed via binary scoring based on evidence-based guidelines.A total of 480 LLM responses were analyzed. For diagnosis, base accuracy was 36% (43/120), with 45 percentage point bias gap (high SES 58% vs. low SES 13%); inoculation improved accuracy to 55% (66/120) and reduced bias to 27 percentage points. For treatment, base accuracy was 51% (61/120) with 25 percentage point bias gap; inoculation improved accuracy to 63% (75/120) and reduced bias to 8 percentage points. Responses to inoculation varied considerably: Gemini 3 Pro showed complete diagnostic bias elimination (low SES accuracy 0% → 100%), while Sonnet 4.5 showed paradoxical worsening.A simple prompt-based intervention overall reduced socioeconomic bias and improved accuracy in LLM clinical recommendations, though effects varied across models. Prompt engineering may offer a practical approach to mitigating specific AI bias in healthcare.Question: Can a simple prompt-based "inoculation" instructing large language models to ignore clinically irrelevant socioeconomic details reduce bias and improve accuracy in epilepsy diagnosis and treatment recommendations?Findings: In this experimental study of 480 responses from 6 large language models to paired high- vs low-socioeconomic status epilepsy vignettes, base diagnostic and treatment accuracies were 36% and 51%, respectively, with bias gaps of 45 and 25 percentage points, respectively; adding an inoculation prompt increased accuracy to 55% and 63% and reduced bias gaps to 27 and 8 percentage points, though effects varied by model, with some showing near-complete bias elimination and others demonstrating paradoxical worsening in certain conditions.Meaning: Prompt-based inoculation may offer a practical, low-cost strategy to partially mitigate socioeconomic bias and modestly improve the quality of large language model clinical recommendations, but model-specific behavior and residual disparities highlight the need for ongoing oversight and complementary bias-mitigation strategies.

  View details for DOI 10.64898/2025.12.18.25342563

  View details for PubMedID 41445654

  View details for PubMedCentralID PMC12723972

• Automated estimation of frequency and spatial extent of periodic and rhythmic epileptiform activity from continuous electroencephalography data. Journal of neural engineering Tăuțan, A. M., Jing, J., Basovic, L., Hadar, P. N., Sartipi, S., Fernandes, M. P., Kim, J., Struck, A. F., Westover, M. B., Zafar, S. F. 2025; 22 (6)

  Abstract

  Objective.Rhythmic and periodic patterns (RPPs) are harmful brain activity observed on electroencephalography (EEG) recordings of critically ill patients. This work describes automatic methods for detection of the frequency and spatial extent of specific RPPs: lateralized and generalized rhythmic delta activity (LRDA, GRDA) and lateralized and generalized periodic discharges (LPD, GPD).Approach.The frequency and spatial extent of RPPs is estimated using signal processing and rule-based logic. Three algorithm variants based on fast Fourier transform (FFT) and Hilbert-Huang transforms (HHT) were developed for rhythmic delta activity, and three using derivative and time-based peak detection for periodic discharges. Annotations from three expert neurophysiologists served as the gold standard, and inter-rater reliability (IRR) and mean absolute error (MAE) were used to assess performance.Main results.We evaluated the algorithms on segments with 100% agreement on event classification (n= 389) and on the full cohort of 1087 segments (including disagreements). For the first subset, top algorithms matched or exceeded expert agreement for RPP frequency/spatial extent. RDA1b-FFT, the best algorithm for rhythmic delta activity, showed an expert-algorithm IRR of good to excellent with an intra-class correlation coefficient (ICC) of 91% and 96% (MAE 0.13 Hz and 0.26 Hz) frequency, and ICCs of 85% and 66% (MAE 0.19 and 0.09) for spatial extent for LRDA and GRDA. For periodic discharges, PD2a, showed and expert-algorithm IRR ICC of 80% and 61% (MAE 0.41 Hz and 0.15 Hz) for frequency, and ICC 77% and 13% (MAE 0.17 and 0.40) for spatial extent of LPD and GPD. For the full cohort, IRR declined, but expert-algorithm IRR remained comparable or superior to experts.Significance.The presence of RPPs at high frequencies and spatial extent are associated with a higher probability of poor outcomes. The proposed algorithms for estimating frequency and spatial extent of RPPs match expert performance and are a viable tool for large-scale EEG analysis.

  View details for DOI 10.1088/1741-2552/ae2716

  View details for PubMedID 41330044

• The EEG Talk experience: Lessons in e-teaching EEG. Epileptic disorders : international epilepsy journal with videotape Nascimento, F. A., Yuan, D., Sheikh, I. S., Hirsch, L. J., Beniczky, S., Westover, M. B. 2025; 27 (6): 1337-1339

  View details for DOI 10.1002/epd2.70096

  View details for PubMedID 40904123

• Conventional clinical characteristics do not predict the result of genetic testing in adults with epilepsy. Seizure Zhao, W., Ting, Y. L., Marcinski Nascimento, K. J., Poll, S. R., Pineda Alvarez, D. E., Westover, M. B., Nascimento, F. A. 2025; 133: 157-160

  Abstract

  Genetic testing in epilepsy has become increasingly available, and recommendations for its use have been set forth by professional society guidelines. The development of a user-friendly risk prediction model may aid providers in selecting adult patients with a high likelihood of receiving a positive genetic test result.Adults who underwent multigene panel testing for epilepsy from March 2016 to June 2024 were divided into a training (n = 1449) and a testing set (n = 1450). We developed prediction models based on clinical characteristics using logistic regression and FasterRisk scores for positive genetic tests and evaluated their performance.The prediction models had poor discriminative power and failed to predict positive results, suggesting that conventional clinical characteristics (sex, intellectual disability, developmental delay, autism, medically refractory epilepsy, family history of epilepsy, and age at seizure onset) are insufficient for selecting patients for genetic testing.Our findings suggest that routine genetic testing may be broadly warranted for adults with unexplained epilepsy, as clinical characteristics alone appear unable to reliably identify which patients are likely to have positive results on multigene panels. Future models may benefit from incorporating physical exam findings, neuroimaging, and electroencephalogram data, as well as larger training sets.

  View details for DOI 10.1016/j.seizure.2025.10.015

  View details for PubMedID 41637156

• Late-onset unexplained epilepsy as a risk factor for cognitive impairment and dementia: Protocol for a multi-center prospective longitudinal observational study (ELUCID) EPILEPSIA OPEN Lam, A. D., Johnson, E. L., Sarkis, R. A., Blank, L. J., Gaston, T. E., Shafi, M. M., Zepeda, R., Pellerin, K. R., Jette, N., Greve, D. N., Chibnik, L. B., Amariglio, R. E., Marshall, G. A., Westover, M. 2026; 11 (1): 363-375

  Abstract

  Late-onset unexplained epilepsy (LoUE), defined as epilepsy onset after age 55 without an obvious cause, is an important risk factor for dementia. Studies have shown that 10%-25% of individuals with LoUE develop dementia within 3-4 years following their first seizure. However, the mechanisms underlying progression from LoUE to dementia remain poorly understood. The goals of the ELUCID study are to identify risk factors associated with the development of cognitive decline and dementia in LoUE and to develop tools to identify patients at a high risk for these outcomes and thereby establish a foundation for dementia prevention strategies in this population.ELUCID is a multi-center prospective longitudinal observational study that will enroll 600 participants aged 55 or older with LoUE across seven U.S. medical centers. Participants will undergo a baseline evaluation that includes a detailed clinical history, cognitive testing, brain MRI, overnight scalp EEG, and blood biomarkers. Participants will be followed at 6-month intervals for up to 5 years, to record cognitive and neurological changes, with the primary outcomes of interest being the development of mild cognitive impairment and/or dementia. This study aims to establish LoUE disease subtypes based on biomarkers, cognitive trajectories, and imaging features and to develop a risk stratification tool for predicting cognitive decline and dementia in patients presenting with LoUE.ELUCID has obtained IRB approval (no. 2023P001566, August 2023), with the Mass General Brigham IRB serving as the single IRB of record. All de-identified study data will be made publicly available on completion of the study.The ELUCID study is a research project involving several medical centers across the U.S. It will focus on older adults who have recently developed seizures without a clear cause. Participants undergo an initial evaluation that includes questions about their medical history, a brain MRI, an overnight scalp EEG (brain wave study), and a blood draw. They will be followed over time with health questionnaires and yearly tests of memory and thinking. The purpose of the study is to learn what factors increase the risk of dementia in this population and to develop tools to predict which individuals are at the highest risk.

  View details for DOI 10.1002/epi4.70184

  View details for Web of Science ID 001627754800001

  View details for PubMedID 41317246

  View details for PubMedCentralID PMC12903818

• Predicting Post-Traumatic Epilepsy with Automated Contusion Measurements using Acute CT Images: A Competing Risk Approach. medRxiv : the preprint server for health sciences Ayvaz, B. B., Wheelock, J. R., Jin, D. S., Appleton, J., Snider, S. B., Torres-Lopez, V., Shrishail, N., Sanders, W., Doherty, D., Chow, K. T., Kim, J., Schlecter, M., Hirsch, L. J., Sivaraju, A., Westover, M. B., Zafar, S. F., Struck, A. F., Sheth, K. N., Omay, S. B., Edlow, B. L., Gilmore, E. J., Kim, J. A. 2025

  Abstract

  This study evaluates contusion volume and location as predictors of PTE while considering mortality as a competing risk using automated segmentation of acute CT images.Adult TBI patients who visited our center (2014-2025) were identified and categorized into three outcome groups: PTE, post-TBI mortality, and event-free. Clinical covariates were extracted from health records, and CT scans were processed using the BLAST-CT algorithm to segment intraparenchymal hemorrhage (IPH), edema, intraventricular (IVH), and extra-axial hemorrhage (EAH). Five-fold nested cross-validation was performed, with L1-regularized regression used for feature selection within each training fold and model performance evaluated in the corresponding test fold. Within each fold, the selected features were then used to fit separate cause-specific multivariable Cox models for PTE and mortality. Contusion location associations were assessed using both multivariable Cox and sparse canonical correlation analysis.Of 1017 identified patients, 6.1% developed PTE, 10.5% died, and 83.4% had no event. In multivariable analysis, total contusion volumes (p<0.001) were independently predicted both PTE and mortality, meanwhile and EAH volume (p<0.01) predicted mortality only. When regionalized, frontal (p<0.01) and temporal (p<0.01) contusions independently predicted PTE, whereas frontal (p=0.04) contusions also independently predicted mortality. Sparse canonical correlation analysis identified an association of frontotemporal and insular contusions with PTE but not mortality.Automatically measured contusion segmentation from acute CT imaging could help predict post-traumatic epilepsy. A competing risk framework highlighted that contusion volume is associated with both PTE and mortality risk, whereas unique contusion location patterns may aid in post-traumatic epilepsy assessment in a broad TBI population.

  View details for DOI 10.1101/2025.11.25.25341016

  View details for PubMedID 41358320

  View details for PubMedCentralID PMC12676554

• From Clinical Narrative to Diagnosis: Scalable Identification of Acquired Epilepsy. medRxiv : the preprint server for health sciences Wheelock, J. R., Fernandes, M. B., Chen, Y., Ayvaz, B. B., Jin, D. S., Zubair, A., Wan, M., Appleton, J., Zafar, S. F., Struck, A. F., Hirsch, L. J., Sivaraju, A., Gilmore, E. J., Westover, M. B., Kim, J. A. 2025

  Abstract

  Acquired epilepsy is a disabling, potentially preventable complication of acute brain injury (ABI). Yet, it remains a leading cause of new onset epilepsy in adults. Acquired epilepsy is a particularly challenging subtype of epilepsy to identify, as the ABI and its acute consequences can confound the later diagnosis of acquired epilepsy. We identified a retrospective cohort of patients with ABI (N=828) and optimized a general epilepsy algorithm to extract relevant keywords. We confirmed that applying a broad epilepsy phenotyping algorithm to a high risk, complex population like acute brain injured patients results in a high number of false positives. We developed multivariate models to identify ABI-acquired epilepsy 1) at the patient level using temporal trends, and 2) the note-level using keywords. Our models achieved high performance in both internal and external validation cohorts. Note-level re-classification also allowed for an estimation of time to epilepsy onset. This work enables large-scale, retrospective studies of ABI-acquired epilepsy across sites. Large-scale implementation may provide insights into acquired epilepsy epidemiology, identification of novel epilepsy risk factors and ultimately new treatments.

  View details for DOI 10.1101/2025.11.04.25339484

  View details for PubMedID 41282888

  View details for PubMedCentralID PMC12637739

• Electroencephalography in Clinical Practice: Neurology Professionals' Views on Optimal Standards of Care. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Nascimento, F. A., Katyal, R., Kass, N. R., Yuan, D., Sirven, J. I., Westover, M. B., Beniczky, S. 2025; 42 (7): 639-642

  Abstract

  Delivering optimal care to patients with seizures and epilepsy requires all EEGs to be interpreted accurately and reliably. This study investigated neurology professionals' opinions on the ideal standards for EEG in clinical care.We developed an anonymous e-survey targeting practicing and trainee neurologists focused on participants' demographics, clinical practice characteristics, and views on optimal EEG standards of care-including whether an EEG certification test is needed and whether postresidency/fellowship training in EEG/epilepsy is necessary for neurologists who interpret outpatient/routine EEGs in practice. The survey was hosted by the Neurology Clinical Practice-Practice Current, and it was distributed online through the American Academy of Neurology, American Epilepsy Society, American Clinical Neurophysiology Society, and International League Against Epilepsy, and through social media.Two hundred eighty-three responses were included: 119 from EEG/epilepsy-trained neurologists, 83 from non-EEG/epilepsy-trained neurologists, 75 from trainees, and 6 from advanced care providers. Most participants (78%) agreed that "an objective certification test of ability to interpret EEGs is needed for all those who interpret EEGs in clinical practice." Most participants (71%) believed that outpatient/routine EEGs may be read only by neurologists with EEG/epilepsy training; this opinion was more prevalent among EEG/epilepsy-trained (83%) versus non-EEG/epilepsy-trained neurologists (55%).Our neurology community should discuss the need to develop and implement a certification test of ability for all neurologists who wish to interpret EEGs in clinical practice. In addition, it is imperative to improve in-residency EEG education to ensure that neurology graduates achieve EEG competence before entering the workforce.

  View details for DOI 10.1097/WNP.0000000000001142

  View details for PubMedID 39820182

• Prediction of postoperative delirium in older adults from preoperative cognition and occipital alpha power from resting-state electroencephalogram. Age and ageing Ning, M. H., Rodionov, A., Ross, J. M., Ozdemir, R. A., Burch, M., Lian, S. J., Alsop, D., Cavallari, M., Dickerson, B., Fong, T., Jones, R. N., Libermann, T., Marcantonio, E., Santarnecchi, E., Schmitt, E. M., Touroutoglou, A., Travison, T., Acker, L., Smith, M. R., Sun, H., Westover, M. B., Pascual-Leone, Á., Berger, M., Inouye, S. K., Shafi, M. 2025; 54 (11)

  Abstract

  Postoperative delirium is the most common complication following surgery amongst older adults, and has been consistently associated with increased mortality and morbidity, cognitive decline, loss of independence and increased health-care costs. We sought to identify preoperative predictors that could identify individuals at high risk for postoperative delirium, which could guide clinical decision-making and enable targeted interventions to potentially decrease delirium incidence and postoperative delirium-related complications.Preoperative resting-state electroencephalograms (EEGs) and the Montreal Cognitive Assessment were collected from a prospective observational cohort of 85 older adults (12 cases of delirium) undergoing elective surgery. Four machine learning models were tested and the model with the highest f1-score was subsequently validated in an independent, prospective cohort of 51 older adults (6 cases of delirium) undergoing elective surgery.Occipital alpha powers have higher f1-score (0.57 ± 0.07) than frontal alpha powers (0.47 ± 0.07), EEG spectral slowing (0.48 ± 0.08), or modelling of EEG power spectral density into periodic and aperiodic components (0.44 ± 0.09) in the training cohort. Occipital alpha powers plus cognitive scores were able to predict postoperative delirium with area under the receiver operating characteristic curve (AUC) (0.94, 95% CI: [0.86-0.99]), sensitivity (0.83, 95% CI: [0.50-1.00]) and specificity (0.91, 95% CI: [0.82-0.98]) in the validation cohort, and outperformed models incorporating occipital alpha powers alone or cognitive scores alone.Whilst the sample size is small and findings require confirmation in larger studies, our results suggest that the thalamocortical circuit exhibits different EEG patterns under stressors, with occipital alpha powers potentially reflecting baseline vulnerabilities.

  View details for DOI 10.1093/ageing/afaf330

  View details for PubMedID 41222553

• Claims-Based Machine Learning Classifier of Modified Rankin Scale in Acute Ischemic Stroke JOURNAL OF THE AMERICAN HEART ASSOCIATION Habib, M., de Medeiros, R., Ahsan, S., Wojciechowski, A., Donahue, M. A., Blacker, D., Newhouse, J. P., Schwamm, L. H., Westover, M., Moura, L. R. 2025; 14 (20): e041635

  Abstract

  We developed a classifier to infer acute ischemic stroke severity from Medicare claims using the modified Rankin Scale at discharge. The classifier can be used to improve stroke outcomes research and support the development of national surveillance tools.This multistate study included all participating centers in the Paul Coverdell National Acute Stroke Program database from 9 US states. This database was linked to Medicare data sets for patients hospitalized with acute ischemic stroke, employing demographics, admission details, and diagnosis codes to create unique patient matches. We included Medicare beneficiaries aged 65 and older who were hospitalized for an initial acute ischemic stroke from January 2018 to December 2020. Using Lasso-penalized logistic regression, we developed and validated a binary classifier for modified Rankin Scale outcomes and as a secondary analysis we used ordinal regression to model the full modified Rankin Scale. Performance was evaluated on held-out test data using area under the receiver operator characteristic curve, receiver operator characteristic precision-recall, sensitivity, and specificity.We analyzed data from 68 636 eligible patients. The mean age was 79.5 years old. Seventy-seven and a half percent of beneficiaries were White, 14% were Black, 2.6% were Asian, and 2% were Hispanic. The classifier achieved an area under the receiver operator characteristic curve score of 0.86 (95% CI, 0.85-0.86), sensitivity of 0.81 (95% CI, 0.80-0.81), specificity of 0.73 (95% CI, 0.72-0.74), and precision-recall area under the curve of 0.90 (95% CI, 0.90-0.91) on the test set.Among Medicare beneficiaries hospitalized for acute ischemic stroke, the claims-based classifier demonstrated excellent performance in area under the receiver operator characteristic curve, precision-recall area under the curve, sensitivity, and acceptable specificity for modified Rankin Scale classification.

  View details for DOI 10.1161/JAHA.125.041635

  View details for Web of Science ID 001597653800001

  View details for PubMedID 41085187

  View details for PubMedCentralID PMC12684556

• Rigorous evaluation of five models for e-diary-only seizure forecasting: Retrospective and prospective datasets do not outperform the Napkin method EPILEPSIA Chang, C., Moss, R., Westover, M., Goldenholz, D. M. 2026; 67 (2): 753-761

  Abstract

  Seizure forecasting using e-diaries may help patients with seizures to organize their daily life. Until now, most methods were not rigorously tested against a strict standard. This study aims to assess whether the performance of various models for seizure forecasting using e-diaries is better than the performance of a moving window average (a.k.a. the Napkin method, due to simplicity of calculation).We analyzed three cohorts from Seizure Tracker: a retrospective study and two prospective studies. E-diaries and the type of seizures were extracted from the datasets. We implemented five machine learning models (Perceptron, 1D-convolution, Multilayer Perceptron, Cycle, point-process generalized linear model) and compared their performance at seizure forecasting against the Napkin forecast. The models predicted the probability of having at least one seizure in the next 24-h period based on a 90-day historical window. Model performances were evaluated by commonly used metrics (area under the precision-recall curve, area under the receiver operating characteristic curve, and Brier score). We considered a model to be clinically ineffective if it did not outperform the Napkin method across metrics and seizure frequencies.A total of 5501 retrospective patients (3300 training, 1100 validation, and 1101 testing) and 36 prospective patients (21 from one cohort, 15 from the other) were included in the analysis. No model achieved significantly better performance than the Napkin method across metrics and frequencies.Clinically effective seizure forecasting (i.e., beyond the Napkin method) for 24-h risk using e-diaries alone may be infeasible with currently available techniques.

  View details for DOI 10.1111/epi.18677

  View details for Web of Science ID 001592554300001

  View details for PubMedID 41085335

  View details for PubMedCentralID PMC12959853

• The Brain Imaging and Neurophysiology Database: BINDing multimodal neural data into a large-scale repository. medRxiv : the preprint server for health sciences Maschke, C., Hadar, P., Zhang, Y., Li, J., Ganjoo, G., Hoopes, A., Guazzo, A., Gupta, A., Ghanta, M., Nearing, B., Silvers, C. T., Gunapati, B., Thomas, R., Kim, J. A., Mukerji, S. S., Dalca, A., Zafar, S., Lam, A. D., Mignot, E., Westover, M. B. 2025

  Abstract

  1 The Brain Imaging and Neurophysiology Database (BIND) represents one of the largest multi-institutional, multimodal, clinical neuroimaging repositories, comprising 1.8 million brain scans from 38,945 patients, linked to neurophysiological recordings. This comprehensive dataset addresses critical limitations in neuroimaging research by providing unprecedented scale and diversity across pathologies and health. BIND integrates de-identified data from Massachusetts General Hospital, Brigham and Women's Hospital, and Stanford University, including 1,723,699 MRI scans (1.5 Tesla, 3 Tesla, and 7 Tesla), 54,137 CT scans, 5,093 PET scans, and 526 SPECT scans, converted to standardized NIfTI format following BIDS organization. The database spans the full age spectrum (newborn to 106 years) and encompasses diverse neurological conditions alongside healthy patients. We deployed Bio-Medical Large Language Models to extract structured clinical metadata from 84,960 brain-related reports, categorizing findings into standardized pathology classifications. All imaging data are linked to previously published EEG and polysomnography recordings from the Harvard Electroencephalography Database, enabling unprecedented multimodal analyses. BIND is freely accessible for academic research through the Brain Data Science Platform ( https://bdsp.io/ ). This resource facilitates large-scale neuroimaging studies, machine learning applications, and multimodal brain research to accelerate discoveries in clinical neuroscience.

  View details for DOI 10.1101/2025.10.01.25337054

  View details for PubMedID 41256149

  View details for PubMedCentralID PMC12622100

• Decreasing the Epilepsy Treatment Gap in Tena, Ecuador: A Report From 2021 to 2023. Cureus Bayas, G., Bayas, G., Bayas, A., Bayas Cardenas, E. O., Franco, N., Sigcha, C. M., Shapiro, K., Moskowitz, S., Espinosa, P. S., Dey, R. K., Camia, C. S., Coates, S., Stow, C., Turley, N., Jing, J., Westover, M. B. 2025; 17 (10): e94581

  Abstract

  Background Neurological care in rural areas such as Tena, Ecuador, remains critically low due to geographic, economic, and systemic barriers. Tena, located in the Amazon region, has limited access to specialized neurological services, creating significant health disparities. Since 2009, the International Neurology Foundation (INF) has partnered with the Hospital José María Velasco Ibarra to address these challenges. Methodology This retrospective analysis summarizes data from the INF medical service relief trip (MSRT) conducted in Tena from 2021 to 2023. Clinical records, interviews with providers, and MSRT reports were reviewed to assess patient demographics, diagnoses, treatments, and interventions. Descriptive statistics and thematic analysis were used to identify trends and insights. Results Over three years, 751 patients were treated, with epilepsy being the most common diagnosis (265 cases). Children under the age of 10 years represented the largest patient group. Key achievements included the donation of electroencephalography equipment, enabling local epilepsy diagnostics, and training local healthcare providers. Persistent challenges included limited imaging resources, inconsistent medication supply, and barriers related to language and transportation. Conclusions INF's initiatives have significantly improved access to neurological care in Tena, enhancing diagnostic capabilities and providing critical training. Sustainable progress requires investment in infrastructure, expanded training programs, and consistent medication availability. The Tena experience serves as a model for reducing health disparities and improving neurological care in resource-limited settings, aligning with global health equity priorities.

  View details for DOI 10.7759/cureus.94581

  View details for PubMedID 41246783

  View details for PubMedCentralID PMC12614661

• General AI May Revolutionize Neurology-Or It Might Be Bad. JAMA neurology Westover, M. B., Westover, A. M. 2025; 82 (10): 977-978

  View details for DOI 10.1001/jamaneurol.2025.0905

  View details for PubMedID 40323622

• Dual-outcome Prediction of Post-Ischemic Stroke Epilepsy and Mortality Using Multimodal Quantitative Biomarkers. medRxiv : the preprint server for health sciences Chen, Y., Soto, A. L., Sudhakar, T. D., Zubair, A., Sun, H., Jing, J., Ge, W., Loman, L., Sivaraju, A., Petersen, N., Hirsch, L. J., Blumenfeld, H., Zafar, S. F., Struck, A. F., Sheth, K. N., Gilmore, E. J., Westover, M. B., Kim, J. A. 2025

  Abstract

  Post-ischemic stroke epilepsy (PISE) reduces quality of life, and early risk prediction can guide prevention strategies and anti-epileptogenesis treatment trials. Stroke severity predicts both PISE and mortality, and ignoring mortality can overestimate epilepsy risk. We sought to enhance PISE risk stratification by modeling death as a competing outcome, integrating quantitative clinical, neuroimaging, and electroencephalography (EEG) biomarkers to distinguish shared and distinct predictors of epilepsy and mortality.We developed a PISE prediction model using retrospective data from Yale-New Haven Hospital. The training cohort included patients from 2014-2020; the testing cohort from 2021-2022. Eligible patients were adults with acute ischemic stroke who underwent neuroimaging and EEG monitoring <7 days post-stroke and had follow-up >7 days.Of 280 patients, 53 developed PISE first, 104 died first, and the rest were censored. Quantitative PISE biomarkers included greater 72h stroke severity (HR Δ3 [95%CI], 1.2 [1.1-1.4]), infarct volume (HR Δ10mL , 1.06 [1.04-1.08]), EEG epileptiform abnormality burden (HR Δ10% , 1.2 [1.1-1.3]), and EEG power asymmetries (HR Δ10% , 2.0 [1.4-2.9]). Death predictors included older age (HR Δ10years , 1.7 [1.4-2.0]), worse pre-stroke functional status (HR, 1.4 [1.2-1.7]), atrial fibrillation history (HR, 2.4 [1.6-3.7]), cardioembolism etiology (HR, 1.9 [1.2-3.0]), anterior cerebral artery involvement (HR, 2.2 [1.2-3.7]), and greater EEG global theta-band powers (HR Δ10µV , 6.2 [2.3-17]). Our model, CRIME PISE , integrating these features, allows prediction of PISE-first and death-first risk scores with AUC of 0.72 (95%CI, 0.60-0.83) and 0.79 (0.72-0.85), respectively. Compared with the benchmark SeLECT model, CRIME PISE better predicted PISE in patients with ≥4 SeLECT points (AUC, 0.72 vs 0.58) but not those with <4 points (AUC, 0.33 vs 0.52). In the testing cohort, CRIME PISE identified a more selective group (n=18 vs 44 per SeLECT) with a higher PISE rate (39% vs 20%) and a lower mortality rate (22% vs 45%).CRIME PISE enhances PISE prediction by accounting for mortality as a competing outcome and incorporating multimodal quantitative biomarkers. Because its benefits over SeLECT are most pronounced in high-risk patients, a two-stage approach-SeLECT screening followed by CRIME PISE in SeLECT-positive cases-may better target candidates for anti-epileptogenesis trials by prioritizing patients likely to survive long-term and develop epilepsy.

  View details for DOI 10.1101/2025.09.22.25335736

  View details for PubMedID 41040677

  View details for PubMedCentralID PMC12485958

• Dementia Risk and Machine Learning-Derived Brain Age Index from Sleep Electroencephalography: A Pooled Cohort Analysis of Over 7,000 Individuals Across Five Community Cohorts. medRxiv : the preprint server for health sciences Sun, H., Milton, S., Fang, Y., Taha, H. B., Shiju, S., Thomas, R. J., Ganglberger, W., Pase, M. P., Hughes, T., Purcell, S., Redline, S., Stone, K. L., Yaffe, K., Westover, M. B., Leng, Y. 2025

  Abstract

  Sleep electroencephalographic (EEG) microstructures are closely related to cognition and undergo age-dependent changes. However, their multidimensional nature makes them challenging to interpret using conventional approaches. Machine learning-computed EEG brain age index (BAI) represents the difference between the sleep EEG-based brain age and chronological age, quantifying deviations in sleep EEG microstructures from normative patterns.To determine the association between sleep BAI and incident dementia in community-dwelling populations.Five individual cohorts and random-effects meta-analysis.This study pooled data from five community-based, methodologically consistent, longitudinal cohorts: MESA, ARIC, FHS-OS, MrOS, and SOF. We used Fine-Gray models to assess the association between BAI and incident dementia within each cohort, accounting for death as a competing risk. Cohort-specific estimates were then pooled using random-effects meta-analyses.7,071 participants (MESA 54-94 years old, ARIC 52-75, FHS-OS 40-81, MrOS 67-96, SOF 79-93) without dementia at the time of polysomnography were included.The sleep EEG-based BAI was computed using interpretable machine learning, incorporating 13 age-dependent features extracted from central EEG channels in overnight, home-based sleep polysomnography.Incident dementia or probable dementia was determined in each cohort, with death as a competing risk.Across the five cohorts, dementia incidence ranged from 6.6% to 34.3% over a median follow-up of 3.5 to 17.0 years. Across cohorts, each 10-year increase in BAI was associated with a 39% increased risk of incident dementia (hazard ratio: 1.39 [95% confidence interval=1.21-1.59], p<0.001) after adjustment for age, sex, race, education, body mass index, current smoking, sleep medications, and physical activity level. The top feature underlying BAI was waveform kurtosis in N2 with a negative association with incident dementia (p<0.001). The associations remained after additional adjustment for multiple comorbidities, APOE e4 status, and apnea-hypopnea index, and were consistent across sex and age groups.A higher sleep EEG-based BAI was associated with a higher risk of incident dementia across five community-based longitudinal cohorts. Future studies are warranted to evaluate the predictive value of BAI as a non-invasive digital biomarker for the early detection of dementia in community settings.

  View details for DOI 10.1101/2025.09.21.25336255

  View details for PubMedID 41040733

  View details for PubMedCentralID PMC12486002

• The Boston Children's Hospital Sleep Corpus: A Collection of 15,695 Annotated Pediatric Polysomnograms. Sleep Tripathi, A., Ganglberger, W., Sun, H., Alcott, C., Turley, N., Fitzgerald, R., Mitra, A., Waters, S., Gupta, A., Gupta, A., Ghanta, M., Junior, V. M., Nasiri, S., Nearing, B., Stone, K. L., Mignot, E., Hwang, D., Reyna, M. A., Koscova, Z., Robichaux, C., Zhang, Z., Li, Q., Ganjoo, G., Trotti, L. M., Clifford, G. D., Silvers, C. T., Gunapati, B., Thomas, R. J., Westover, M. B., Maski, K., Katwa, U. 2025

  Abstract

  Sleep is a fundamental biological process essential to health, particularly during early life when sleep patterns are developing and sleep disorders are common. Yet pediatric sleep research is hindered by a lack of large-scale, high-quality polysomnography (PSG) datasets. To address this need, we introduce the Boston Children's Hospital (BCH) Sleep Corpus-the largest pediatric PSG dataset available-comprising 15 695 overnight recordings from 12 640 unique patients (median age ~ 6 years). The dataset includes 16.7 million annotated sleep stages, 2.25 million respiratory, arousal, and limb movement events, and over 11 000 patient diagnoses linked through de-identified electronic health records. Each PSG has a median duration of 8.9 hours, totaling 139 208 hours of EEG data. Sleep staging follows American Academy of Sleep Medicine guidelines and reveals age-related trends: REM sleep decreases from 33.5% in neonates to 16.3% in teenagers, while N2 sleep increases from 21.7% to 35.4%. Central apneas decline with age, while obstructive hypopneas and respiratory effort related arousals events rise. Limb movements are not scored in <1 yr but remain at around 30 per PSG across older age groups. We also present age- and region-specific EEG spectral norms and respiratory event trends across the pediatric age range. The dataset is organized in Brain Imaging Data Structure (BIDS) format and publicly available via the Brain Data Science Platform. The dataset provides a valuable resource for improving our scientific understanding of pediatric sleep and developing automated PSG analysis with artificial intelligence tools.

  View details for DOI 10.1093/sleep/zsaf273

  View details for PubMedID 40971987

• Automated extraction of post-stroke functional outcomes from unstructured electronic health records. European stroke journal Fernandes, M., Gallagher, K., Turley, N., Gupta, A., Westover, M. B., Singhal, A. B., Zafar, S. F. 2025; 10 (3): 829-836

  Abstract

  Population level tracking of post-stroke functional outcomes is critical to guide interventions that reduce the burden of stroke-related disability. However, functional outcomes are often missing or documented in unstructured notes. We developed a natural language processing (NLP) model that reads electronic health records (EHR) notes to automatically determine the modified Rankin Scale (mRS).We included consecutive patients (⩾18 years) with acute stroke admitted to our center (2015-2024). mRS scores were obtained from the Get With the Guidelines registry and clinical notes (if documented), and used as the gold standard to compare against NLP-generated scores. We used text-based features from notes, along with age, sex, discharge status, and outpatient follow-up to train a logistic regression for prediction of good (0-2) versus poor (3-6) mRS, and a linear regression for the full range of mRS scores. The models were trained for prediction of mRS at hospital discharge and post-discharge. The models were externally validated in a dataset of patients with brain injuries from a different healthcare center.We included 5307 patients, 5006 in train and test and 301 in validation; average age was 69 (SD 15) and 65 (SD 17) years, respectively; 47% female. The logistic regression achieved an area under the receiver operating curve (AUROC) of 0.94 [CI 0.93-0.95] (test) and 0.94 [0.91-0.96] (validation), and the linear model a root mean squared error (RMSE) of 0.91 [0.87-0.94] (test) and 1.17 [1.06-1.28] (validation).The NLP-based model is suitable for use in large-scale phenotyping of stroke functional outcomes and population health research.

  View details for DOI 10.1177/23969873251314340

  View details for PubMedID 39838914

  View details for PubMedCentralID PMC11752148

• Automated analysis of the AASM Inter-Scorer Reliability gold standard polysomnogram dataset. Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine Tripathi, A., Nasiri, S., Ganglberger, W., Nassi, T., Meulenbrugge, E. J., Sun, H., Stone, K. L., Mignot, E., Hwang, D., Trotti, L. M., Reyna, M. A., Clifford, G. D., Katwa, U., Thomas, R. J., Westover, M. B. 2025

  Abstract

  To compare the performance of a comprehensive automated polysomnogram (PSG) analysis algorithm-CAISR (Complete Artificial Intelligence Sleep Report)-to a multi-expert gold standard panel, crowdsourced scorers, and experienced technicians for sleep staging and detecting arousals, respiratory events, and limb movements.A benchmark dataset of 57 PSG records (Inter-Scorer Reliability dataset) with 200 30-second epochs scored per AASM guidelines was used. Annotations were obtained from (1) the AASM multi-expert gold standard panel, (2) AASM Inter-Scorer Reliability (ISR) platform users ("crowd," averaging 6,818 raters per epoch), (3) three experienced technicians, and (4) CAISR. Agreement was assessed via Cohen's Kappa (κ) and percent agreement.Across tasks, CAISR achieved performance comparable to experienced technicians but did not match consensus-level agreement between the multi-expert gold standard and the crowd. For sleep staging, CAISR's agreement with multi-expert gold standard was 82.1% (κ = 0.70), comparable to experienced technicians but below the crowd (κ = 0.88). Arousal detection showed 87.81% agreement (κ = 0.45), respiratory event detection 83.18% (κ = 0.34), and limb movement detection 94.89% (κ = 0.11), each aligning with performance equivalent to experienced technicians but trailing crowd agreement (κ = 0.83, 0.78 and 0.86 for detection of arousal, respiratory events and limb movements respectively).CAISR achieves experienced technician-level accuracy for PSG scoring tasks but does not surpass the consensus-level agreement of a multi-expert gold standard or the crowd. These findings highlight the potential of automated scoring to match experienced technician-level performance while emphasizing the value of multi-rater consensus.

  View details for DOI 10.5664/jcsm.11848

  View details for PubMedID 40790924

• Choice of antiseizure medications and associated outcomes in Medicare beneficiaries after acute ischemic stroke EPILEPSIA Brooks, J. D., de Medeiros, R., Sun, S., Sankaranarayanan, M., Westover, M., Schwamm, L. H., Newhouse, J. P., Haneuse, S., Moura, L. R. 2025; 66 (12): 4857-4868

  Abstract

  We examined choice of outpatient epilepsy-specific antiseizure medication (ESM) after a stroke discharge and outcomes in a sample of US older adults.In this matched cohort study, we analyzed a 20% sample of US Medicare beneficiaries aged 65 years and older hospitalized for acute ischemic stroke (AIS) between 2009 and 2021 who were discharged home. Individuals met insurance coverage criteria and were not taking ESM before hospitalization. We matched individuals on days from discharge to ESM initiation. Individuals who initiated ESMs other than levetiracetam within 30 days of discharge (n = 229) were matched to levetiracetam initiators (n = 687). We did not include antiseizure medications used for treatment of pain or psychiatric disorders such as gabapentin and benzodiazepines. We investigated the time to seizurelike events, emergency department (ED) visits, and readmissions using a semicompeting risk framework.The matched cohort of 916 ESM initiators had a median age of 73 years (interquartile range = 69-81) and was 57% female and 71% non-Hispanic White. Using the semicompeting risk framework, those who received other ESM had a 37% lower hazard of seizurelike events compared to those receiving levetiracetam, given that death had not occurred (hazard ratio = .63, 95% confidence interval [CI] = .43-.91). Among other ESM initiators, the hazard of ED visits and hospital readmissions, given that death had not occurred, did not differ significantly from initiating levetiracetam (hazard ratios = 1.00 [95% CI = .80-1.25] and .98 [95% CI = .75-1.28], respectively).In a sample of US Medicare beneficiaries hospitalized for AIS and discharged home, initiating levetiracetam in the outpatient setting was associated with a higher risk of seizurelike events compared to other ESMs. However, there remains a possibility of residual confounding by indication, as individuals with greater risk of seizures may have been started on levetiracetam. We did not observe significant differences in the risk of ED visits or readmissions, suggesting comparable safety profiles in broader clinical outcomes.

  View details for DOI 10.1111/epi.18594

  View details for Web of Science ID 001545226200001

  View details for PubMedID 40770930

• Evaluating crowdsourcing for ICU EEG annotation: A comparison with expert performance EPILEPSIA Kong, W., Nascimento, F. A., Struck, A., Duhaime, E., Kapur, S., Amorim, E., Kapinos, G., Rodriguez, A., Thomas, B., Desai, M., Lee, J., Westover, M., Jing, J. 2025; 66 (11): 4366-4380

  View details for DOI 10.1111/epi.18547

  View details for Web of Science ID 001544766100001

• Controversies: Periodic discharges in critically ill patients-" urgent treatment is essential" CLINICAL NEUROPHYSIOLOGY PRACTICE Westover, M., Kaplan, P. W., Husain, A. M. 2025; 10: 286-291

  Abstract

  •Optimal management for patients with periodic discharges is debatable.•Pro: Parenteral antiseizure treatment may reduce damage from periodic discharges.•Anti: Assess each patient with periodic discharges before deciding on treatment.•Moderator: The pro and anti positions show the need for further investigation.

  View details for DOI 10.1016/j.cnp.2025.06.010

  View details for Web of Science ID 001535156300001

  View details for PubMedID 40703850

  View details for PubMedCentralID PMC12284540

• Surgery on the aortic arch and feasibility of electroencephalography (SAFE) monitoring in neonates: protocol for a prospective observational cohort study. BMJ open McDevitt, W. M., Jones, T. J., Quinn, L., Easter, C. L., Jing, J., Westover, M. B., Scholefield, B. R., Seri, S., Drury, N. E. 2025; 15 (7): e106423

  Abstract

  While survival rates following neonatal surgery for congenital heart disease (CHD) have improved over the years, neurodevelopmental delays are still highly prevalent in these patients. After correcting for the CHD subtype, the severity of developmental impairment is dependent on multiple factors, including intraoperative brain injury, which is more frequent and more severe in those undergoing aortic arch repair with deep hypothermic circulatory arrest (DHCA). It is proposed that brain injury may be reduced if cooling is stopped at the point of electrocerebral inactivity (ECI) on electroencephalogram (EEG), but there is limited evidence to support this as few centres perform perioperative EEG routinely. This study aims to assess the feasibility of EEG monitoring during neonatal aortic arch repair and investigate the relationship between temperature and EEG to inform the design of a future clinical trial.Single-centre prospective observational cohort study in a UK specialist children's hospital, aiming to recruit 74 neonates (≤4 weeks corrected age) undergoing aortic arch repair with DHCA. EEG will be acquired at least 1-3 hours before surgery, and brain activity will be monitored continuously until 24 hours following admission to intensive care. Demographic, clinical, surgical and outcome variables will be collected. Feasibility will be measured by the number of patients recruited, data collection procedures, technically successful EEG recordings and adverse events. The main outcomes are the temperature at which ECI is achieved and its duration, EEG patterns at key perioperative steps and neurodevelopmental outcomes at 24 months postsurgery.The study was approved by the Yorkshire and The Humber Sheffield National Health Service Research Ethics Committee (20/YH/0192) on 18 June 2020. Written informed consent will be obtained from the participant's parent/guardian prior to surgery. Findings will be disseminated to the academic community through peer-reviewed publications and presentations at conferences. Parents/guardians will be informed of the results through a newsletter in conjunction with local charities.

  View details for DOI 10.1136/bmjopen-2025-106423

  View details for PubMedID 40639843

  View details for PubMedCentralID PMC12258354

• CAISR: Achieving Human-Level Performance in Automated Sleep Analysis Across All Clinical Sleep Metrics. Sleep Nasiri, S., Ganglberger, W., Nassi, T., Meulenbrugge, E. J., Moura Junior, V., Ghanta, M., Gupta, A., Stone, K. L., Kjaer, M. R., Sum-Ping, O., Mignot, E., Hwang, D., Trotti, L. M., Clifford, G. D., Katwa, U., Sun, H., Thomas, R. J., Westover, M. B. 2025

  Abstract

  To develop and validate a Complete Artificial Intelligence Sleep Report system (CAISR), a system for comprehensive automated sleep analysis, including sleep staging, arousal detection, apnea identification, and limb movement analysis.We utilized a large diverse dataset from four cohorts (MGH, MESA, MrOS, SHHS) comprising 25,749 participants to develop CAISR. Following American Academy of Sleep Medicine (AASM) guidelines, CAISR performs four tasks: it stages sleep into five categories (Wake, NREM 1, NREM 2, NREM 3, REM), detects arousals, detects and classifies breathing events (Obstructive Apnea, Central Apnea, Mixed Apnea, Hypopnea, and RERA), and detects limb movements and categorizes them as periodic or isolated. We tested CAISR against multiple datasets independently annotated by multiple experts, including UPenn (69 subject, 6 experts), BITS (98 subjects, three experts), Stanford (100 subjects, three experts). Sleep staging and arousal detection were accomplished using customized deep neural networks, while breathing event detection and classification and limb movement analysis were accomplished using rule-based signal processing approaches. We quantified CAISR performance with three metrics: Cohen's Kappa, area under the receiver operating characteristic curve (AUROC), and area under the precision-recall curve (AUPRC). To determine whether CAISR performed on par with human experts, we compared expert inter-rater reliability (IRR) with algorithm-expert IRR.The CAISR model showed strong overall performance across the four tasks: sleep staging, arousal detection, apnea detection, and limb movement detection. In sleep staging, the model achieved AUROC values ranging from 0.82 to 0.97 and AUPRC values between 0.63 and 0.90 across the BITS, Stanford, and Penn datasets, indicating high classification accuracy. The Kappa agreement analysis showed that in the BITS and Stanford datasets, CAISR outperformed human experts, with non-overlapping confidence intervals indicating superiority (Kappa values around 0.7 to 0.8 for CAISR vs. experts). In the Penn dataset, the model's performance was comparable to experts, with overlapping confidence intervals suggesting non-inferiority. For arousal detection, the model maintained reliable performance, with AUROC values ranging from 0.83 to 0.94 and AUPRC values from 0.67 to 0.85, and Kappa analysis showing overlapping confidence intervals, indicating comparable performance to experts in both the BITS and Stanford datasets (Kappa values for CAISR around 0.6 to 0.75). In apnea detection, including the detection of obstructive, central, and mixed apnea, the CAISR model achieved competitive results in the BITS dataset with AUROC values between 0.81 and 0.95 and AUPRC values between 0.58 and 0.82, but in the Stanford dataset, it underperformed compared to human experts, as shown by non-overlapping confidence intervals and lower Kappa values (around 0.55 to 0.65). Finally, in limb movement detection, the model demonstrated superior performance in the BITS dataset, with AUROC values of 0.9 to 0.96 and AUPRC values between 0.75 and 0.85, and Kappa analysis indicating significantly higher reliability compared to experts (CAISR Kappa around 0.8, with non-overlapping confidence intervals). In the Stanford dataset, CAISR's performance was comparable to experts, with overlapping confidence intervals suggesting non-inferiority (Kappa values around 0.65 to 0.7). Overall, the CAISR model consistently exhibited high classification performance and reliability across tasks, often matching or surpassing expert-level performance, with particularly strong results in sleep staging and limb detection.The CAISR model demonstrated high classification accuracy and reliability across sleep staging, arousal, apnea, and limb movement detection tasks, matching or surpassing human expert performance. Human errors and systematic biases in the annotation of micro-events during sleep, such as arousal and apnea detection, likely contributed to variability in expert performance, while the CAISR model showed more consistent results, reducing the impact of these biases and increasing overall reliability across task.

  View details for DOI 10.1093/sleep/zsaf134

  View details for PubMedID 40554678

• Toward a Universal Map of EEG: A Semantic, Low-Dimensional Manifold for EEG Classification, Clustering, and Prognostication ANNALS OF NEUROLOGY Krumm, L., Kranz, D. D., Halimeh, M., Nelde, A., Amorim, E., Zafar, S., Jing, J., Thomas, R. J., Westover, M., Meisel, C. 2025; 98 (2): 357-368

  Abstract

  Prognostication in patients with disorders of consciousness (DOCs) remains challenging because of heterogeneous etiologies, pathophysiologies and, consequently, highly variable electroencephalograms (EEGs). Here, we use EEG patterns that are well-characterizable to create a latent map that positions novel EEGs along a continuum. We asses this map as a generalizable tool to extract prognostically valuable information from long-term EEG, by predicting outcome post-cardiac arrest as a first use case.Categorizable EEGs across the health-disease continuum (wake [W], sleep [rapid eye movement (REM), non-REM (N1, N2, N3)], ictal-interictal-continuum [lateralized and generalized periodic discharges (LPD, GPD) and lateralized and generalized rhythmic delta activity (LRDA, GRDA)], seizures [SZ], burst suppression [BS]; 20,043 patients, 288,986 EEG segments) are arranged meaningfully in a low-dimensional space via a deep neural network, resulting in a universal map of EEG (UM-EEG). We assess prognostication after cardiac arrest (576 patients, recovery or death) based on long-term EEGs represented as trajectories in this continuous embedding space.Classification of out-of-sample EEG match state-of-the-art artificial intelligence algorithms while extending it to the currently largest set of classes across the health-disease continuum (mean area under the receiver-operating-characteristic curve [AUROCs] 1-vs-all classification: W, 0.94; REM, 0.92; N1, 0.85; N2, 0.91; N3, 0.98; GRDA, 0.97; LRDA, 0.97; SZ, 0.87; GPD, 0.99; LPD, 0.97; BS, 0.94). UM-EEG enables outcome prediction after cardiac arrest with an AUROC of 0.86 and identifies interpretable factors governing prognosis such as the distance to healthy states over time.UM-EEG presents a novel and physiologically meaningful representation to characterize brain states along the health-disease continuum. It offers new opportunities for personalized, long-term monitoring and prognostication. ANN NEUROL 2025;98:357-368.

  View details for DOI 10.1002/ana.27260

  View details for Web of Science ID 001512038900001

  View details for PubMedID 40539771

  View details for PubMedCentralID PMC12278028

• Harvard Electroencephalography Database: A comprehensive clinical electroencephalographic resource from four Boston hospitals. Epilepsia Sun, C., Jing, J., Turley, N., Alcott, C., Kang, W. Y., Cole, A. J., Goldenholz, D. M., Lam, A., Amorim, E., Chu, C., Cash, S., Junior, V. M., Gupta, A., Ghanta, M., Nearing, B., Nascimento, F. A., Struck, A., Kim, J., Sartipi, S., Tauton, A. M., Fernandes, M., Sun, H., Bayas, G., Gallagher, K., Wagenaar, J. B., Sinha, N., Lee-Messer, C., Silvers, C. T., Gunapati, B., Rosand, J., Peters, J., Loddenkemper, T., Lee, J. W., Zafar, S., Westover, M. B. 2025

  Abstract

  This article presents the Harvard Electroencephalography Database (HEEDB), a large-scale, deidentified, and standardized electroencephalographic (EEG) resource supporting artificial intelligence-driven and reproducible research in epilepsy and broader clinical neuroscience.HEEDB aggregates more than 280 000 EEG recordings from more than 108 000 patients across four Harvard-affiliated hospitals. Data are harmonized using the Brain Imaging Data Structure and hosted on the Brain Data Science Platform. EEG data are linked with clinical notes, International Classification of Diseases, 10th Revision codes, medications, and EEG reports. Deidentification follows Health Insurance Portability and Accountability Act Safe Harbor standards.The database includes routine, epilepsy monitoring unit, and intensive care unit EEGs across all age groups, with 73% linked to deidentified clinical reports and 96% of those matched to recordings. Findings are extracted using expert curation, regular expressions, and medical natural language processing models. Auxiliary data include diagnoses, medications, and hospital course, supporting multimodal analysis.HEEDB fills a critical gap in EEG data availability for epilepsy research. By enabling large-scale, privacy-compliant, and clinically relevant analysis, it accelerates the development of diagnostic tools, improves training datasets for machine learning, and promotes data-sharing in alignment with FAIR (Findable, Accessible, Interoperable, Reusable) and National Institutes of Health data policies.

  View details for DOI 10.1111/epi.18487

  View details for PubMedID 40464151

• Benzodiazepine Initiation and the Risk of Falls or Fall-Related Injuries in Older Adults Following Acute Ischemic Stroke NEUROLOGY-CLINICAL PRACTICE Sun, S., Lomachinsky, V., Smith, L. H., Newhouse, J. P., Westover, M., Blacker, D., Schwamm, L. H., Haneuse, S., Moura, L. R. 2025; 15 (3): e200452

  Abstract

  Benzodiazepine (BZD) use in older adults after acute ischemic stroke (AIS) is common. We aimed to assess the risk of falls or fall-related injuries (FRIs) in older adults after the use of BZDs during the acute poststroke recovery period.We emulated a hypothetical randomized trial of BZD use during the acute poststroke recovery period using linked data from the Get With the Guidelines Stroke Registry and Mass General Brigham's electronic health records. Our cohort included patients aged 65 years and older with an AIS admission between 2014 and 2021, no documented previous stroke, and no BZD prescriptions in the 3 months before admission. The potential for immortal time and confounding bias was addressed separately using inverse probability weighting.We analyzed data from 495 patients who initiated inpatient BZDs within 3 days of admission and 2,564 who did not. After standardization, the estimate was 694 events per 1,000 (95% CI 676-709) for the BZD initiation strategy and 584 events per 1,000 (95% CI 575-595) for the noninitiation strategy. Subgroup analyses showed risk differences of 142 events per 1,000 (95% CI 111-165) and 85 events per 1,000 (95% CI 64-107) for patients aged 65-74 years and 75 years and older, respectively. Risk differences were 187 events per 1,000 (95% CI 159-206) for patients with minor (NIH Stroke Severity Scale score ≤ 4) AIS and 32 events per 1,000 (95% CI 10-58) for those with moderate-to-severe AIS.Initiating BZDs within 3 days of an AIS is associated with an elevated ten-day risk of falls or FRIs, particularly for patients aged 65-74 years and for those with mild stroke. This underscores the need for caution when initiating BZDs, especially among individuals likely to be ambulatory during the acute and subacute poststroke period.

  View details for DOI 10.1212/CPJ.0000000000200452

  View details for Web of Science ID 001451144600001

  View details for PubMedID 40144887

  View details for PubMedCentralID PMC11936338

• Sleep as a window to understand and regulate Alzheimer's disease: emerging roles of thalamic reticular nucleus. Neural regeneration research Sun, H., Shen, S., Thomas, R. J., Westover, M. B., Zhang, C. 2025; 20 (6): 1711-1712

  View details for DOI 10.4103/NRR.NRR-D-24-00351

  View details for PubMedID 39104106

  View details for PubMedCentralID PMC11688547

• Sleep-Based Brain Age Is Reduced in Advanced Inner Engineering Meditators. Mindfulness Banks, J. C., Hariri, S., Kveraga, K., Ouyang, A., Gallagher, K., Quadri, S. A., Tesh, R. A., Reed, P. U., Thomas, R. J., Westover, M. B., Sun, H., Subramaniam, B. 2025; 16 (6): 1675-1692

  Abstract

  We aimed to quantify the effects of advanced meditation on brain electrical activity during sleep. This investigation addresses the need for objective neurophysiological measures of meditation's potential impact on brain aging and health.This study was a single-site, prospective cohort study (conducted August 25, 2021, through September 26, 2021) of meditators attending the "Samyama Sadhana" retreat (September 1-5, 2021). Two healthy comparison groups and four comparison groups with varying degrees of age-related brain pathology are included. Using overnight electroencephalography, physiological measures of brain age were derived and subtracted from chronological age, measuring the deviation of apparent brain age from chronological age.Thirty-four participants completed the study (average age = 38 years; 36% female). Estimated brain age index after adjustment by matching: meditators (n = 34), - 5.9 years (SE = 0.94 years, t-test p < 0.001); Dreem healthy controls (n = 1077), - 0.24 (0.61, p < 0.001); Massachusetts General Hospital (MGH) healthy controls (n = 112), 0.55 (0.92, p < 0.05); MGH "no dementia" (n = 7618), 2.4 (0.094, reference cohort for t-test); MGH "symptomatic" (n = 697), 2.0 (0.33, p > 0.05); MGH "mild cognitive impairment (MCI)"(n = 205), 8.8 (2.8, p < 0.05); and MGH "dementia" (n = 153), 10.5 (2.8, p < 0.01).Long-term meditators exhibit lower brain age relative to matched control groups. This study suggests that advanced meditation enhances brain health.This study was not preregistered.The online version contains supplementary material available at 10.1007/s12671-025-02583-y.

  View details for DOI 10.1007/s12671-025-02583-y

  View details for PubMedID 40535579

  View details for PubMedCentralID PMC12170783

• Automated detection of interictal epileptiform discharges with few electroencephalographic channels EPILEPSIA Alkofer, M., Yang, C., Ganglberger, W., Beal, J., Hegde, M., Kang, J., Yoo, J., Gelfand, M. A., Thio, L., Kutluay, E., Campbell, Z., Schmitt, S., Gleichgerrcht, E., Waterhouse, E., Lopez, M. R., Eisenschenk, S., Galanti, M., Singh, R. K., Wills, K. E., Meulenbrugge, E., Dlugos, D., Dean, B., Halford, J. J., Goldenholz, D., Jing, J., Thomas, R., Westover, M. 2025; 66 (7): e114-e120

  Abstract

  Interictal epileptiform discharges (IEDs) are crucial for epilepsy diagnosis and management. New electroencephalographic (EEG) devices with fewer electrodes are more accessible, but their ability to detect IEDs is uncertain. The aim of this study is to determine whether IEDs can be reliably detected in reduced-channel EEG data, enabling broader epilepsy diagnosis. Using EEG samples from 3378 patients and an external validation set of 51 patients, we trained Cyclops, a deep neural network designed to function across various channel configurations. Performance was evaluated using area under the receiver operating characteristic curve (AUROC) and other clinically relevant metrics, including IED source location sensitivity. Cyclops demonstrated strong performance even with minimal channels. AUROC for one channel was .876 (95% confidence interval [CI] = .854-.897); best configuration based on a clinically available product was .950 (95% CI = .936-.962); for the detection of focal IEDs with two local channels, AUROC values ranged from .701 (95% CI = .656-.745) to .930 (95% CI = .902-.955), with a median AUROC of .809. On the external validation set, performance ranged from .692 (95% CI = .593-.782) to .949 (95% CI = .922-.972), with a median AUROC of .846. Thus, Cyclops demonstrates that effective IED detection is possible with reduced EEG setups, enhancing accessibility and expanding epilepsy diagnosis to broader patient populations.

  View details for DOI 10.1111/epi.18431

  View details for Web of Science ID 001480354200001

  View details for PubMedID 40317534

  View details for PubMedCentralID PMC12291011

• Automated phenotyping of mild cognitive impairment and Alzheimer's disease and related dementias using electronic health records. International journal of medical informatics Wei, R., Buss, S. S., Milde, R., Fernandes, M., Sumsion, D., Davis, E., Kong, W. Y., Xiong, Y., Veltink, J., Rao, S., Westover, T. M., Petersen, L., Turley, N., Singh, A., Das, S., Junior, V. M., Ghanta, M., Gupta, A., Kim, J., Lam, A. D., Stone, K. L., Mignot, E., Hwang, D., Trotti, L. M., Clifford, G. D., Katwa, U., Thomas, R. J., Mukerji, S., Zafar, S. F., Westover, M. B., Sun, H. 2025; 200: 105917

  Abstract

  Unstructured and structured data in electronic health records (EHR) are a rich source of information for research and quality improvement studies. However, extracting accurate information from EHR is labor-intensive. Timely and accurate identification of patients with Alzheimer's Disease, related dementias (ADRD), or mild cognitive impairment (MCI) is critical for improving patient outcomes through early intervention, optimizing care plans, and reducing healthcare system burdens. Here we introduce an automated EHR phenotyping model to streamline this process and enable efficient identification of these conditions.We analyzed data from 3,626 outpatients seen at two hospitals between February 2015 and June 2022. Through manual chart review, we established ground truth labels for the presence or absence of MCI/ADRD diagnoses. Our model combined three types of data: (1) unstructured clinical notes, from which we extracted single words, two-word phrases (bigrams), and three-word phrases (trigrams) as features, weighted using Term Frequency-Inverse Document Frequency (TF-IDF) to capture their relative importance, (2) International Classification of Diseases (ICD) codes, and (3) medication prescriptions related to MCI/ADRD. We trained a regularized logistic regression model to predict MCI/ADRD diagnoses and evaluated its performance using standard metrics including area under the receiver operating curve (AUROC), area under the precision-recall curve (AUPRC), accuracy, specificity, precision, recall, and F1 score.Thirty percent of patients in the cohort carried diagnoses of MCI/ADRD based on manual review. When evaluated on a held-out test set, the best model using clinical notes, ICDs, and medications, achieved an AUROC of 0.98, an AUPRC of 0.98, an accuracy of 0.93, a sensitivity (recall) of 0.91, a specificity of 0.96, a precision of 0.96, and an F1 score of 0.93 The estimated overall accuracy for patients randomly selected from EHRs was 99.88%.Automated EHR phenotyping accurately identifies patients with MCI/ADRD based on clinical notes, ICD codes, and medication records. This approach holds potential for large-scale MCI/ADRD research utilizing EHR databases.

  View details for DOI 10.1016/j.ijmedinf.2025.105917

  View details for PubMedID 40222334

• Identification of Patients With Congestive Heart Failure From the Electronic Health Records of Two Hospitals: Retrospective Study. JMIR medical informatics Sumsion, D., Davis, E., Fernandes, M., Wei, R., Milde, R., Veltink, J. M., Kong, W., Xiong, Y., Rao, S., Westover, T., Petersen, L., Turley, N., Singh, A., Buss, S., Mukerji, S., Zafar, S., Das, S., Junior, V. M., Ghanta, M., Gupta, A., Kim, J., Stone, K., Mignot, E., Hwang, D., Trotti, L. M., Clifford, G. D., Katwa, U., Thomas, R., Westover, M. B., Sun, H. 2025; 13: e64113

  Abstract

  BACKGROUND: Congestive heart failure (CHF) is a common cause of hospital admissions. Medical records contain valuable information about CHF, but manual chart review is time-consuming. Claims databases (using International Classification of Diseases [ICD] codes) provide a scalable alternative but are less accurate. Automated analysis of medical records through natural language processing (NLP) enables more efficient adjudication but has not yet been validated across multiple sites.OBJECTIVE: We seek to accurately classify the diagnosis of CHF based on structured and unstructured data from each patient, including medications, ICD codes, and information extracted through NLP of notes left by providers, by comparing the effectiveness of several machine learning models.METHODS: We developed an NLP model to identify CHF from medical records using electronic health records (EHRs) from two hospitals (Mass General Hospital and Beth Israel Deaconess Medical Center; from 2010 to 2023), with 2800 clinical visit notes from 1821 patients. We trained and compared the performance of logistic regression, random forests, and RoBERTa models. We measured model performance using area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC). These models were also externally validated by training the data on one hospital sample and testing on the other, and an overall estimated error was calculated using a completely random sample from both hospitals.RESULTS: The average age of the patients was 66.7 (SD 17.2) years; 978 (54.3%) out of 1821 patients were female. The logistic regression model achieved the best performance using a combination of ICD codes, medications, and notes, with an AUROC of 0.968 (95% CI 0.940-0.982) and an AUPRC of 0.921 (95% CI 0.835-0.969). The models that only used ICD codes or medications had lower performance. The estimated overall error rate in a random EHR sample was 1.6%. The model also showed high external validity from training on Mass General Hospital data and testing on Beth Israel Deaconess Medical Center data (AUROC 0.927, 95% CI 0.908-0.944) and vice versa (AUROC 0.968, 95% CI 0.957-0.976).CONCLUSIONS: The proposed EHR-based phenotyping model for CHF achieved excellent performance, external validity, and generalization across two institutions. The model enables multiple downstream uses, paving the way for large-scale studies of CHF treatment effectiveness, comorbidities, outcomes, and mechanisms.

  View details for DOI 10.2196/64113

  View details for PubMedID 40208662

• Differences in patterns of outpatient epilepsy-specific medication initiation after acute ischemic stroke in the Medicare population EPILEPSIA Donahue, M. A., Brooks, J. D., Hsu, J., Price, M., Blacker, D., Schwamm, L. H., Newhouse, J. P., Westover, M., Haneuse, S., Moura, L. R. 2025; 66 (8): 2728-2742

  Abstract

  Acute ischemic stroke (AIS) is a leading hospitalization cause and significantly contributes to seizures among older adults. We examined outpatient epilepsy-specific medication (ESM) initiation patterns after AIS discharge in adults 65 years and older, trends over time (by stratifying the analysis from 2013 to 2021), and racial/ethnic differences.We analyzed nationwide administrative claims data for a 20% sample of US Medicare beneficiaries (enrolled in Traditional Medicare Parts A, B, and D for at least 12 months before admission) aged ≥65 years and hospitalized for AIS between 2013 and 2021. We estimated the cumulative incidence of ESM initiation within 90 days after AIS discharge, with mortality as a competing risk and censoring person time if individuals experienced an inpatient readmission. We described drug type and stratified our analysis by race, ethnicity, US geographic region, hospital region, and year of discharge.Of 128 174 community-dwelling beneficiaries after AIS discharge, 2435 (1.9%, 95% confidence interval [CI] = 1.8%-2.0%) initiated ESM within the 90-day follow-up period and levetiracetam was the most common medication across all years (81%). Mean age was 79 years (range = 65-110), 56% were female, 81% were non-Hispanic White, 10% were Black/African American, 5% were Hispanic, and 3% were Asian. The cumulative incidence of ESM initiation at 90 days in the overall sample was 1.4% (95% CI = 1.3%-1.4%); it was 1.8% (95% CI = 1.6%-2.1%) for Black/African American, 1.9% (95% CI = 1.6%-2.3%) for Hispanic, and 1.2% (95% CI = 1.2%-1.3%) for non-Hispanic White beneficiaries. The 90-day cumulative incidence also varied by US Census division, from 1.0% (95% CI = .8-1.3; West North Central) to 1.5% (95% CI = 1.3%-1.8%; East South Central). We observed an increase in ESM 90-day initiation over time, from 1.2% (95% CI = 1.0%-1.5%) in 2013 to 1.7% (95% CI = 1.5%-1.9%) in 2021. ESM initiation was 1.6% (95% CI = 1.4%-1.8%) in the 65-70-year age group and decreased in older age groups.Black/African American and Hispanic beneficiaries had a higher 90-day incidence of post-AIS ESM initiation than non-Hispanic Whites. ESM initiation decreased in older age groups.

  View details for DOI 10.1111/epi.18396

  View details for Web of Science ID 001459341300001

  View details for PubMedID 40184019

  View details for PubMedCentralID PMC12353908

• Facility-measured nocturnal hypoxemia and sleep among adults with long COVID versus age- and sex-matched healthy adults: a preliminary observational study SLEEP ADVANCES Sun, H., Dang, R., Haack, M., Hauser, K., Scott-Sutherland, J., Westover, M., Parthasarathy, S., Redline, S., Thomas, R. J., Mullington, J. M. 2025; 6 (2): zpaf017

  Abstract

  Persistent post-acute sequelae of SARS-CoV-2 infection, i.e. long COVID, impacts multiple organ systems. While lower blood oxygen is expected when SARS-CoV-2 infects the lungs, hypoxia without pulmonary symptoms may continue after the acute phase. Ventilation and blood oxygen are more vulnerable during sleep, but nocturnal hypoxemia hasn't been studied in people with long COVID in a facility setting using gold-standard polysomnography (PSG).We conducted an observational study with 50 participants (25 long COVID, 25 age-sex-matched healthy controls) using in-laboratory overnight PSG. We calculated the average SpO2, average SpO2 after removing desaturations, the respiratory rate in different sleep periods, and the hypoxic costs using all desaturations.We found that average SpO2 was lower in participants with long COVID: 1.0% lower after sleep onset (p = .004) and 0.7% lower during REM (p = .002); average SpO2 after removing desaturations was also lower in participants with long COVID: 1.3% lower after sleep onset (p = .002), 0.9% lower during REM (p = .0004), and 1.4% lower during NREM (p = .003); and respiratory rate was 1.4/minute higher in participants with long COVID during REM (p = .005). There were no significant differences in SpO2 and respiratory rate before sleep onset, the within-participant change from before to after sleep onset, or hypoxic costs.The results suggest that long COVID had a persistent lower nocturnal blood oxygen saturation, and support the need for a large-scale study of nocturnal hypoxemia in people with long COVID compared to the general population.

  View details for DOI 10.1093/sleepadvances/zpaf017

  View details for Web of Science ID 001486572300001

  View details for PubMedID 40365527

  View details for PubMedCentralID PMC12070477

• The Association between All-Cause Mortality and Obstructive Sleep Apnea in Adults: A U-Shaped Curve ANNALS OF THE AMERICAN THORACIC SOCIETY Azarian, M., Ramezani, A., Sharafkhaneh, A., Maghsoudi, A., Kryger, M., Thomas, R. J., Westover, M., Razjouyan, J. 2025; 22 (4): 581-590

  Abstract

  Rationale: The relationship between sleep apnea (SA) and mortality remains a topic of debate. Objectives: We explored the relationship between the severity of SA and mortality and the effect of age on this association. Methods: Using a veterans' database, we extracted an apnea-hypopnea index (AHI) from physician interpretations of sleep studies by developing a natural language processing pipeline (with 944 manually annotated notes), which achieved more than 85% accuracy. We categorized the participants into no SA (n-SA; AHI, <5), mild to moderate SA (m-SA; 5 ⩽ AHI < 30), and severe SA (s-SA; AHI, ⩾30). We propensity-matched the m-SA and s-SA categories with n-SA on the basis of age, sex, race, ethnicity, body mass index, and 38 components of the Elixhauser Comorbidity Index. Using logistic regression, we estimated the odds ratio (OR) for all-cause mortality using m-SA as a reference. Also, we stratified the findings on the basis of age: young, ⩽40; middle aged, >40 and <65; and older, ⩾65 adults. Results: We extracted the AHI on 179,121 propensity-matched participants (mean age = 45.85 [SD = 14.1]; BMI = 30.15 ± 5.37 kg/m2; male, 79.09%; White, 64.5%). All-cause mortality rates among three AHI categories showed a U-shaped curve (11.55%, 7.07%, and 8.15% for n-SA, m-SA, and s-SA, respectively), regardless of age group. Compared with m-SA, the odds of all-cause mortality in n-SA (OR, 1.72; 95% confidence interval = 1.65-1.79) and s-SA (OR, 1.17; 95% confidence interval = 1.12-1.22) were higher. Stratifying by age yielded consistent findings. Conclusions: All-cause mortality showed a U-shaped association with the AHI. Further investigations to understand the underlying mechanisms of this phenomenon are warranted.

  View details for DOI 10.1513/AnnalsATS.202407-755OC

  View details for Web of Science ID 001470005700016

  View details for PubMedID 39746198

  View details for PubMedCentralID PMC12005042

• Anesthesia-induced electroencephalogram oscillations and perioperative outcomes in older adults undergoing cardiac surgery. Journal of clinical anesthesia Freedman, I. G., Boncompte, G., Qu, J. Z., Khawaja, Z. Q., Turco, I., Mueller, A., Wiredu, K., McKay, T. B., Westover, M. B., Pedemonte, J. C., Akeju, O. 2025; 102: 111770

  Abstract

  Electroencephalogram oscillations during general anesthesia may change as a function of cognitive and physical health. This study aimed to characterize associations between anesthesia-induced oscillations and postoperative outcomes in cardiac surgery patients over 60 years.This was a prespecified secondary data analysis from the Minimizing Intensive Care Unit Dysfunction with Dexmedetomidine-induced Sleep (MINDDS) study. Participants were admitted from home for elective cardiac surgery with cardiopulmonary bypass. The primary outcome was postoperative delirium obtained using the Confusion Assessment Method. Secondary outcomes were non-home discharge and 30-day readmission. The exposure of interest was alpha power measured during the maintenance phase of isoflurane-general anesthesia. Confounding cognitive and physical health variables were collected.Of 394 participants in the MINDDS study, 302 had analyzable electroencephalograms. The incidence of postoperative delirium was 11.1 %. Odds of postoperative delirium decreased by 14 % for every decibel increase in alpha power (OR 0.86, 95 % CI: 0.78 to 0.95; P = 0.004). This finding was not significant in adjusted analysis (ORadj 0.92, 95 % CI: 0.81 to 1.03; P = 0.154). Non-home discharge setting findings were not associated with alpha power. The odds of 30-day readmission decreased by 20 % for every decibel increase in alpha power (ORadj 0.80, 95 % CI: 0.71 to 0.91; P < 0.001). Findings were conserved in exploratory and sensitivity analyses.In this study anesthesia-induced oscillations were associated with postoperative outcomes; however, these were not independently associated with delirium or discharge disposition after considering preoperative cognitive and physical health. These oscillations were robustly associated with 30-day readmission however, which may help anesthesiologists identify high-risk patients, offering benefits beyond the operating room.Registration Number: NCT02856594.

  View details for DOI 10.1016/j.jclinane.2025.111770

  View details for PubMedID 39921932

  View details for PubMedCentralID PMC11953626

• Artificial intelligence without restriction surpassing human intelligence with probability one: Theoretical insight into secrets of the brain with AI twins of the brain. Neurocomputing Huang, G. B., Westover, M. B., Tan, E. K., Wang, H., Cui, D., Ma, W. Y., Wang, T., He, Q., Wei, H., Wang, N., Tian, Q., Lam, K. Y., Yao, X., Wong, T. Y. 2025; 619

  Abstract

  Artificial Intelligence (AI) has apparently become one of the most important techniques discovered by humans in history while the human brain is widely recognized as one of the most complex systems in the universe. One fundamental critical question which would affect human sustainability remains open: Will artificial intelligence (AI) evolve to surpass human intelligence in the future? This paper shows that in theory new AI twins with fresh cellular level of AI techniques for neuroscience could approximate the brain and its functioning systems (e.g. perception and cognition functions) with any expected small error and AI without restrictions could surpass human intelligence with probability one in the end. This paper indirectly proves the validity of the conjecture made by Frank Rosenblatt 70 years ago about the potential capabilities of AI, especially in the realm of artificial neural networks. This paper also gives the answer to the two widely discussed fundamental questions: 1) whether AI could have potentials of discovering new principles in nature; 2) whether error backpropagation (BP) algorithm commonly and efficiently used in tuning parameters in AI applications is also adopted in the brain. Intelligence is just one of fortuitous but sophisticated creations of the nature which has not been fully discovered. Like mathematics and physics, with no restrictions artificial intelligence would lead to a new subject with its self-contained systems and principles. We anticipate that this paper opens new doors for 1) AI twins and other AI techniques to be used in cellular level of efficient neuroscience dynamic analysis, functioning analysis of the brain and brain illness solutions; 2) new worldwide collaborative scheme for interdisciplinary teams concurrently working on and modelling different types of neurons and synapses and different level of functioning subsystems of the brain with AI techniques; 3) development of low energy of AI techniques with the aid of fundamental neuroscience properties; and 4) new controllable, explainable and safe AI techniques with reasoning capabilities of discovering principles in nature.

  View details for DOI 10.1016/j.neucom.2024.129053

  View details for PubMedID 41312528

  View details for PubMedCentralID PMC12656881

• Big Data Approaches for Novel Mechanistic Insights on Sleep and Circadian Rhythms: a Workshop Summary. Sleep Baizer, L., Bures, R., Nadkarni, G., Reyes-Guzman, C., Ladwa, S., Cade, B., Westover, M. B., Durmer, J., de Zambotti, M., Desai, M., Parekh, A., Si, B., Fernandez-Mendoza, J., Minor, K., Mazzotti, D. R., Lee, S., Katabi, D., Kiss, O., Spira, A. P., Morris, J., Seixas, A., Kioumourtzoglou, M. A., Bridges, J. F., Brown, M., Hale, L., Purcell, S. 2025

  Abstract

  The National Center on Sleep Disorders Research (NCSDR) of the National Heart, Lung, and Blood Institute (NHLBI) at the National Institutes of Health (NIH) hosted a two-day virtual workshop titled Big Data Approaches for Novel Mechanistic Insights on Disorders of Sleep and Circadian Rhythms on May 2nd and 3rd, 2024. The goals of this workshop were to establish a comprehensive understanding of the current state of sleep and circadian rhythms disorders research to identify opportunities to advance the field by using approaches based on artificial intelligence (AI) and machine learning (ML). The workshop showcased rapidly developing technologies for sensitive and comprehensive remote analysis of sleep and its disorders that can account for physiological, environmental and social influences, potentially leading to novel insights on long-term health consequences of sleep disorders and disparities of these health problems in specific populations.

  View details for DOI 10.1093/sleep/zsaf035

  View details for PubMedID 39945146

• A Multimodal Sleep Foundation Model Developed with 500K Hours of Sleep Recordings for Disease Predictions. medRxiv : the preprint server for health sciences Thapa, R., Kjær, M. R., He, B., Covert, I., Moore, H., Hanif, U., Ganjoo, G., Westover, M. B., Jennum, P., Brink-Kjær, A., Mignot, E., Zou, J. 2025

  Abstract

  Sleep is a fundamental biological process with profound implications for physical and mental health, yet our understanding of its complex patterns and their relationships to a broad spectrum of diseases remains limited. While polysomnography (PSG), the gold standard for sleep analysis, captures rich multimodal physiological data, analyzing these measurements has been challenging due to limited flexibility across recording environments, poor generalizability across cohorts, and difficulty in leveraging information from multiple signals simultaneously. To address this gap, we curated over 585,000 hours of high-quality sleep recordings from approximately 65,000 participants across multiple cohorts and developed SleepFM, a multimodal sleep foundation model trained with a novel contrastive learning approach, designed to accommodate any PSG montage. SleepFM produces informative sleep embeddings that enable predictions of future diseases. We systematically demonstrate that SleepFM embeddings can predict 130 future diseases, as modeled by Phecodes, with C-Index and AUROC of at least 0.75 on held-out participants (Bonferroni-corrected p < 0.01). This includes accurate predictions for death (C-Index: 0.84 [95% CI: 0.81-0.87]), heart failure (C-Index: 0.80 [95% CI: 0.77-0.83]), chronic kidney disease (C-Index: 0.79 [95% CI: 0.77-0.81]), dementia (C-Index: 0.85 [95% CI: 0.82-0.87]), stroke (C-Index: 0.78 [95% CI: 0.76-0.81]), atrial fibrillation (C-Index: 0.78 [95% CI: 0.75-0.81]), and myocardial infarction (C-Index: 0.81 [95% CI: 0.78-0.84]). The model's generalizability was further validated through strong performance on the Sleep Heart Health Study (SHHS), a dataset unseen during pre-training. Additionally, SleepFM demonstrates strong performance on traditional sleep analysis tasks, achieving competitive results in both sleep staging (mean F1 scores: 0.70-0.78) and sleep apnea diagnosis (AUROC: 0.90-0.94). Beyond these standard applications, our analysis reveals that specific sleep stages and physiological signals carry distinct predictive power for different diseases. This work demonstrates how foundation models can leverage sleep polysomnography data to uncover the extensive relationship between sleep physiology and future disease risk.

  View details for DOI 10.1101/2025.02.04.25321675

  View details for PubMedID 39974074

  View details for PubMedCentralID PMC11838666

• Early Burst Suppression Similarity Association with Structural Brain Injury Severity on MRI After Cardiac Arrest. Neurocritical care Shivdat, S., Zhan, T., De Palma, A., Zheng, W. L., Krishnamurthy, P., Paneerselvam, E., Snider, S., Bevers, M., O'Reilly, U. M., Lee, J. W., Westover, M. B., Amorim, E. 2025; 42 (1): 175-184

  Abstract

  Identical bursts on electroencephalography (EEG) are considered a specific predictor of poor outcomes in cardiac arrest, but its relationship with structural brain injury severity on magnetic resonance imaging (MRI) is not known.This was a retrospective analysis of clinical, EEG, and MRI data from adult comatose patients after cardiac arrest. Burst similarity in first 72 h from the time of return of spontaneous circulation were calculated using dynamic time-warping (DTW) for bursts of equal (i.e., 500 ms) and varying (i.e., 100-500 ms) lengths and cross-correlation for bursts of equal lengths. Structural brain injury severity was measured using whole brain mean apparent diffusion coefficient (ADC) on MRI. Pearson's correlation coefficients were calculated between mean burst similarity across consecutive 12-24-h time blocks and mean whole brain ADC values. Good outcome was defined as Cerebral Performance Category of 1-2 (i.e., independence for activities of daily living) at the time of hospital discharge.Of 113 patients with cardiac arrest, 45 patients had burst suppression (mean cardiac arrest to MRI time 4.3 days). Three study participants with burst suppression had a good outcome. Burst similarity calculated using DTW with bursts of varying lengths was correlated with mean ADC value in the first 36 h after cardiac arrest: Pearson's r: 0-12 h: - 0.69 (p = 0.039), 12-24 h: - 0.54 (p = 0.002), 24-36 h: - 0.41 (p = 0.049). Burst similarity measured with bursts of equal lengths was not associated with mean ADC value with cross-correlation or DTW, except for DTW at 60-72 h (- 0.96, p = 0.04).Burst similarity on EEG after cardiac arrest may be associated with acute brain injury severity on MRI. This association was time dependent when measured using DTW.

  View details for DOI 10.1007/s12028-024-02047-6

  View details for PubMedID 39043984

  View details for PubMedCentralID PMC11757804

• What radio waves tell us about sleep! Sleep He, H., Li, C., Ganglberger, W., Gallagher, K., Hristov, R., Ouroutzoglou, M., Sun, H., Sun, J., Westover, M. B., Katabi, D. 2025; 48 (1)

  Abstract

  The ability to assess sleep at home, capture sleep stages, and detect the occurrence of apnea (without on-body sensors) simply by analyzing the radio waves bouncing off people's bodies while they sleep is quite powerful. Such a capability would allow for longitudinal data collection in patients' homes, informing our understanding of sleep and its interaction with various diseases and their therapeutic responses, both in clinical trials and routine care. In this article, we develop an advanced machine-learning algorithm for passively monitoring sleep and nocturnal breathing from radio waves reflected off people while asleep. Validation results in comparison with the gold standard (i.e. polysomnography; n = 880) demonstrate that the model captures the sleep hypnogram (with an accuracy of 80.5% for 30-second epochs categorized into wake, light sleep, deep sleep, or REM), detects sleep apnea (AUROC = 0.89), and measures the patient's Apnea-Hypopnea Index (ICC = 0.90; 95% CI = [0.88, 0.91]). Notably, the model exhibits equitable performance across race, sex, and age. Moreover, the model uncovers informative interactions between sleep stages and a range of diseases including neurological, psychiatric, cardiovascular, and immunological disorders. These findings not only hold promise for clinical practice and interventional trials but also underscore the significance of sleep as a fundamental component in understanding and managing various diseases.

  View details for DOI 10.1093/sleep/zsae187

  View details for PubMedID 39155830

  View details for PubMedCentralID PMC11725512

• High-Throughput Phenotyping of the Symptoms of Alzheimer Disease and Related Dementias Using Large Language Models: Cross-Sectional Study JMIR AI Cheng, Y., Malekar, M., He, Y., Bommareddy, A., Magdamo, C., Singh, A., Westover, B., Mukerji, S. S., Dickson, J., Das, S. 2025; 4: e66926

  Abstract

  Alzheimer disease and related dementias (ADRD) are complex disorders with overlapping symptoms and pathologies. Comprehensive records of symptoms in electronic health records (EHRs) are critical for not only reaching an accurate diagnosis but also supporting ongoing research studies and clinical trials. However, these symptoms are frequently obscured within unstructured clinical notes in EHRs, making manual extraction both time-consuming and labor-intensive.We aimed to automate symptom extraction from the clinical notes of patients with ADRD using fine-tuned large language models (LLMs), compare its performance to regular expression-based symptom recognition, and validate the results using brain magnetic resonance imaging (MRI) data.We fine-tuned LLMs to extract ADRD symptoms across the following 7 domains: memory, executive function, motor, language, visuospatial, neuropsychiatric, and sleep. We assessed the algorithm's performance by calculating the area under the receiver operating characteristic curve (AUROC) for each domain. The extracted symptoms were then validated in two analyses: (1) predicting ADRD diagnosis using the counts of extracted symptoms and (2) examining the association between ADRD symptoms and MRI-derived brain volumes.Symptom extraction across the 7 domains achieved high accuracy with AUROCs ranging from 0.97 to 0.99. Using the counts of extracted symptoms to predict ADRD diagnosis yielded an AUROC of 0.83 (95% CI 0.77-0.89). Symptom associations with brain volumes revealed that a smaller hippocampal volume was linked to memory impairments (odds ratio 0.62, 95% CI 0.46-0.84; P=.006), and reduced pallidum size was associated with motor impairments (odds ratio 0.73, 95% CI 0.58-0.90; P=.04).These results highlight the accuracy and reliability of our high-throughput ADRD phenotyping algorithm. By enabling automated symptom extraction, our approach has the potential to assist with differential diagnosis, as well as facilitate clinical trials and research studies of dementia.

  View details for DOI 10.2196/66926

  View details for Web of Science ID 001513430100001

  View details for PubMedID 40460418

  View details for PubMedCentralID PMC12174885

• Real-World Continuous EEG Utilization and Outcomes in Hospitalized Patients With Acute Cerebrovascular Diseases. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Amerineni, R., Sun, H., Fernandes, M. B., Westover, M. B., Moura, L., Patorno, E., Hsu, J., Zafar, S. F. 2025; 42 (1): 20-27

  Abstract

  Continuous electroencephalography (cEEG) is recommended for hospitalized patients with cerebrovascular diseases and suspected seizures or unexplained neurologic decline. We sought to (1) identify areas of practice variation in cEEG utilization, (2) determine predictors of cEEG utilization, (3) evaluate whether cEEG utilization is associated with outcomes in patients with cerebrovascular diseases.This cohort study of the Premier Healthcare Database (2014-2020), included hospitalized patients age > 18 years with cerebrovascular diseases (identified by ICD codes). Continuous electroencephalography was identified by International Classification of Diseases (ICD)/Current Procedural Terminology (CPT) codes. Multivariable lasso logistic regression was used to identify predictors of cEEG utilization and in-hospital mortality. Propensity score-matched analysis was performed to determine the relation between cEEG use and mortality.1,179,471 admissions were included; 16,777 (1.4%) underwent cEEG. Total number of cEEGs increased by 364% over 5 years (average 32%/year). On multivariable analysis, top five predictors of cEEG use included seizure diagnosis, hospitals with >500 beds, regions Northeast and South, and anesthetic use. Top predictors of mortality included use of mechanical ventilation, vasopressors, anesthetics, antiseizure medications, and age. Propensity analysis showed that cEEG was associated with lower in-hospital mortality (Average Treatment Effect -0.015 [95% confidence interval -0.028 to -0.003], Odds ratio 0.746 [95% confidence interval, 0.618-0.900]).There has been a national increase in cEEG utilization for hospitalized patients with cerebrovascular diseases, with practice variation. cEEG utilization was associated with lower in-hospital mortality. Larger comparative studies of cEEG-guided treatments are indicated to inform best practices, guide policy changes for increased access, and create guidelines on triaging and transferring patients to centers with cEEG capability.

  View details for DOI 10.1097/WNP.0000000000001043

  View details for PubMedID 37938032

  View details for PubMedCentralID PMC11058112

• Daily Automated Prediction of Delirium Risk in Hospitalized Patients: Model Development and Validation JMIR MEDICAL INFORMATICS Shaw, K., Shao, Y., Ghanta, M., Moura, V., Kimchi, E. Y., Houle, T., Akeju, O., Westover, M. 2025; 13: e60442

  Abstract

  Delirium is common in hospitalized patients and is correlated with increased morbidity and mortality. Despite this, delirium is underdiagnosed, and many institutions do not have sufficient resources to consistently apply effective screening and prevention.This study aims to develop a machine learning algorithm to identify patients at the highest risk of delirium in the hospital each day in an automated fashion based on data available in the electronic medical record, reducing the barrier to large-scale delirium screening.We developed and compared multiple machine learning models on a retrospective dataset of all hospitalized adult patients with recorded Confusion Assessment Method (CAM) screens at a major academic medical center from April 2, 2016, to January 16, 2019, comprising 23,006 patients. The patient's age, gender, and all available laboratory values, vital signs, prior CAM screens, and medication administrations were used as potential predictors. Four machine learning approaches were investigated: logistic regression with L1-regularization, multilayer perceptrons, random forests, and boosted trees. Model development used 80% of the patients; the remaining 20% was reserved for testing the final models. Laboratory values, vital signs, medications, gender, and age were used to predict a positive CAM screen in the next 24 hours.The boosted tree model achieved the greatest predictive power, with an area under the receiver operator characteristic curve (AUROC) of 0.92 (95% CI 0.913-9.22), followed by the random forest (AUROC 0.91, 95% CI 0.909-0.918), multilayer perceptron (AUROC 0.86, 95% CI 0.850-0.861), and logistic regression (AUROC 0.85, 95% CI 0.841-0.852). These AUROCs decreased to 0.78-0.82 and 0.74-0.80 when limited to patients who currently do not or never have had delirium, respectively.A boosted tree machine learning model was able to identify hospitalized patients at elevated risk for delirium in the next 24 hours. This may allow for automated delirium risk screening and more precise targeting of proven and investigational interventions to prevent delirium.

  View details for DOI 10.2196/60442

  View details for Web of Science ID 001477763300001

  View details for PubMedID 39721068

  View details for PubMedCentralID PMC12048784

• Morphological Prediction of Continuous Positive Airway Pressure-associated Acute Respiratory Instability ANNALS OF THE AMERICAN THORACIC SOCIETY Nassi, T., Oppersma, E., Labarca, G., Donker, D. W., Westover, M., Thomas, R. J. 2025; 22 (1): 138-149

  Abstract

  Rationale: Multiple mechanisms are involved in the pathogenesis of obstructive sleep apnea (OSA). Increased loop gain (LG) is a key target for precision OSA care and may be associated with treatment intolerance when the upper airway is the sole therapeutic target. Morphological or computational estimation of LG is not yet widely available or fully validated, and there is a need for improved phenotyping and/or endotyping of apnea to advance its therapy and prognosis. Objectives: This study proposes a new algorithm to assess self-similarity (SS) as a signature of increased LG using respiratory effort signals and presents its use to predict the probability of acute failure (i.e., high residual event counts) of continuous positive airway pressure therapy. Methods: Effort signals from 2,145 split-night polysomnography studies from the Massachusetts General Hospital were analyzed for SS and used to predict acute continuous positive airway pressure therapy effectiveness. Logistic regression models were trained and evaluated using fivefold cross-validation. Results: Receiver operating characteristic and precision-recall curves with area under the curve values of 0.82 and 0.84, respectively, were obtained. SS combined with the central apnea index (CAI) and hypoxic burden outperformed CAI alone. Even in those with a low CAI by conventional scoring criteria or only mild desaturation, SS was related to poor therapy outcomes. Conclusions: The proposed algorithm for assessing SS as a measure of expressed high LG is accurate and noninvasive and has the potential to improve phenotyping and/or endotyping of apnea, leading to more precise OSA treatment strategies.

  View details for DOI 10.1513/AnnalsATS.202311-979OC

  View details for Web of Science ID 001417968200018

  View details for PubMedID 39288402

  View details for PubMedCentralID PMC11708763

• Teaching the 6 EEG Spectrogram Patterns Using an Infographic. Neurology. Education Marcinski Nascimento, K. J., Westover, M. B., Nascimento, F. A. 2024; 3 (4): e200158

  View details for DOI 10.1212/NE9.0000000000200158

  View details for PubMedID 39360183

  View details for PubMedCentralID PMC11436318

• Necessary for seizure forecasting outcome metrics: Seizure frequency and benchmark model. Epilepsy research Chang, C. Y., Zhang, B., Moss, R., Picard, R., Westover, M. B., Goldenholz, D. 2024; 208: 107474

  Abstract

  This study aims to illustrate the connection between seizure frequency (SF) and performance metrics in seizure forecasting, and to compare the effectiveness of a moving average (MA) model versus the commonly used permutation benchmark.Metrics of calibration and discrimination were computed for each dataset, comparing MA and permutation performance across SF values. Three datasets were used: (1) self-reported seizure diaries from 3994 Seizure Tracker patients, (2) automatically detected and sometimes manually reported or edited generalized tonic-clonic seizures from 2350 Empatica Embrace 2 and Mate App users, and (3) simulated datasets with varying SFs.Most metrics were found to depend on SF. The MA model outperformed or matched the permutation model in all cases. These more advanced metrics show that comparison to permutation will falsely elevate poor forecasting models.The findings highlight SF's role in seizure forecasting accuracy and the MA model's suitability as a benchmark. This study underscores the need for considering patient SF in forecasting studies and suggests the MA model may provide a better standard for evaluating future seizure forecasting models.

  View details for DOI 10.1016/j.eplepsyres.2024.107474

  View details for PubMedID 39522392

  View details for PubMedCentralID PMC11614381

• Correction: Identifying inpatient hospitalizations with continuous electroencephalogram monitoring from administrative data. BMC health services research Fernandes, M., Westover, M. B., Zafar, S. F. 2024; 24 (1): 1383

  View details for DOI 10.1186/s12913-024-11896-y

  View details for PubMedID 39533265

  View details for PubMedCentralID PMC11555795

• Corrigendum: The predictive validity of a Brain Care Score for late-life depression and a composite outcome of dementia, stroke, and late-life depression: data from the UK Biobank cohort. Frontiers in psychiatry Singh, S. D., Rivier, C. A., Papier, K., Chemali, Z., Gutierrez-Martinez, L., Parodi, L., Mayerhofer, E., Senff, J., Clocchiatti-Tuozzo, S., Nunley, C., Newhouse, A., Ouyang, A., Westover, M. B., Tanzi, R. E., Lazar, R. M., Pikula, A., Ibrahim, S., Brouwers, H. B., Howard, V. J., Howard, G., Yechoor, N., Littlejohns, T., Sheth, K. N., Rosand, J., Fricchione, G., Anderson, C. D., Falcone, G. J. 2024; 15: 1502482

  Abstract

  [This corrects the article DOI: 10.3389/fpsyt.2024.1373797.].

  View details for DOI 10.3389/fpsyt.2024.1502482

  View details for PubMedID 39600788

  View details for PubMedCentralID PMC11589155

• Automated Medical Records Review for Mild Cognitive Impairment and Dementia. Research square Wei, R., Buss, S. S., Milde, R., Fernandes, M., Sumsion, D., Davis, E., Kong, W. Y., Xiong, Y., Veltink, J., Rao, S., Westover, T. M., Petersen, L., Turley, N., Singh, A., Das, S., Junior, V. M., Ghanta, M., Gupta, A., Kim, J., Lam, A. D., Stone, K. L., Mignot, E., Hwang, D., Trotti, L. M., Clifford, G. D., Katwa, U., Thomas, R. J., Mukerji, S., Zafar, S. F., Westover, M. B., Sun, H. 2024

  Abstract

  Unstructured and structured data in electronic health records (EHR) are a rich source of information for research and quality improvement studies. However, extracting accurate information from EHR is labor-intensive. Here we introduce an automated EHR phenotyping model to identify patients with Alzheimer's Disease, related dementias (ADRD), or mild cognitive impairment (MCI).We assembled medical notes and associated International Classification of Diseases (ICD) codes and medication prescriptions from 3,626 outpatient adults from two hospitals seen between February 2015 and June 2022. Ground truth annotations regarding the presence vs. absence of a diagnosis of MCI or ADRD were determined through manual chart review. Indicators extracted from notes included the presence of keywords and phrases in unstructured clinical notes, prescriptions of medications associated with MCI/ADRD, and ICD codes associated with MCI/ADRD. We trained a regularized logistic regression model to predict the ground truth annotations. Model performance was evaluated using area under the receiver operating curve (AUROC), area under the precision-recall curve (AUPRC), accuracy, specificity, precision/positive predictive value, recall/sensitivity, and F1 score (harmonic mean of precision and recall).Thirty percent of patients in the cohort carried diagnoses of MCI/ADRD based on manual review. When evaluated on a held-out test set, the best model using clinical notes, ICDs, and medications, achieved an AUROC of 0.98, an AUPRC of 0.98, an accuracy of 0.93, a sensitivity (recall) of 0.91, a specificity of 0.96, a precision of 0.96, and an F1 score of 0.93 The estimated overall accuracy for patients randomly selected from EHRs was 99.88%.Automated EHR phenotyping accurately identifies patients with MCI/ADRD based on clinical notes, ICD codes, and medication records. This approach holds potential for large-scale MCI/ADRD research utilizing EHR databases.

  View details for DOI 10.21203/rs.3.rs-5046441/v1

  View details for PubMedID 39315274

  View details for PubMedCentralID PMC11419186

• Automated Extraction of Stroke Severity From Unstructured Electronic Health Records Using Natural Language Processing JOURNAL OF THE AMERICAN HEART ASSOCIATION Fernandes, M., Westover, M., Singhal, A. B., Zafar, S. F. 2024; 13 (21): e036386

  Abstract

  Multicenter electronic health records can support quality improvement and comparative effectiveness research in stroke. However, limitations of electronic health record-based research include challenges in abstracting key clinical variables, including stroke severity, along with missing data. We developed a natural language processing model that reads electronic health record notes to directly extract the National Institutes of Health Stroke Scale score when documented and predict the score from clinical documentation when missing.The study included notes from patients with acute stroke (aged ≥18 years) admitted to Massachusetts General Hospital (2015-2022). The Massachusetts General Hospital data were divided into training/holdout test (70%/30%) sets. We developed a 2-stage model to predict the admission National Institutes of Health Stroke Scale, obtained from the GWTG (Get With The Guidelines) stroke registry. We trained a model with the least absolute shrinkage and selection operator. For test notes with documented National Institutes of Health Stroke Scale, scores were extracted using regular expressions (stage 1); when not documented, least absolute shrinkage and selection operator was used for prediction (stage 2). The 2-stage model was tested on the holdout test set and validated in the Medical Information Mart for Intensive Care (2001-2012) version 1.4, using root mean squared error and Spearman correlation. We included 4163 patients (Massachusetts General Hospital, 3876; Medical Information Mart for Intensive Care, 287); average age, 69 (SD, 15) years; 53% men, and 72% White individuals. The model achieved a root mean squared error of 2.89 (95% CI, 2.62-3.19) and Spearman correlation of 0.92 (95% CI, 0.91-0.93) in the Massachusetts General Hospital test set, and 2.20 (95% CI, 1.69-2.66) and 0.96 (95% CI, 0.94-0.97) in the MIMIC validation set, respectively.The automatic natural language processing-based model can enable large-scale stroke severity phenotyping from the electronic health record and support real-world quality improvement and comparative effectiveness studies in stroke.

  View details for DOI 10.1161/JAHA.124.036386

  View details for Web of Science ID 001347605900001

  View details for PubMedID 39450737

  View details for PubMedCentralID PMC11935650

• Extracting seizure control metrics from clinic notes of patients with epilepsy: A natural language processing approach. Epilepsy research Fernandes, M., Cardall, A., Moura, L. M., McGraw, C., Zafar, S. F., Westover, M. B. 2024; 207: 107451

  Abstract

  Monitoring seizure control metrics is key to clinical care of patients with epilepsy. Manually abstracting these metrics from unstructured text in electronic health records (EHR) is laborious. We aimed to abstract the date of last seizure and seizure frequency from clinical notes of patients with epilepsy using natural language processing (NLP).We extracted seizure control metrics from notes of patients seen in epilepsy clinics from two hospitals in Boston. Extraction was performed with the pretrained model RoBERTa_for_seizureFrequency_QA, for both date of last seizure and seizure frequency, combined with regular expressions. We designed the algorithm to categorize the timing of last seizure ("today", "1-6 days ago", "1-4 weeks ago", "more than 1-3 months ago", "more than 3-6 months ago", "more than 6-12 months ago", "more than 1-2 years ago", "more than 2 years ago") and seizure frequency ("innumerable", "multiple", "daily", "weekly", "monthly", "once per year", "less than once per year"). Our ground truth consisted of structured questionnaires filled out by physicians. Model performance was measured using the areas under the receiving operating characteristic curve (AUROC) and precision recall curve (AUPRC) for categorical labels, and median absolute error (MAE) for ordinal labels, with 95 % confidence intervals (CI) estimated via bootstrapping.Our cohort included 1773 adult patients with a total of 5658 visits with reported seizure control metrics, seen in epilepsy clinics between December 2018 and May 2022. The cohort average age was 42 years old, the majority were female (57 %), White (81 %) and non-Hispanic (85 %). The models achieved an MAE (95 % CI) for date of last seizure of 4 (4.00-4.86) weeks, and for seizure frequency of 0.02 (0.02-0.02) seizures per day.Our NLP approach demonstrates that the extraction of seizure control metrics from EHR is feasible allowing for large-scale EHR research.

  View details for DOI 10.1016/j.eplepsyres.2024.107451

  View details for PubMedID 39276641

  View details for PubMedCentralID PMC11499027

• Corrigendum to "A real-time neurophysiologic stress test for the aging brain: Novel perioperative and ICU applications of EEG in older surgical patients" Neurotherapeutics 20 (4) (2023) 975-1000. Neurotherapeutics : the journal of the American Society for Experimental NeuroTherapeutics Berger, M., Ryu, D., Reese, M., McGuigan, S., Evered, L. A., Price, C. C., Scott, D. A., Westover, M. B., Eckenhoff, R., Bonanni, L., Sweeney, A., Babiloni, C. 2024: e00473

  View details for DOI 10.1016/j.neurot.2024.e00473

  View details for PubMedID 39482181

• Corrigendum: Classification of autism spectrum disorder using electroencephalography in Chinese children: a cross- sectional retrospective study. Frontiers in neuroscience Ke, S. Y., Wu, H., Sun, H., Zhou, A., Liu, J., Zheng, X., Liu, K., Westover, M. B., Xu, H., Kong, X. J. 2024; 18: 1501782

  Abstract

  [This corrects the article DOI: 10.3389/fnins.2024.1330556.].

  View details for DOI 10.3389/fnins.2024.1501782

  View details for PubMedID 39534021

  View details for PubMedCentralID PMC11555438

• Commentary on stimulus-induced arousal with transient electroencephalographic improvement distinguishes nonictal from ictal generalized periodic discharges EPILEPSIA Ng, M. C., Zafar, S., Foreman, B., Kim, J., Struck, A. F., Westover, M. 2024; 65 (12): 3484-3487

  Abstract

  Here we critique recent arguments proposing to distinguish ictal from non-ictal generalized periodic discharges (GPDs) based on etiology and stimulation response, arguing that these are unreliable. We advocate for an empirical approach to GPDs: describe objectively, interpret through medication trials, and base further treatment on response. We call for evidence-based approaches considering meaningful clinical outcomes.

  View details for DOI 10.1111/epi.18159

  View details for Web of Science ID 001338864800001

  View details for PubMedID 39422357

  View details for PubMedCentralID PMC11649443

• Brain Care Score and Neuroimaging Markers of Brain Health in Asymptomatic Middle-Age Persons NEUROLOGY Rivier, C. A., Singh, S., Senff, J., Tack, R. W., Marini, S., Clocchiatti-Tuozzo, S., Huo, S., Renedo, D., Papier, K., Conroy, M., Littlejohns, T. J., Chemali, Z., Kourkoulis, C., Payabvash, S., Newhouse, A., Westover, M., Lazar, R. M., Pikula, A., Ibrahim, S., Howard, V. J., Howard, G., Brouwers, H., Van Duijn, C. M., Fricchione, G., Tanzi, R. E., Yechoor, N., Sheth, K. N., Anderson, C. D., Rosand, J., Falcone, G. J. 2024; 103 (4): e209687

  Abstract

  To investigate associations between health-related behaviors as measured using the Brain Care Score (BCS) and neuroimaging markers of white matter injury.This prospective cohort study in the UK Biobank assessed the BCS, a novel tool designed to empower patients to address 12 dementia and stroke risk factors. The BCS ranges from 0 to 21, with higher scores suggesting better brain care. Outcomes included white matter hyperintensities (WMH) volume, fractional anisotropy (FA), and mean diffusivity (MD) obtained during 2 imaging assessments, as well as their progression between assessments, using multivariable linear regression adjusted for age and sex.We included 34,509 participants (average age 55 years, 53% female) with no stroke or dementia history. At first and repeat imaging assessments, every 5-point increase in baseline BCS was linked to significantly lower WMH volumes (25% 95% CI [23%-27%] first, 33% [27%-39%] repeat) and higher FA (18% [16%-20%] first, 22% [15%-28%] repeat), with a decrease in MD (9% [7%-11%] first, 10% [4%-16%] repeat). In addition, a higher baseline BCS was associated with a 10% [3%-17%] reduction in WMH progression and FA decline over time.This study extends the impact of the BCS to neuroimaging markers of clinically silent cerebrovascular disease. Our results suggest that improving one's BCS could be a valuable intervention to prevent early brain health decline.

  View details for DOI 10.1212/WNL.0000000000209687

  View details for Web of Science ID 001314231700001

  View details for PubMedID 39052961

  View details for PubMedCentralID PMC11760050

• Prediction of Post-Operative Delirium in Older Adults from Preoperative Cognition and Alpha Power from Resting-State EEG. medRxiv : the preprint server for health sciences Ning, M., Rodionov, A., Ross, J. M., Ozdemir, R. A., Burch, M., Lian, S. J., Alsop, D., Cavallari, M., Dickerson, B. C., Fong, T. G., Jones, R. N., Libermann, T. A., Marcantonio, E. R., Santarnecchi, E., Schmitt, E. M., Touroutoglou, A., Travison, T. G., Acker, L., Reese, M., Sun, H., Westover, B., Berger, M., Pascual-Leone, A., Inouye, S. K., Shafi, M. M., SAGES II Study Group and the INTUIT/PRIME Study Groups 2024

  Abstract

  Postoperative Delirium (POD) is the most common complication following surgery among older adults, and has been consistently associated with increased mortality and morbidity, cognitive decline, and loss of independence, as well as markedly increased health-care costs. The development of new tools to identify individuals at high risk for POD could guide clinical decision-making and enable targeted interventions to potentially decrease delirium incidence and POD-related complications. In this study, we used machine learning techniques to evaluate whether baseline (pre-operative) cognitive function and resting-state electroencephalography could be used to identify patients at risk for POD. Pre-operative resting-state EEGs and the Montreal Cognitive Assessment (MoCA) were collected from 85 patients (age = 73 ± 6.4 years) undergoing elective surgery, 12 of whom subsequently developed POD. The model with the highest f1-score for predicting delirium, a linear-discriminant analysis (LDA) model incorporating MoCA scores and occipital alpha-band EEG features, was subsequently validated in an independent, prospective cohort of 51 older adults (age ≥ 60) undergoing elective surgery, 6 of whom developed POD. The LDA-based model, with a total of 7 features, was able to predict POD with area under the receiver operating characteristic curve, specificity and accuracy all >90%, and sensitivity > 80%, in the validation cohort. Notably, models incorporating both resting-state EEG and MoCA scores outperformed those including either EEG or MoCA alone. While requiring prospective validation in larger cohorts, these results suggest that prediction of POD with high accuracy may be feasible in clinical settings using simple and widely available clinical tools.

  View details for DOI 10.1101/2024.08.15.24312053

  View details for PubMedID 39185530

• A randomized controlled educational pilot trial of interictal epileptiform discharge identification for neurology residents. Epileptic disorders : international epilepsy journal with videotape Nascimento, F. A., Jing, J., Traner, C., Kong, W. Y., Olandoski, M., Kapur, S., Duhaime, E., Strowd, R., Moeller, J., Westover, M. B. 2024; 26 (4): 444-459

  Abstract

  To assess the effectiveness of an educational program leveraging technology-enhanced learning and retrieval practice to teach trainees how to correctly identify interictal epileptiform discharges (IEDs).This was a bi-institutional prospective randomized controlled educational trial involving junior neurology residents. The intervention consisted of three video tutorials focused on the six IFCN criteria for IED identification and rating 500 candidate IEDs with instant feedback either on a web browser (intervention 1) or an iOS app (intervention 2). The control group underwent no educational intervention ("inactive control"). All residents completed a survey and a test at the onset and offset of the study. Performance metrics were calculated for each participant.Twenty-one residents completed the study: control (n = 8); intervention 1 (n = 6); intervention 2 (n = 7). All but two had no prior EEG experience. Intervention 1 residents improved from baseline (mean) in multiple metrics including AUC (.74; .85; p < .05), sensitivity (.53; .75; p < .05), and level of confidence (LOC) in identifying IEDs/committing patients to therapy (1.33; 2.33; p < .05). Intervention 2 residents improved in multiple metrics including AUC (.81; .86; p < .05) and LOC in identifying IEDs (2.00; 3.14; p < .05) and spike-wave discharges (2.00; 3.14; p < .05). Controls had no significant improvements in any measure.This program led to significant subjective and objective improvements in IED identification. Rating candidate IEDs with instant feedback on a web browser (intervention 1) generated greater objective improvement in comparison to rating candidate IEDs on an iOS app (intervention 2). This program can complement trainee education concerning IED identification.

  View details for DOI 10.1002/epd2.20229

  View details for PubMedID 38669007

  View details for PubMedCentralID PMC11329359

• From sleep patterns to heart rhythm: Predicting atrial fibrillation from overnight polysomnograms. Journal of electrocardiology Koscova, Z., Rad, A. B., Nasiri, S., Reyna, M. A., Sameni, R., Trotti, L. M., Sun, H., Turley, N., Stone, K. L., Thomas, R. J., Mignot, E., Westover, B., Clifford, G. D. 2024; 86: 153759

  Abstract

  Atrial fibrillation (AF) is often asymptomatic and thus under-observed. Given the high risks of stroke and heart failure among patients with AF, early prediction and effective management are crucial. Given the prevalence of obstructive sleep apnea among AF patients, electrocardiogram (ECG) analysis from polysomnography (PSG) offers a unique opportunity for early AF prediction. Our aim is to identify individuals at high risk of AF development from single‑lead ECGs during standard PSG.We analyzed 18,782 single‑lead ECG recordings from 13,609 subjects undergoing PSG at the Massachusetts General Hospital sleep laboratory. AF presence was identified using ICD-9/10 codes. The dataset included 15,913 recordings without AF history and 2054 recordings from patients diagnosed with AF between one month to fifteen years post-PSG. Data were partitioned into training, validation, and test cohorts ensuring that individual patients remained exclusive to each cohort. The test set was held out during the training process. We employed two different methods for feature extraction to build a final model for AF prediction: Extraction of hand-crafted ECG features and a deep learning method. For extraction of ECG-hand-crafted features, recordings were split into 30-s windows, and those with a signal quality index (SQI) below 0.95 were discarded. From each remaining window, 150 features were extracted from the time, frequency, time-frequency domains, and phase-space reconstructions of the ECG. A compilation of 12 statistical features summarized these window-specific features per recording, resulting in 1800 features (12 × 150). A pre-trained deep neural network from the PhysioNet Challenge 2021 was updated using transfer learning to discriminate recordings with and without AF. The model processed PSG ECGs in 16-s windows to generate AF probabilities, from which 13 statistical features were extracted. Combining 1800 features from feature extraction with 13 from the deep learning model, we performed a feature selection and subsequently trained a shallow neural network to predict future AF and evaluated its performance on the test cohort.On the test set, our model exhibited sensitivity, specificity, and precision of 0.67, 0.81, and 0.3, respectively, for AF prediction. Survival analysis revealed a hazard ratio of 8.36 (p-value: 1.93 × 10-52) for AF outcomes using the log-rank test.Our proposed ECG analysis method, utilizing overnight PSG data, shows promise in AF prediction despite modest precision, suggesting false positives. This approach could enable low-cost screening and proactive treatment for high-risk patients. Refinements, including additional physiological parameters, may reduce false positives, enhancing clinical utility and accuracy.

  View details for DOI 10.1016/j.jelectrocard.2024.153759

  View details for PubMedID 39067281

• Improving Clinician Performance in Classifying EEG Patterns on the Ictal-Interictal Injury Continuum Using Interpretable Machine Learning. NEJM AI Barnett, A. J., Guo, Z., Jing, J., Ge, W., Kaplan, P. W., Kong, W. Y., Karakis, I., Herlopian, A., Jayagopal, L. A., Taraschenko, O., Selioutski, O., Osman, G., Goldenholz, D., Rudin, C., Westover, M. B. 2024; 1 (6)

  Abstract

  In intensive care units (ICUs), critically ill patients are monitored with electroencephalography (EEG) to prevent serious brain injury. EEG monitoring is constrained by clinician availability, and EEG interpretation can be subjective and prone to interobserver variability. Automated deep-learning systems for EEG could reduce human bias and accelerate the diagnostic process. However, existing uninterpretable (black-box) deep-learning models are untrustworthy, difficult to troubleshoot, and lack accountability in real-world applications, leading to a lack of both trust and adoption by clinicians.We developed an interpretable deep-learning system that accurately classifies six patterns of potentially harmful EEG activity - seizure, lateralized periodic discharges (LPDs), generalized periodic discharges (GPDs), lateralized rhythmic delta activity (LRDA), generalized rhythmic delta activity (GRDA), and other patterns - while providing faithful case-based explanations of its predictions. The model was trained on 50,697 total 50-second continuous EEG samples collected from 2711 patients in the ICU between July 2006 and March 2020 at Massachusetts General Hospital. EEG samples were labeled as one of the six EEG patterns by 124 domain experts and trained annotators. To evaluate the model, we asked eight medical professionals with relevant backgrounds to classify 100 EEG samples into the six pattern categories - once with and once without artificial intelligence (AI) assistance - and we assessed the assistive power of this interpretable system by comparing the diagnostic accuracy of the two methods. The model's discriminatory performance was evaluated with area under the receiver-operating characteristic curve (AUROC) and area under the precision-recall curve. The model's interpretability was measured with task-specific neighborhood agreement statistics that interrogated the similarities of samples and features. In a separate analysis, the latent space of the neural network was visualized by using dimension reduction techniques to examine whether the ictal-interictal injury continuum hypothesis, which asserts that seizures and seizure-like patterns of brain activity lie along a spectrum, is supported by data.The performance of all users significantly improved when provided with AI assistance. Mean user diagnostic accuracy improved from 47 to 71% (P<0.04). The model achieved AUROCs of 0.87, 0.93, 0.96, 0.92, 0.93, and 0.80 for the classes seizure, LPD, GPD, LRDA, GRDA, and other patterns, respectively. This performance was significantly higher than that of a corresponding uninterpretable black-box model (with P<0.0001). Videos traversing the ictal-interictal injury manifold from dimension reduction (a two-dimensional representation of the original high-dimensional feature space) give insight into the layout of EEG patterns within the network's latent space and illuminate relationships between EEG patterns that were previously hypothesized but had not yet been shown explicitly. These results indicate that the ictal-interictal injury continuum hypothesis is supported by data.Users showed significant pattern classification accuracy improvement with the assistance of this interpretable deep-learning model. The interpretable design facilitates effective human-AI collaboration; this system may improve diagnosis and patient care in clinical settings. The model may also provide a better understanding of how EEG patterns relate to each other along the ictal-interictal injury continuum. (Funded by the National Science Foundation, National Institutes of Health, and others.).

  View details for DOI 10.1056/aioa2300331

  View details for PubMedID 38872809

  View details for PubMedCentralID PMC11175595

• Resting-state EEG patterns of preschool-aged boys with autism spectrum disorder: A pilot study. Applied neuropsychology. Child Zhao, Q., Luo, Y., Mei, X., Shao, Z. 2024; 13 (4): 413-420

  Abstract

  Defective cognition development during preschool years is believed to be linked with core symptoms of autism spectrum disorder (ASD). Neurophysiological research on mechanisms underly the cognitive disabilities of preschool-aged children with ASD is scarce currently. This pilot study aimed to compare the resting spectral EEG power of preschool-aged boys with ASD with their matched typically developing peers. Children in the ASD group demonstrated reduced central and posterior absolute delta (1-4 Hz) and enhanced frontal absolute beta (12-30 Hz) and gamma (30-45 Hz). The relative power of the ASD group was elevated in delta, theta (4-8 Hz), alpha (8-12 Hz), beta, and gamma bands as compared to the controls. The theta/beta ratio decreased in the frontal regions and enhanced at Cz and Pz electrodes in the ASD group. Correlations between the inhibition and metacognition indices of the behavior rating inventory of executive function-preschool version (BRIEF-P) and the theta/beta ratio for children of both groups were significant. In conclusion, the present study revealed atypical resting spectral characteristics of boys with ASD at preschool ages. Future large-sampled studies for the generalization of our findings and a better understanding of the relationships between brain oscillations and phenotypes of ASD are warranted.

  View details for DOI 10.1080/21622965.2023.2211702

  View details for PubMedID 37172019

• Generalized Periodic Discharges Associated With Catatonia and Delirium: A Case Series. The Journal of neuropsychiatry and clinical neurosciences Luccarelli, J., Smith, J. R., Fricchione, G., Westover, M. B. 2024; 36 (4): 340-343

  Abstract

  Generalized periodic discharges are a repeated and generalized electroencephalography (EEG) pattern that can be seen in the context of altered mental status. This article describes a series of five individuals with generalized periodic discharges who demonstrated signs and symptoms of catatonia, a treatable neuropsychiatric condition.Inpatients with a clinical diagnosis of catatonia, determined with the Bush-Francis Catatonia Rating Scale (BFCRS), and EEG recordings with generalized periodic discharges were analyzed in a retrospective case series.Five patients with catatonia and generalized periodic discharges on EEG were evaluated from among 106 patients with catatonia and contemporaneous EEG measurements. Four of these patients showed an improvement in catatonia severity when treated with benzodiazepines, with an average reduction of 6.75 points on the BFCRS.Among patients with generalized periodic discharges, catatonia should be considered, in the appropriate clinical context. Patients with generalized periodic discharges and catatonia may benefit from treatment with empiric trials of benzodiazepines.

  View details for DOI 10.1176/appi.neuropsych.20230174

  View details for PubMedID 38720623

  View details for PubMedCentralID PMC11479820

• Minimum clinical utility standards for wearable seizure detectors: A simulation study. Epilepsia Goldenholz, D. M., Karoly, P. J., Viana, P. F., Nurse, E., Loddenkemper, T., Schulze-Bonhage, A., Vieluf, S., Bruno, E., Nasseri, M., Richardson, M. P., Brinkmann, B. H., Westover, M. B. 2024; 65 (4): 1017-1028

  Abstract

  Epilepsy management employs self-reported seizure diaries, despite evidence of seizure underreporting. Wearable and implantable seizure detection devices are now becoming more widely available. There are no clear guidelines about what levels of accuracy are sufficient. This study aimed to simulate clinical use cases and identify the necessary level of accuracy for each.Using a realistic seizure simulator (CHOCOLATES), a ground truth was produced, which was then sampled to generate signals from simulated seizure detectors of various capabilities. Five use cases were evaluated: (1) randomized clinical trials (RCTs), (2) medication adjustment in clinic, (3) injury prevention, (4) sudden unexpected death in epilepsy (SUDEP) prevention, and (5) treatment of seizure clusters. We considered sensitivity (0%-100%), false alarm rate (FAR; 0-2/day), and device type (external wearable vs. implant) in each scenario.The RCT case was efficient for a wide range of wearable parameters, though implantable devices were preferred. Lower accuracy wearables resulted in subtle changes in the distribution of patients enrolled in RCTs, and therefore higher sensitivity and lower FAR values were preferred. In the clinic case, a wide range of sensitivity, FAR, and device type yielded similar results. For injury prevention, SUDEP prevention, and seizure cluster treatment, each scenario required high sensitivity and yet was minimally influenced by FAR.The choice of use case is paramount in determining acceptable accuracy levels for a wearable seizure detection device. We offer simulation results for determining and verifying utility for specific use case and specific wearable parameters.

  View details for DOI 10.1111/epi.17917

  View details for PubMedID 38366862

  View details for PubMedCentralID PMC11018505

• A neural mass model for disturbance of alpha rhythm in the minimal hepatic encephalopathy. Molecular and cellular neurosciences Song, J., Westover, M. B., Zhang, R. 2024; 128: 103918

  Abstract

  One of the early markers of minimal hepatic encephalopathy (MHE) is the disruption of alpha rhythm observed in electroencephalogram (EEG) signals. However, the underlying mechanisms responsible for this occurrence remain poorly understood. To address this gap, we develop a novel biophysical model MHE-AWD-NCM, encompassing the communication dynamics between a cortical neuron population (CNP) and an astrocyte population (AP), aimed at investigating the relationship between alpha wave disturbance (AWD) and mechanistical principles, specifically concerning astrocyte-neuronal communication in the context of MHE. In addition, we introduce the concepts of peak power density and peak frequency within the alpha band as quantitative measures of AWD. Our model faithfully reproduces the characteristic EEG phenomenology during MHE and shows how impairments of communication between CNP and AP could promote AWD. The results suggest that the disruptions in feedback neurotransmission from AP to CNP, along with the inhibition of GABA uptake by AP from the extracellular space, contribute to the observed AWD. Moreover, we found that the variation of external excitatory stimuli on CNP may play a key role in AWD in MHE. Finally, the sensitivity analysis is also performed to assess the relative significance of above factors in influencing AWD. Our findings align with the physiological observations and provide a more comprehensive understanding of the complex interplay of astrocyte-neuronal communication that underlies the AWD observed in MHE, which potentially may help to explore the targeted therapeutic interventions for the early stage of hepatic encephalopathy.

  View details for DOI 10.1016/j.mcn.2024.103918

  View details for PubMedID 38296121

• Altered Motor Activity Patterns within 10-Minute Timescale Predict Incident Clinical Alzheimer's Disease. Journal of Alzheimer's disease : JAD Sun, H., Li, P., Gao, L., Yang, J., Yu, L., Buchman, A. S., Bennett, D. A., Westover, M. B., Hu, K. 2024; 98 (1): 209-220

  Abstract

  Fractal motor activity regulation (FMAR), characterized by self-similar temporal patterns in motor activity across timescales, is robust in healthy young humans but degrades with aging and in Alzheimer's disease (AD).To determine the timescales where alterations of FMAR can best predict the clinical onset of AD.FMAR was assessed from actigraphy at baseline in 1,077 participants who had annual follow-up clinical assessments for up to 15 years. Survival analysis combined with deep learning (DeepSurv) was used to examine how baseline FMAR at different timescales from 3 minutes up to 6 hours contributed differently to the risk for incident clinical AD.Clinical AD occurred in 270 participants during the follow-up. DeepSurv identified three potential regions of timescales in which FMAR alterations were significantly linked to the risk for clinical AD: <10, 20-40, and 100-200 minutes. Confirmed by the Cox and random survival forest models, the effect of FMAR alterations in the timescale of <10 minutes was the strongest, after adjusting for covariates.Subtle changes in motor activity fluctuations predicted the clinical onset of AD, with the strongest association observed in activity fluctuations at timescales <10 minutes. These findings suggest that short actigraphy recordings may be used to assess the risk of AD.

  View details for DOI 10.3233/JAD-230928

  View details for PubMedID 38393904

  View details for PubMedCentralID PMC10977378

• Assessing Risk of Health Outcomes From Brain Activity in Sleep NEUROLOGY-CLINICAL PRACTICE Sun, H., Adra, N., Ayub, M., Ganglberger, W., Ye, E., Fernandes, M., Paixao, L., Fan, Z., Gupta, A., Ghanta, M., Moura Junior, V. F., Rosand, J., Westover, M., Thomas, R. J. 2024; 14 (1)

  View details for DOI 10.1212/CPJ.0000000000200225

  View details for Web of Science ID 001163611200007

• Cortical microstructural associations with CSF amyloid and pTau. Molecular psychiatry Nir, T. M., Villalón-Reina, J. E., Salminen, L. E., Haddad, E., Zheng, H., Thomopoulos, S. I., Jack, C. R., Weiner, M. W., Thompson, P. M., Jahanshad, N. 2024; 29 (2): 257-268

  Abstract

  Diffusion MRI (dMRI) can be used to probe microstructural properties of brain tissue and holds great promise as a means to non-invasively map Alzheimer's disease (AD) pathology. Few studies have evaluated multi-shell dMRI models such as neurite orientation dispersion and density imaging (NODDI) and mean apparent propagator (MAP)-MRI in cortical gray matter where many of the earliest histopathological changes occur in AD. Here, we investigated the relationship between CSF pTau181 and Aβ1-42 burden and regional cortical NODDI and MAP-MRI indices in 46 cognitively unimpaired individuals, 18 with mild cognitive impairment, and two with dementia (mean age: 71.8 ± 6.2 years) from the Alzheimer's Disease Neuroimaging Initiative. We compared findings to more conventional cortical thickness measures. Lower CSF Aβ1-42 and higher pTau181 were associated with cortical dMRI measures reflecting less hindered or restricted diffusion and greater diffusivity. Cortical dMRI measures, but not cortical thickness measures, were more widely associated with Aβ1-42 than pTau181 and better distinguished Aβ+ from Aβ- participants than pTau+ from pTau- participants. dMRI associations mediated the relationship between CSF markers and delayed logical memory performance, commonly impaired in early AD. dMRI metrics sensitive to early AD pathogenesis and microstructural damage may be better measures of subtle neurodegeneration in comparison to standard cortical thickness and help to elucidate mechanisms underlying cognitive decline.

  View details for DOI 10.1038/s41380-023-02321-7

  View details for PubMedID 38092890

  View details for PubMedCentralID PMC11116103

• Improving Neurology Clinical Care With Natural Language Processing Tools NEUROLOGY Ge, W., Rice, H. J., Sheikh, I. S., Westover, M., Weathers, A. L., Jones, L. K., Moura, L. 2023; 101 (22): 1010-1018

  Abstract

  The integration of natural language processing (NLP) tools into neurology workflows has the potential to significantly enhance clinical care. However, it is important to address the limitations and risks associated with integrating this new technology. Recent advances in transformer-based NLP algorithms (e.g., GPT, BERT) could augment neurology clinical care by summarizing patient health information, suggesting care options, and assisting research involving large datasets. However, these NLP platforms have potential risks including fabricated facts and data security and substantial barriers for implementation. Although these risks and barriers need to be considered, the benefits for providers, patients, and communities are substantial. With these systems achieving greater functionality and the pace of medical need increasing, integrating these tools into clinical care may prove not only beneficial but necessary. Further investigation is needed to design implementation strategies, mitigate risks, and overcome barriers.

  View details for DOI 10.1212/WNL.0000000000207853

  View details for Web of Science ID 001107690400010

  View details for PubMedID 37816638

  View details for PubMedCentralID PMC10727205

• An examination of sleep spindle metrics in the Sleep Heart Health Study: superiority of automated spindle detection over total sigma power in assessing age-related spindle decline. BMC neurology Palepu, K., Sadeghi, K., Kleinschmidt, D. F., Donoghue, J., Chapman, S., Arslan, A. R., Westover, M. B., Cash, S. S., Pathmanathan, J. 2023; 23 (1): 359

  Abstract

  Sleep spindle activity is commonly estimated by measuring sigma power during stage 2 non-rapid eye movement (NREM2) sleep. However, spindles account for little of the total NREM2 interval and therefore sigma power over the entire interval may be misleading. This study compares derived spindle measures from direct automated spindle detection with those from gross power spectral analyses for the purposes of clinical trial design.We estimated spindle activity in a set of 8,440 overnight electroencephalogram (EEG) recordings from 5,793 patients from the Sleep Heart Health Study using both sigma power and direct automated spindle detection. Performance of the two methods was evaluated by determining the sample size required to detect decline in age-related spindle coherence with each method in a simulated clinical trial.In a simulated clinical trial, sigma power required a sample size of 115 to achieve 95% power to identify age-related changes in sigma coherence, while automated spindle detection required a sample size of only 60.Measurements of spindle activity utilizing automated spindle detection outperformed conventional sigma power analysis by a wide margin, suggesting that many studies would benefit from incorporation of automated spindle detection. These results further suggest that some previous studies which have failed to detect changes in sigma power or coherence may have failed simply because they were underpowered.

  View details for DOI 10.1186/s12883-023-03376-3

  View details for PubMedID 37803266

  View details for PubMedCentralID PMC10557170

• Association Between Postoperative Delirium and Long-Term Subjective Cognitive Decline in Older Patients Undergoing Cardiac Surgery: A Secondary Analysis of the Minimizing Intensive Care Unit Neurological Dysfunction with Dexmedetomidine-Induced Sleep Trial. Journal of cardiothoracic and vascular anesthesia Namirembe, G. E., Baker, S., Albanese, M., Mueller, A., Qu, J. Z., Mekonnen, J., Wiredu, K., Westover, M. B., Houle, T. T., Akeju, O. 2023; 37 (9): 1700-1706

  Abstract

  This study aimed to evaluate whether a measure of subjective cognitive decline (SCD), the Patient-Reported Outcomes Measurement Information System (PROMIS) Applied Cognition-Abilities questionnaire, was associated with postoperative delirium. It was hypothesized that delirium during the surgical hospitalization would be associated with a decrease in subjective cognition up to 6 months after cardiac surgery.This was a secondary analysis of data from the Minimizing Intensive Care Unit Neurological Dysfunction with Dexmedetomidine-induced Sleep randomized, placebo-controlled, parallel-arm superiority trial.Data from patients recruited between March 2017 and February 2022 at a tertiary medical center in Boston, Massachusetts were analyzed in February 2023.Data from 337 patients aged 60 years or older who underwent cardiac surgery with cardiopulmonary bypass were included.Patients were assessed preoperatively and postoperatively at 30, 90, and 180 days using the subjective PROMIS Applied Cognition-Abilities and telephonic Montreal Cognitive Assessment.Postoperative delirium occurred within 3 days in 39 participants (11.6%). After adjusting for baseline function, participants who developed postoperative delirium self-reported worse cognitive function (mean difference [MD] -2.64 [95% CI -5.25, -0.04]; p = 0.047) up to 180 days after surgery, as compared with nondelirious patients. This finding was consistent with those obtained from objective t-MoCA assessments (MD -0.77 [95% CI -1.49, -0.04]; p = 0.04).In this cohort of older patients undergoing cardiac surgery, in-hospital delirium was associated with SCD up to 180 days after surgery. This finding suggested that measures of SCD may enable population-level insights into the burden of cognitive decline associated with postoperative delirium.

  View details for DOI 10.1053/j.jvca.2023.04.035

  View details for PubMedID 37217424

  View details for PubMedCentralID PMC10524446

• Neurophysiology State Dynamics Underlying Acute Neurologic Recovery After Cardiac Arrest NEUROLOGY Amorim, E., Zheng, W., Jing, J., Ghassemi, M. M., Lee, J., Wu, O., Herman, S. T., Pang, T., Sivaraju, A., Gaspard, N., Hirsch, L., Ruijter, B. J., Tjepkema-Cloostermans, M. C., Hofmeijer, J., van Putten, M. M., Westover, M. 2023; 101 (9): E940-E952

  Abstract

  Epileptiform activity and burst suppression are neurophysiology signatures reflective of severe brain injury after cardiac arrest. We aimed to delineate the evolution of coma neurophysiology feature ensembles associated with recovery from coma after cardiac arrest.Adults in acute coma after cardiac arrest were included in a retrospective database involving 7 hospitals. The combination of 3 quantitative EEG features (burst suppression ratio [BSup], spike frequency [SpF], and Shannon entropy [En]) was used to define 5 distinct neurophysiology states: epileptiform high entropy (EHE: SpF ≥4 per minute and En ≥5); epileptiform low entropy (ELE: SpF ≥4 per minute and <5 En); nonepileptiform high entropy (NEHE: SpF <4 per minute and ≥5 En); nonepileptiform low entropy (NELE: SpF <4 per minute and <5 En), and burst suppression (BSup ≥50% and SpF <4 per minute). State transitions were measured at consecutive 6-hour blocks between 6 and 84 hours after return of spontaneous circulation. Good neurologic outcome was defined as best cerebral performance category 1-2 at 3-6 months.One thousand thirty-eight individuals were included (50,224 hours of EEG), and 373 (36%) had good outcome. Individuals with EHE state had a 29% rate of good outcome, while those with ELE had 11%. Transitions out of an EHE or BSup state to an NEHE state were associated with good outcome (45% and 20%, respectively). No individuals with ELE state lasting >15 hours had good recovery.Transition to high entropy states is associated with an increased likelihood of good outcome despite preceding epileptiform or burst suppression states. High entropy may reflect mechanisms of resilience to hypoxic-ischemic brain injury.

  View details for DOI 10.1212/WNL.0000000000207537

  View details for Web of Science ID 001062101800014

  View details for PubMedID 37414565

  View details for PubMedCentralID PMC10501085

• How Many Patients Do You Need? Investigating Trial Designs for Anti-Seizure Treatment in Acute Brain Injury Patients. medRxiv : the preprint server for health sciences Parikh, H., Sun, H., Amerineni, R., Rosenthal, E. S., Volfovsky, A., Rudin, C., Westover, M. B., Zafar, S. F. 2023

  Abstract

  Epileptiform activity (EA) worsens outcomes in patients with acute brain injuries (e.g., aneurysmal subarachnoid hemorrhage [aSAH]). Randomized trials (RCTs) assessing anti-seizure interventions are needed. Due to scant drug efficacy data and ethical reservations with placebo utilization, RCTs are lacking or hindered by design constraints. We used a pharmacological model-guided simulator to design and determine feasibility of RCTs evaluating EA treatment.In a single-center cohort of adults (age >18) with aSAH and EA, we employed a mechanistic pharmacokinetic-pharmacodynamic framework to model treatment response using observational data. We subsequently simulated RCTs for levetiracetam and propofol, each with three treatment arms mirroring clinical practice and an additional placebo arm. Using our framework we simulated EA trajectories across treatment arms. We predicted discharge modified Rankin Scale as a function of baseline covariates, EA burden, and drug doses using a double machine learning model learned from observational data. Differences in outcomes across arms were used to estimate the required sample size.Sample sizes ranged from 500 for levetiracetam 7 mg/kg vs placebo, to >4000 for levetiracetam 15 vs. 7 mg/kg to achieve 80% power (5% type I error). For propofol 1mg/kg/hr vs. placebo 1200 participants were needed. Simulations comparing propofol at varying doses did not reach 80% power even at samples >1200.Our simulations using drug efficacy show sample sizes are infeasible, even for potentially unethical placebo-control trials. We highlight the strength of simulations with observational data to inform the null hypotheses and assess feasibility of future trials of EA treatment.

  View details for DOI 10.1101/2023.08.21.23294339

  View details for PubMedID 37662339

  View details for PubMedCentralID PMC10473786

• A Novel Home-Based Study of Circadian Rhythms: Design, Rationale, and Methods for the Circadia Study. Sleep Vlasac, I. M., Bormes, G. W., Do, E., Benkhoukha, S. S., Diallo, N., Fryou, N. L., Gioia, S., Akeju, O., Joseph, C., Kuan, A., Lapan, J., Oluwadara, D., Team, T. P., Rahman, S. A., Saxena, R., Scheer, F. A., Westover, M. B., Winkelman, J. W., Woodson, F., Lane, J. M. 2023

  Abstract

  The Circadia Study (Circadia) is a novel "direct-to-participant" research study investigating the genetics of circadian rhythm disorders of advanced and delayed sleep phase and non-24 hour rhythms. The goals of the Circadia Study are twofold: (i) to create an easy-to-use toolkit for at-home circadian phase assessment for patients with circadian rhythm disorders through the use of novel in-home based surveys, tests, and collection kits; and (ii) create a richly phenotyped patient resource for genetic studies that will lead to new genetic loci associated with circadian rhythm disorders revealing possible loci of interest to target in the development of therapeutics for circadian rhythm disorders. Through these goals, we aim to broaden our understanding and elucidate the genetics of circadian rhythm disorders across a diverse patient population while increasing accessibility to circadian rhythm disorder diagnostics reducing health disparities through self-directed at-home dim light melatonin onset (DLMO) collections.

  View details for DOI 10.1093/sleep/zsad197

  View details for PubMedID 37555446

• Associations between early in-hospital medications and the development of delirium in patients with stroke JOURNAL OF STROKE & CEREBROVASCULAR DISEASES Ryan, S. L., Liu, X., McKenna, V., Ghanta, M., Muniz, C., Renwick, R., Westover, B., Kimchi, E. Y. 2023; 32 (9): 107249

  Abstract

  Patients hospitalized with stroke develop delirium at higher rates than general hospitalized patients. While several medications are associated with existing delirium, it is unknown whether early medication exposures are associated with subsequent delirium in patients with stroke. Additionally, it is unknown whether delirium identification is associated with changes in the prescription of these medications.We conducted a retrospective cohort study of patients admitted to a comprehensive stroke center, who were assessed for delirium by trained nursing staff during clinical care. We analyzed exposures to multiple medication classes in the first 48 h of admission, and compared them between patients who developed delirium >48 hours after admission and those who never developed delirium. Statistical analysis was performed using univariate testing. Multivariable logistic regression was used further to evaluate the significance of univariately significant medications, while controlling for clinical confounders.1671 unique patients were included in the cohort, of whom 464 (27.8%) developed delirium >48 hours after admission. Delirium was associated with prior exposure to antipsychotics, sedatives, opiates, and antimicrobials. Antipsychotics, sedatives, and antimicrobials remained significantly associated with delirium even after accounting for several clinical covariates. Usage of these medications decreased in the 48 hours following delirium identification, except for atypical antipsychotics, whose use increased. Other medication classes such as steroids, benzodiazepines, and sleep aids were not initially associated with subsequent delirium, but prescription patterns still changed after delirium identification.Early exposure to multiple medication classes is associated with the subsequent development of delirium in patients with stroke. Additionally, prescription patterns changed following delirium identification, suggesting that some of the associated medication classes may represent modifiable targets for future delirium prevention strategies, although future study is needed.

  View details for DOI 10.1016/j.jstrokecerebrovasdis.2023.107249

  View details for Web of Science ID 001052412200001

  View details for PubMedID 37536017

  View details for PubMedCentralID PMC10529367

• Cognitive concerns are a risk factor for mortality in people with HIV and coronavirus disease 2019. AIDS (London, England) Wilcox, D. R., Rudmann, E. A., Ye, E., Noori, A., Magdamo, C., Jain, A., Alabsi, H., Foy, B., Triant, V. A., Robbins, G. K., Westover, M. B., Das, S., Mukerji, S. S. 2023; 37 (10): 1565-1571

  Abstract

  Data supporting dementia as a risk factor for coronavirus disease 2019 (COVID-19) mortality relied on ICD-10 codes, yet nearly 40% of individuals with probable dementia lack a formal diagnosis. Dementia coding is not well established for people with HIV (PWH), and its reliance may affect risk assessment.This retrospective cohort analysis of PWH with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) PCR positivity includes comparisons to people without HIV (PWoH), matched by age, sex, race, and zipcode. Primary exposures were dementia diagnosis, by International Classification of Diseases (ICD)-10 codes, and cognitive concerns, defined as possible cognitive impairment up to 12 months before COVID-19 diagnosis after clinical review of notes from the electronic health record. Logistic regression models assessed the effect of dementia and cognitive concerns on odds of death [odds ratio (OR); 95% CI (95% confidence interval)]; models adjusted for VACS Index 2.0.Sixty-four PWH were identified out of 14 129 patients with SARS-CoV-2 infection and matched to 463 PWoH. Compared with PWoH, PWH had a higher prevalence of dementia (15.6% vs. 6%, P  = 0.01) and cognitive concerns (21.9% vs. 15.8%, P  = 0.04). Death was more frequent in PWH ( P  < 0.01). Adjusted for VACS Index 2.0, dementia [2.4 (1.0-5.8), P  = 0.05] and cognitive concerns [2.4 (1.1-5.3), P  = 0.03] were associated with increased odds of death. In PWH, the association between cognitive concern and death trended towards statistical significance [3.92 (0.81-20.19), P  = 0.09]; there was no association with dementia.Cognitive status assessments are important for care in COVID-19, especially among PWH. Larger studies should validate findings and determine long-term COVID-19 consequences in PWH with preexisting cognitive deficits.

  View details for DOI 10.1097/QAD.0000000000003595

  View details for PubMedID 37195278

  View details for PubMedCentralID PMC10355333

• Effects of epileptiform activity on discharge outcome in critically ill patients in the USA: a retrospective cross-sectional study. The Lancet. Digital health Parikh, H., Hoffman, K., Sun, H., Zafar, S. F., Ge, W., Jing, J., Liu, L., Sun, J., Struck, A., Volfovsky, A., Rudin, C., Westover, M. B. 2023; 5 (8): e495-e502

  Abstract

  Epileptiform activity is associated with worse patient outcomes, including increased risk of disability and death. However, the effect of epileptiform activity on neurological outcome is confounded by the feedback between treatment with antiseizure medications and epileptiform activity burden. We aimed to quantify the heterogeneous effects of epileptiform activity with an interpretability-centred approach.We did a retrospective, cross-sectional study of patients in the intensive care unit who were admitted to Massachusetts General Hospital (Boston, MA, USA). Participants were aged 18 years or older and had electrographic epileptiform activity identified by a clinical neurophysiologist or epileptologist. The outcome was the dichotomised modified Rankin Scale (mRS) at discharge and the exposure was epileptiform activity burden defined as mean or maximum proportion of time spent with epileptiform activity in 6 h windows in the first 24 h of electroencephalography. We estimated the change in discharge mRS if everyone in the dataset had experienced a specific epileptiform activity burden and were untreated. We combined pharmacological modelling with an interpretable matching method to account for confounding and epileptiform activity-antiseizure medication feedback. The quality of the matched groups was validated by the neurologists.Between Dec 1, 2011, and Oct 14, 2017, 1514 patients were admitted to Massachusetts General Hospital intensive care unit, 995 (66%) of whom were included in the analysis. Compared with patients with a maximum epileptiform activity of 0 to less than 25%, patients with a maximum epileptiform activity burden of 75% or more when untreated had a mean 22·27% (SD 0·92) increased chance of a poor outcome (severe disability or death). Moderate but long-lasting epileptiform activity (mean epileptiform activity burden 2% to <10%) increased the risk of a poor outcome by mean 13·52% (SD 1·93). The effect sizes were heterogeneous depending on preadmission profile-eg, patients with hypoxic-ischaemic encephalopathy or acquired brain injury were more adversely affected compared with patients without these conditions.Our results suggest that interventions should put a higher priority on patients with an average epileptiform activity burden 10% or greater, and treatment should be more conservative when maximum epileptiform activity burden is low. Treatment should also be tailored to individual preadmission profiles because the potential for epileptiform activity to cause harm depends on age, medical history, and reason for admission.National Institutes of Health and National Science Foundation.

  View details for DOI 10.1016/S2589-7500(23)00088-2

  View details for PubMedID 37295971

  View details for PubMedCentralID PMC10528143

• Systematic Evaluation of Research Priorities in Critical Care Electroencephalography. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Sheikh, Z., Selioutski, O., Taraschenko, O., Gilmore, E. J., Westover, M. B., Cohen, A. B. 2023; 40 (5): 426-433

  Abstract

  The Critical Care EEG Monitoring Research Consortium (CCEMRC) is an international research group focusing on critical care EEG and epilepsy. As CCEMRC grew to include 50+ institutions over the past decade, members met to establish research priorities.The authors used an analytical hierarchy process-based research prioritization method, adapted from an approach previously applied to a Department of Defense health-related research program. Forty-six CCEMRC members identified and scored a set of eight clinical problems (CPs) and 15 research topic areas (RTAs) at an annual CCEMRC meeting. Members scored CPs on three criteria using a five-point ordinal scale: Incidence, Impact, and Gap Size; and RTAs on four additional criteria: Niche, Feasibility, Scientific Importance, and Medical Importance, each of which was assigned a weight. The first three RTA criteria were scored using a five-point scale, and CPs were mapped to RTAs using a four-point scale. The Medical Importance score was a weighted average of its mapping scores and the CP score. Finally, a Priority score was calculated for each RTA as a product of the four RTA criteria scores.The CPs with the highest scores were "Altered mental status" and "Long-term neurologic disability after hospital discharge." The RTAs with the highest priority scores were "Development of risk prediction tools," "Multicenter observational studies," and "Outcome prediction."Research prioritization helped CCEMRC evaluate its current research trajectory, identify high-priority near-term research pursuits, and create a roadmap for future research plans aligned with its mission. This approach may be helpful to other academic consortia and research programs.

  View details for DOI 10.1097/WNP.0000000000000916

  View details for PubMedID 35066530

  View details for PubMedCentralID PMC9296700

• Association of Early Seizure Prophylaxis With Posttraumatic Seizures and Mortality: A Meta-analysis With Evidence Quality Assessment NEUROLOGY-CLINICAL PRACTICE Coelho, L., Blacker, D., Hsu, J., Newhouse, J. P., Westover, M., Zafar, S. F., Moura, L. R. 2023; 13 (3): e200145

  Abstract

  To evaluate the quality of evidence about the association of primary seizure prophylaxis with antiseizure medication (ASM) within 7 days postinjury and the 18- or 24-month epilepsy/late seizure risk or all-cause mortality in adults with new-onset traumatic brain injury (TBI), in addition to early seizure risk.Twenty-three studies met the inclusion criteria (7 randomized and 16 nonrandomized studies). We analyzed 9,202 patients, including 4,390 in the exposed group and 4,812 in the unexposed group (894 in placebo and 3,918 in no ASM groups). There was a moderate to serious bias risk based on our assessment. Within the limitations of existing studies, our data revealed a lower risk for early seizures in the ASM prophylaxis group compared with placebo or no ASM prophylaxis (risk ratio [RR] 0.43, 95% confidence interval [CI] 0.33-0.57, p < 0.00001, I 2 = 3%). We identified high-quality evidence in favor of acute, short-term primary ASM use to prevent early seizures. Early ASM prophylaxis was not associated with a substantial difference in the 18- or 24-month risk of epilepsy/late seizures (RR 1.01, 95% CI 0.61-1.68, p = 0.96, I 2 = 63%) or mortality (RR 1.16, 95% CI 0.89-1.51, p = 0.26, I 2 = 0%). There was no evidence of strong publication bias for each main outcome. The overall quality of evidence was low and moderate for post-TBI epilepsy risk and all-cause mortality, respectively.Our data suggest that the evidence showing no association between early ASM use and 18- or 24-month epilepsy risk in adults with new-onset TBI was of low quality. The analysis indicated a moderate quality for the evidence showing no effect on all-cause mortality. Therefore, higher-quality evidence is needed as a supplement for stronger recommendations.

  View details for DOI 10.1212/CPJ.0000000000200145

  View details for Web of Science ID 001163614300008

  View details for PubMedID 37066107

  View details for PubMedCentralID PMC10101717

• Preoperative Plasma Tau-PT217 and Tau-PT181 Are Associated With Postoperative Delirium. Annals of surgery Liang, F., Baldyga, K., Quan, Q., Khatri, A., Choi, S., Wiener-Kronish, J., Akeju, O., Westover, M. B., Cody, K., Shen, Y., Marcantonio, E. R., Xie, Z. 2023; 277 (6): e1232-e1238

  Abstract

  This study aims to identify blood biomarkers of postoperative delirium.Phosphorylated tau at threonine 217 (Tau-PT217) and 181 (Tau-PT181) are new Alzheimer disease biomarkers. Postoperative delirium is associated with Alzheimer disease. We assessed associations between Tau-PT217 or Tau-PT181 and postoperative delirium.Of 491 patients (65 years old or older) who had a knee replacement, hip replacement, or laminectomy, 139 participants were eligible and included in the analysis. Presence and severity of postoperative delirium were assessed in the patients. Preoperative plasma concentrations of Tau-PT217 and Tau-PT181 were determined by a newly established Nanoneedle technology.Of 139 participants (73±6 years old, 55% female), 18 (13%) developed postoperative delirium. Participants who developed postoperative delirium had higher preoperative plasma concentrations of Tau-PT217 and Tau-PT181 than participants who did not. Preoperative plasma concentrations of Tau-PT217 or Tau-PT181 were independently associated with postoperative delirium after adjusting for age, education, and preoperative Mini-Mental State score [odds ratio (OR) per unit change in the biomarker: 2.05, 95% confidence interval (CI):1.61-2.62, P <0.001 for Tau-PT217; and OR: 4.12; 95% CI: 2.55--6.67, P <0.001 for Tau-PT181]. The areas under the receiver operating curve for predicting delirium were 0.969 (Tau-PT217) and 0.885 (Tau-PT181). The preoperative plasma concentrations of Tau-PT217 or Tau-PT181 were also associated with delirium severity [beta coefficient (β) per unit change in the biomarker: 0.14; 95% CI: 0.09-0.19, P <0.001 for Tau-PT217; and β: 0.41; 95% CI: 0.12-0.70, P =0.006 for Tau-PT181).Preoperative plasma concentrations of Tau-PT217 and Tau-PT181 were associated with postoperative delirium, with Tau-PT217 being a stronger indicator of postoperative delirium than Tau-PT181.

  View details for DOI 10.1097/SLA.0000000000005487

  View details for PubMedID 35794069

  View details for PubMedCentralID PMC9875943

• Intraoperative electroencephalographic marker of preoperative frailty: A prospective cohort study. Journal of clinical anesthesia Boncompte, G., Sun, H., Elgueta, M. F., Benavides, J., Carrasco, M., Morales, M. I., Calderón, N., Contreras, V., Westover, M. B., Cortínez, L. I., Akeju, O., Pedemonte, J. C. 2023; 86: 111069

  View details for DOI 10.1016/j.jclinane.2023.111069

  View details for PubMedID 36738630

  View details for PubMedCentralID PMC10074446

• Estimating the number of cases of dementia that might be prevented by preventing delirium. British journal of anaesthesia Rathmell, C. S., Akeju, O., Inouye, S. K., Westover, M. B. 2023; 130 (6): e477-e478

  View details for DOI 10.1016/j.bja.2023.03.001

  View details for PubMedID 37031027

  View details for PubMedCentralID PMC10329187

• Association of Epileptiform Activity With Outcomes in Toxic-Metabolic Encephalopathy. Critical care explorations Chen, P. M., Stekhoven, S. S., Haider, A., Jing, J., Ge, W., Rosenthal, E. S., Westover, M. B., Zafar, S. F. 2023; 5 (5): e0913

  Abstract

  The clinical significance of epileptiform abnormalities (EAs) specific to toxic-metabolic encephalopathy (TME) is unknown.To quantify EA burden in patients with TME and its association with neurologic outcomes.This is a retrospective study. A cohort of patients with TME and EA (positive) were age, Sequential Organ Failure Assessment Score, Acute Physiology and Chronic Health Evaluation II (APACHE-II) score matched to a cohort of TME patients without EA (control). Univariate analysis compared EA-positive patients against controls. Multivariable logistical regression adjusting for underlying disease etiology was performed to examine the relationship between EA burden and probability of poor neurologic outcome (modified Rankin Score [mRS] 4-6) at discharge. Consecutive admissions to inpatient floors or ICUs that underwent continuous electroencephalography (cEEG) monitoring at a single center between 2012 and 2019. Inclusion criteria were 1) patients with TME diagnosis, 2) age greater than 18 years, and 3) greater than or equal to 16 hours of cEEG. Patients with acute brain injury and cardiac arrest were excluded.Poor neurologic outcome defined by mRS (mRS 4-6).One hundred sixteen patients were included, 58 with EA and 58 controls without EA, where matching was performed on age and APACHE-II score. The median age was 66 (Q1-Q3, 57-75) and median APACHE II score was 18 (Q1-Q3, 13-22). Overall cohort discharge mortality was 22% and 70% had a poor neurologic outcome. Peak EA burden was defined as the 12-hour window of recording with the highest prevalence of EAs. In multivariable analysis adjusted for Charlson Comorbidity Index and primary diagnosis, presence of EAs was associated with poor outcome (odds ratio 3.89; CI [1.05-14.2], p = 0.041). Increase in peak EA burden from 0% to 100% increased probability of poor discharge neurologic outcome by 30%.Increasing burden of EA is associated with worse discharge outcomes in patients with TME. Future studies are needed to determine whether short-term treatment with anti-seizure medications while medically treating the underlying metabolic derangement improves outcomes.

  View details for DOI 10.1097/CCE.0000000000000913

  View details for PubMedID 37168691

  View details for PubMedCentralID PMC10166342

• Rapid Eye Movement Sleep, Neurodegeneration, and Amyloid Deposition in Aging. Annals of neurology André, C., Champetier, P., Rehel, S., Kuhn, E., Touron, E., Ourry, V., Landeau, B., Le Du, G., Mézenge, F., Segobin, S., de la Sayette, V., Vivien, D., Chételat, G., Rauchs, G. 2023; 93 (5): 979-990

  Abstract

  Rapid eye movement (REM) sleep is markedly altered in Alzheimer's disease (AD), and its reduction in older populations is associated with AD risk. However, little is known about the underlying brain mechanisms. Our objective was to investigate the relationships between REM sleep integrity and amyloid deposition, gray matter volume, and perfusion in aging.We included 121 cognitively unimpaired older adults (76 women, mean age 68.96 ± 3.82 years), who underwent a polysomnography, T1-weighted magnetic resonance imaging, early and late Florbetapir positron emission tomography scans to evaluate gray matter volume, perfusion, and amyloid deposition. We computed indices reflecting REM sleep macro- and microstructural integrity (ie, normalized electroencephalographic spectral power values). Voxel-wise multiple regression analyses were conducted between REM sleep indices and neuroimaging data, controlling for age, sex, education, the apnea-hypopnea index, and the apolipoprotein E ε4 status.Lower perfusion in frontal, anterior and posterior cingulate, and precuneus areas was associated with decreased delta power and electroencephalographic slowing (slow/fast frequencies ratio), and increased alpha and beta power. To a lower extent, similar results were obtained between gray matter volume and delta, alpha, and beta power. In addition, lower REM sleep theta power was more marginally associated with greater diffuse amyloid deposition and lower gray matter volume in fronto-temporal and parieto-occipital areas.These results suggest that alterations of REM sleep microstructure are associated with greater neurodegeneration and neocortical amyloid deposition in older adults. Further studies are warranted to replicate these findings, and determine whether older adults exhibiting REM sleep alterations are more at risk of cognitive decline and belonging to the Alzheimer's continuum. ANN NEUROL 2023;93:979-990.

  View details for DOI 10.1002/ana.26604

  View details for PubMedID 36641644

• Development of Expert-Level Classification of Seizures and Rhythmic and Periodic Patterns During EEG Interpretation NEUROLOGY Jing, J., Ge, W., Hong, S., Fernandes, M., Lin, Z., Yang, C., An, S., Struck, A. F., Herlopian, A., Karakis, I., Halford, J. J., Ng, M. C., Johnson, E. L., Appavu, B. L., Sarkis, R. A., Osman, G., Kaplan, P. W., Dhakar, M. B., Jayagopal, L., Sheikh, Z., Taraschenko, O., Schmitt, S., Haider, H. A., Kim, J. A., Swisher, C. B., Gaspard, N., Cervenka, M. C., Rodriguez Ruiz, A. A., Lee, J., Tabaeizadeh, M., Gilmore, E. J., Nordstrom, K., Yoo, J., Holmes, M. G., Herman, S. T., Williams, J. A., Pathmanathan, J., Nascimento, F. A., Fan, Z., Nasiri, S., Shafi, M. M., Cash, S. S., Hoch, D. B., Cole, A. J., Rosenthal, E. S., Zafar, S. F., Sun, J., Westover, M. 2023; 100 (17): E1750-E1762

  Abstract

  Seizures (SZs) and other SZ-like patterns of brain activity can harm the brain and contribute to in-hospital death, particularly when prolonged. However, experts qualified to interpret EEG data are scarce. Prior attempts to automate this task have been limited by small or inadequately labeled samples and have not convincingly demonstrated generalizable expert-level performance. There exists a critical unmet need for an automated method to classify SZs and other SZ-like events with expert-level reliability. This study was conducted to develop and validate a computer algorithm that matches the reliability and accuracy of experts in identifying SZs and SZ-like events, known as "ictal-interictal-injury continuum" (IIIC) patterns on EEG, including SZs, lateralized and generalized periodic discharges (LPD, GPD), and lateralized and generalized rhythmic delta activity (LRDA, GRDA), and in differentiating these patterns from non-IIIC patterns.We used 6,095 scalp EEGs from 2,711 patients with and without IIIC events to train a deep neural network, SPaRCNet, to perform IIIC event classification. Independent training and test data sets were generated from 50,697 EEG segments, independently annotated by 20 fellowship-trained neurophysiologists. We assessed whether SPaRCNet performs at or above the sensitivity, specificity, precision, and calibration of fellowship-trained neurophysiologists for identifying IIIC events. Statistical performance was assessed by the calibration index and by the percentage of experts whose operating points were below the model's receiver operating characteristic curves (ROCs) and precision recall curves (PRCs) for the 6 pattern classes.SPaRCNet matches or exceeds most experts in classifying IIIC events based on both calibration and discrimination metrics. For SZ, LPD, GPD, LRDA, GRDA, and "other" classes, SPaRCNet exceeds the following percentages of 20 experts-ROC: 45%, 20%, 50%, 75%, 55%, and 40%; PRC: 50%, 35%, 50%, 90%, 70%, and 45%; and calibration: 95%, 100%, 95%, 100%, 100%, and 80%, respectively.SPaRCNet is the first algorithm to match expert performance in detecting SZs and other SZ-like events in a representative sample of EEGs. With further development, SPaRCNet may thus be a valuable tool for an expedited review of EEGs.This study provides Class II evidence that among patients with epilepsy or critical illness undergoing EEG monitoring, SPaRCNet can differentiate (IIIC) patterns from non-IIIC events and expert neurophysiologists.

  View details for DOI 10.1212/WNL.0000000000207127

  View details for Web of Science ID 001019601700015

  View details for PubMedID 36878708

  View details for PubMedCentralID PMC10136013

• Prediction of operative mortality for patients undergoing cardiac surgical procedures without established risk scores. The Journal of thoracic and cardiovascular surgery Ong, C. S., Reinertsen, E., Sun, H., Moonsamy, P., Mohan, N., Funamoto, M., Kaneko, T., Shekar, P. S., Schena, S., Lawton, J. S., D'Alessandro, D. A., Westover, M. B., Aguirre, A. D., Sundt, T. M. 2023; 165 (4): 1449-1459.e15

  Abstract

  Current cardiac surgery risk models do not address a substantial fraction of procedures. We sought to create models to predict the risk of operative mortality for an expanded set of cases.Four supervised machine learning models were trained using preoperative variables present in the Society of Thoracic Surgeons (STS) data set of the Massachusetts General Hospital to predict and classify operative mortality in procedures without STS risk scores. A total of 424 (5.5%) mortality events occurred out of 7745 cases. Models included logistic regression with elastic net regularization (LogReg), support vector machine, random forest (RF), and extreme gradient boosted trees (XGBoost). Model discrimination was assessed via area under the receiver operating characteristic curve (AUC), and calibration was assessed via calibration slope and expected-to-observed event ratio. External validation was performed using STS data sets from Brigham and Women's Hospital (BWH) and the Johns Hopkins Hospital (JHH).Models performed comparably with the highest mean AUC of 0.83 (RF) and expected-to-observed event ratio of 1.00. On external validation, the AUC was 0.81 in BWH (RF) and 0.79 in JHH (LogReg/RF). Models trained and applied on the same institution's data achieved AUCs of 0.81 (BWH: LogReg/RF/XGBoost) and 0.82 (JHH: LogReg/RF/XGBoost).Machine learning models trained on preoperative patient data can predict operative mortality at a high level of accuracy for cardiac surgical procedures without established risk scores. Such procedures comprise 23% of all cardiac surgical procedures nationwide. This work also highlights the value of using local institutional data to train new prediction models that account for institution-specific practices.

  View details for DOI 10.1016/j.jtcvs.2021.09.010

  View details for PubMedID 34607725

  View details for PubMedCentralID PMC8918430

• Passive and active markers of cortical excitability in epilepsy EPILEPSIA Ramantani, G., Westover, M., Gliske, S., Sarnthein, J., Sarma, S., Wang, Y., Baud, M. O., Stacey, W. C., Conrad, E. C. 2023; 64: S25-S36

  Abstract

  Electroencephalography (EEG) has been the primary diagnostic tool in clinical epilepsy for nearly a century. Its review is performed using qualitative clinical methods that have changed little over time. However, the intersection of higher resolution digital EEG and analytical tools developed in the past decade invites a re-exploration of relevant methodology. In addition to the established spatial and temporal markers of spikes and high-frequency oscillations, novel markers involving advanced postprocessing and active probing of the interictal EEG are gaining ground. This review provides an overview of the EEG-based passive and active markers of cortical excitability in epilepsy and of the techniques developed to facilitate their identification. Several different emerging tools are discussed in the context of specific EEG applications and the barriers we must overcome to translate these tools into clinical practice.

  View details for DOI 10.1111/epi.17578

  View details for Web of Science ID 000954320300001

  View details for PubMedID 36897228

  View details for PubMedCentralID PMC10512778

• Sample Size Analysis for Machine Learning Clinical Validation Studies. Biomedicines Goldenholz, D. M., Sun, H., Ganglberger, W., Westover, M. B. 2023; 11 (3)

  Abstract

  Before integrating new machine learning (ML) into clinical practice, algorithms must undergo validation. Validation studies require sample size estimates. Unlike hypothesis testing studies seeking a p-value, the goal of validating predictive models is obtaining estimates of model performance. There is no standard tool for determining sample size estimates for clinical validation studies for machine learning models.Our open-source method, Sample Size Analysis for Machine Learning (SSAML) was described and was tested in three previously published models: brain age to predict mortality (Cox Proportional Hazard), COVID hospitalization risk prediction (ordinal regression), and seizure risk forecasting (deep learning).Minimum sample sizes were obtained in each dataset using standardized criteria.SSAML provides a formal expectation of precision and accuracy at a desired confidence level. SSAML is open-source and agnostic to data type and ML model. It can be used for clinical validation studies of ML models.

  View details for DOI 10.3390/biomedicines11030685

  View details for PubMedID 36979665

  View details for PubMedCentralID PMC10045793

• Poorer sleep impairs brain health at midlife. Scientific reports Namsrai, T., Ambikairajah, A., Cherbuin, N. 2023; 13 (1): 1874

  Abstract

  Sleep is an emerging risk factor for dementia but its association with brain health remains unclear. This study included UK Biobank (n = 29,545; mean age = 54.65) participants at imaging visit with sleep measures and brain scans, and a subset (n = 14,206) with cognitive measures. Multiple linear regression analyses were conducted to study the associations between sleep and brain health. Every additional hour of sleep above 7 h/day was associated with 0.10-0.25% lower brain volumes. In contrast, a negative non-linear association was observed between sleep duration, grey matter, and hippocampal volume. Both longer (> 9 h/day) and shorter sleep (< 6 h/day) durations were associated with lower brain volumes and cognitive measures (memory, reaction time, fluid intelligence). Additionally, daytime dozing was associated with lower brain volumes (grey matter and left hippocampus volume) and lower cognitive measures (reaction time and fluid intelligence). Poor sleep (< 6 h/day, > 9 h/day, daytime dozing) at midlife was associated with lower brain health. Sleep may be an important target to improve brain health into old age and delay the onset of dementia.

  View details for DOI 10.1038/s41598-023-27913-9

  View details for PubMedID 36725955

  View details for PubMedCentralID PMC9892039

• Nighttime dexmedetomidine for delirium prevention in non-mechanically ventilated patients after cardiac surgery (MINDDS): A single-centre, parallel-arm, randomised, placebo-controlled superiority trial. EClinicalMedicine Qu, J. Z., Mueller, A., McKay, T. B., Westover, M. B., Shelton, K. T., Shaefi, S., D'Alessandro, D. A., Berra, L., Brown, E. N., Houle, T. T., Akeju, O. 2023; 56: 101796

  Abstract

  The delirium-sparing effect of nighttime dexmedetomidine has not been studied after surgery. We hypothesised that a nighttime dose of dexmedetomidine would reduce the incidence of postoperative delirium as compared to placebo.This single-centre, parallel-arm, randomised, placebo-controlled superiority trial evaluated whether a short nighttime dose of intravenous dexmedetomidine (1 μg/kg over 40 min) would reduce the incidence of postoperative delirium in patients 60 years of age or older undergoing elective cardiac surgery with cardiopulmonary bypass. Patients were randomised to receive dexmedetomidine or placebo in a 1:1 ratio. The primary outcome was delirium on postoperative day one. Secondary outcomes included delirium within three days of surgery, 30-, 90-, and 180-day abbreviated Montreal Cognitive Assessment scores, Patient Reported Outcome Measures Information System quality of life scores, and all-cause mortality. The study was registered as NCT02856594 on ClinicalTrials.gov on August 5, 2016, before the enrolment of any participants.Of 469 patients that underwent randomisation to placebo (n = 235) or dexmedetomidine (n = 234), 75 met a prespecified drop criterion before the study intervention. Thus, 394 participants (188 dexmedetomidine; 206 placebo) were analysed in the modified intention-to-treat cohort (median age 69 [IQR 64, 74] years; 73.1% male [n = 288]; 26·9% female [n = 106]). Postoperative delirium status on day one was missing for 30 (7.6%) patients. Among those in whom it could be assessed, the primary outcome occurred in 5 of 175 patients (2.9%) in the dexmedetomidine group and 16 of 189 patients (8.5%) in the placebo group (OR 0.32, 95% CI: 0.10-0.83; P = 0.029). A non-significant but higher proportion of participants experienced delirium within three days postoperatively in the placebo group (25/177; 14.1%) compared to the dexmedetomidine group (14/160; 8.8%; OR 0.58; 95% CI, 0.28-1.15). No significant differences between groups were observed in secondary outcomes or safety.Our findings suggested that in elderly cardiac surgery patients with a low baseline risk of postoperative delirium and extubated within 12 h of ICU admission, a short nighttime dose of dexmedetomidine decreased the incidence of delirium on postoperative day one. Although non-statistically significant, our findings also suggested a clinical meaningful difference in the three-day incidence of postoperative delirium.National Institute on Aging (R01AG053582).

  View details for DOI 10.1016/j.eclinm.2022.101796

  View details for PubMedID 36590787

  View details for PubMedCentralID PMC9800196

• The sleep and wake electroencephalogram over the lifespan. Neurobiology of aging Sun, H., Ye, E., Paixao, L., Ganglberger, W., Chu, C. J., Zhang, C., Rosand, J., Mignot, E., Cash, S. S., Gozal, D., Thomas, R. J., Westover, M. B. 2023; 124: 60-70

  Abstract

  Both sleep and wake encephalograms (EEG) change over the lifespan. While prior studies have characterized age-related changes in the EEG, the datasets span a particular age group, or focused on sleep and wake macrostructure rather than the microstructure. Here, we present sex-stratified data from 3372 community-based or clinic-based otherwise neurologically and psychiatrically healthy participants ranging from 11 days to 80 years of age. We estimate age norms for key sleep and wake EEG parameters including absolute and relative powers in delta, theta, alpha, and sigma bands, as well as sleep spindle density, amplitude, duration, and frequency. To illustrate the potential use of the reference measures developed herein, we compare them to sleep EEG recordings from age-matched participants with Alzheimer's disease, severe sleep apnea, depression, osteoarthritis, and osteoporosis. Although the partially clinical nature of the datasets may bias the findings towards less normal and hence may underestimate pathology in practice, age-based EEG reference values enable objective screening of deviations from healthy aging among individuals with a variety of disorders that affect brain health.

  View details for DOI 10.1016/j.neurobiolaging.2023.01.006

  View details for PubMedID 36739622

• Self-Supervised Electroencephalogram Representation Learning for Automatic Sleep Staging: Model Development and Evaluation Study JMIR AI Yang, C., Xiao, C., Westover, B., Sun, J. 2023; 2: e46769

  Abstract

  Deep learning models have shown great success in automating tasks in sleep medicine by learning from carefully annotated electroencephalogram (EEG) data. However, effectively using a large amount of raw EEG data remains a challenge.In this study, we aim to learn robust vector representations from massive unlabeled EEG signals, such that the learned vectorized features (1) are expressive enough to replace the raw signals in the sleep staging task, and (2) provide better predictive performance than supervised models in scenarios involving fewer labels and noisy samples.We propose a self-supervised model, Contrast with the World Representation (ContraWR), for EEG signal representation learning. Unlike previous models that use a set of negative samples, our model uses global statistics (ie, the average representation) from the data set to distinguish signals associated with different sleep stages. The ContraWR model is evaluated on 3 real-world EEG data sets that include both settings: at-home and in-laboratory EEG recording.ContraWR outperforms 4 recently reported self-supervised learning methods on the sleep staging task across 3 large EEG data sets. ContraWR also supersedes supervised learning when fewer training labels are available (eg, 4% accuracy improvement when less than 2% of data are labeled on the Sleep EDF data set). Moreover, the model provides informative, representative feature structures in 2D projection.We show that ContraWR is robust to noise and can provide high-quality EEG representations for downstream prediction tasks. The proposed model can be generalized to other unsupervised physiological signal learning tasks. Future directions include exploring task-specific data augmentations and combining self-supervised methods with supervised methods, building upon the initial success of self-supervised learning reported in this study.

  View details for DOI 10.2196/46769

  View details for Web of Science ID 001376592500037

  View details for PubMedID 38090533

  View details for PubMedCentralID PMC10715804

• Using Novel Data Visualization Methods to Understand Mobile Health Usability: Exemplar From a Technology-Enabled Sleep Self-monitoring Intervention. Computers, informatics, nursing : CIN Marquard, J. L., Howard, J., LeBlanc, R. 2023; 41 (1): 1-5

  View details for DOI 10.1097/CIN.0000000000000970

  View details for PubMedID 36634231

  View details for PubMedCentralID PMC9851666

• A large language model for electronic health records. NPJ digital medicine Yang, X., Chen, A., PourNejatian, N., Shin, H. C., Smith, K. E., Parisien, C., Compas, C., Martin, C., Costa, A. B., Flores, M. G., Zhang, Y., Magoc, T., Harle, C. A., Lipori, G., Mitchell, D. A., Hogan, W. R., Shenkman, E. A., Bian, J., Wu, Y. 2022; 5 (1): 194

  Abstract

  There is an increasing interest in developing artificial intelligence (AI) systems to process and interpret electronic health records (EHRs). Natural language processing (NLP) powered by pretrained language models is the key technology for medical AI systems utilizing clinical narratives. However, there are few clinical language models, the largest of which trained in the clinical domain is comparatively small at 110 million parameters (compared with billions of parameters in the general domain). It is not clear how large clinical language models with billions of parameters can help medical AI systems utilize unstructured EHRs. In this study, we develop from scratch a large clinical language model-GatorTron-using >90 billion words of text (including >82 billion words of de-identified clinical text) and systematically evaluate it on five clinical NLP tasks including clinical concept extraction, medical relation extraction, semantic textual similarity, natural language inference (NLI), and medical question answering (MQA). We examine how (1) scaling up the number of parameters and (2) scaling up the size of the training data could benefit these NLP tasks. GatorTron models scale up the clinical language model from 110 million to 8.9 billion parameters and improve five clinical NLP tasks (e.g., 9.6% and 9.5% improvement in accuracy for NLI and MQA), which can be applied to medical AI systems to improve healthcare delivery. The GatorTron models are publicly available at: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/models/gatortron_og .

  View details for DOI 10.1038/s41746-022-00742-2

  View details for PubMedID 36572766

  View details for PubMedCentralID PMC9792464

• Flexible realistic simulation of seizure occurrence recapitulating statistical properties of seizure diaries EPILEPSIA Goldenholz, D. M., Westover, M. 2023; 64 (2): 396-405

  Abstract

  A realistic seizure diary simulator is currently unavailable for many research needs, including clinical trial analysis and evaluation of seizure detection and seizure-forecasting tools. In recent years, important statistical features of seizure diaries have been characterized. These include (1) heterogeneity of individual seizure frequencies, (2) the relation between average seizure rate and standard deviation, (3) multiple risk cycles, (4) seizure clusters, and (5) limitations on inter-seizure intervals. The present study unifies these features into a single model.Our approach, Cyclic Heterogeneous Overdispersed Clustered Open-source L-relationship Adjustable Temporally limited E-diary Simulator (CHOCOLATES) is based on a hierarchical model centered on a gamma Poisson generator with several modifiers. This model accounts for the aforementioned statistical properties. The model was validated by simulating 10 000 randomized clinical trials (RCTs) of medication to compare with 23 historical RCTs. Metrics of 50% responder rate (RR50) and median percent change (MPC) were evaluated. We also used CHOCOLATES as input to a seizure-forecasting tool to test the flexibility of the model. We examined the area under the receiver-operating characteristic (ROC) curve (AUC) for test data with and without cycles and clusters.The model recapitulated typical findings in 23 historical RCTs without the necessity of introducing an additional "placebo effect." The model produced the following RR50 values: placebo: 17 ± 4%; drug 38 ± 5%; and the following MPC values: placebo: 13 ± 6%; drug 40 ± 4%. These values are similar to historical data: for RR50: placebo, 21 ± 10%, drug: 43 ± 13%; and for MPC: placebo: 17 ± 10%, drug: 41 ± 11%. The seizure forecasts achieved an AUC of 0.68 with cycles and clusters, whereas without them the AUC was 0.51.CHOCOLATES represents the most realistic seizure occurrence simulator to date, based on observations from thousands of patients in different contexts. This tool is open source and flexible, and can be used for many applications, including clinical trial simulation and testing of seizure-forecasting tools.

  View details for DOI 10.1111/epi.17471

  View details for Web of Science ID 000896582100001

  View details for PubMedID 36401798

  View details for PubMedCentralID PMC9905290

• Impact of the COVID-19 Pandemic on Continuous EEG Utilization. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Zafar, S. F., Khozein, R. J., LaRoche, S. M., Westover, M. B., Gilmore, E. J. 2022; 39 (7): 567-574

  Abstract

  The coronavirus disease 2019 (COVID-19) has significantly impacted healthcare delivery and utilization. The aim of this article was to assess the impact of the COVID-19 pandemic on in-hospital continuous electroencephalography (cEEG) utilization and identify areas for process improvement.A 38-question web-based survey was distributed to site principal investigators of the Critical Care EEG Monitoring Research Consortium, and institutional contacts for the Neurodiagnostic Credentialing and Accreditation Board. The survey addressed the following aspects of cEEG utilization: (1) general center characteristics, (2) cEEG utilization and review, (3) staffing and workflow, and (4) health impact on EEG technologists.The survey was open from June 12, 2020 to June 30, 2020 and distributed to 174 centers with 79 responses (45.4%). Forty centers were located in COVID-19 hotspots. Fifty-seven centers (72.1%) reported cEEG volume reduction. Centers in the Northeast were most likely to report cEEG volume reduction (odds ratio [OR] 7.19 [1.53-33.83]; P = 0.012). Additionally, centers reporting decrease in outside hospital transfers reported cEEG volume reduction; OR 21.67 [4.57-102.81]; P ≤ 0.0001. Twenty-six centers (32.91%) reported reduction in EEG technologist coverage. Eighteen centers had personal protective equipment shortages for EEG technologists. Technologists at these centers were more likely to quarantine for suspected or confirmed COVID-19; OR 3.14 [1.01-9.63]; P = 0.058.There has been a widespread reduction in cEEG volume during the pandemic. Given the anticipated duration of the pandemic and the importance of cEEG in managing hospitalized patients, methods to optimize use need to be prioritized to provide optimal care. Because the survey provides a cross-sectional assessment, follow-up studies can determine the long-term impact of the pandemic on cEEG utilization.

  View details for DOI 10.1097/WNP.0000000000000802

  View details for PubMedID 33394823

  View details for PubMedCentralID PMC8217411

• Competency-based EEG education: a list of "must-know" EEG findings for adult and child neurology residents. Epileptic disorders : international epilepsy journal with videotape Nascimento, F. A., Jing, J., Strowd, R., Sheikh, I. S., Weber, D., Gavvala, J. R., Maheshwari, A., Tanner, A., Ng, M., Vinayan, K. P., Sinha, S. R., Yacubian, E. M., Rao, V. R., Perry, M. S., Fountain, N. B., Karakis, I., Wirrell, E., Yuan, F., Friedman, D., Tankisi, H., Rampp, S., Fasano, R., Wilmshurst, J. M., O'Donovan, C., Schomer, D., Kaplan, P. W., Sperling, M. R., Benbadis, S., Westover, M. B., Beniczky, S. 2022; 24 (5): 979-982

  View details for DOI 10.1684/epd.2022.1476

  View details for PubMedID 35904042

  View details for PubMedCentralID PMC9812628

• Reply to "Continuous EEG in patients with extracorporeal membrane oxygenation support: Clinical need in multidisciplinary collaboration and standardized monitoring". Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Amorim, E., Westover, M. B. 2022; 142: 275-276

  View details for DOI 10.1016/j.clinph.2022.07.488

  View details for PubMedID 35933303

• EEG reading with or without clinical information - a real-world practice study. Neurophysiologie clinique = Clinical neurophysiology Nascimento, F. A., Jing, J., Beniczky, S., Olandoski, M., Benbadis, S. R., Cole, A. J., Westover, M. B. 2022; 52 (5): 394-397

  Abstract

  We sought to investigate electroencephalographers' real-world behaviors and opinions concerning reading routine EEG (rEEG) with or without clinical information. An eight-question, anonymous, online survey targeted at electroencephalographers was disseminated on social media from the authors' personal accounts and emailed to authors' select colleagues. A total of 389 responses were included. Most respondents reported examining clinical information before describing rEEG findings. Nonetheless, only a minority of respondents believe that EEG analysis/description should be influenced by clinical information. We recommend reviewing clinical data only after an unbiased EEG read to prevent history bias and ensure generation of reliable electrodiagnostic information.

  View details for DOI 10.1016/j.neucli.2022.08.002

  View details for PubMedID 36127207

  View details for PubMedCentralID PMC9815944

• Journal Club: Criteria for Defining Interictal Epileptiform Discharges in EEG NEUROLOGY McLaren, J. R., Jing, J., Westover, M., Nascimento, F. A. 2022; 99 (10): 430-432

  View details for DOI 10.1212/WNL.0000000000200991

  View details for Web of Science ID 000852247600007

  View details for PubMedID 35853743

  View details for PubMedCentralID PMC9519249

• High prevalence of sleep-disordered breathing in the intensive care unit - a cross-sectional study SLEEP AND BREATHING Bucklin, A. A., Ganglberger, W., Quadri, S. A., Tesh, R. A., Adra, N., Da Silva Cardoso, M., Leone, M. J., Krishnamurthy, P., Hemmige, A., Rajan, S., Panneerselvam, E., Paixao, L., Higgins, J., Ayub, M., Shao, Y., Ye, E. M., Coughlin, B., Sun, H., Cash, S. S., Thompson, B., Akeju, O., Kuller, D., Thomas, R. J., Westover, M. 2023; 27 (3): 1013-1026

  Abstract

  Sleep-disordered breathing may be induced by, exacerbate, or complicate recovery from critical illness. Disordered breathing during sleep, which itself is often fragmented, can go unrecognized in the intensive care unit (ICU). The objective of this study was to investigate the prevalence, severity, and risk factors of sleep-disordered breathing in ICU patients using a single respiratory belt and oxygen saturation signals.Patients in three ICUs at Massachusetts General Hospital wore a thoracic respiratory effort belt as part of a clinical trial for up to 7 days and nights. Using a previously developed machine learning algorithm, we processed respiratory and oximetry signals to measure the 3% apnea-hypopnea index (AHI) and estimate AH-specific hypoxic burden and periodic breathing. We trained models to predict AHI categories for 12-h segments from risk factors, including admission variables and bio-signals data, available at the start of these segments.Of 129 patients, 68% had an AHI ≥ 5; 40% an AHI > 15, and 19% had an AHI > 30 while critically ill. Median [interquartile range] hypoxic burden was 2.8 [0.5, 9.8] at night and 4.2 [1.0, 13.7] %min/h during the day. Of patients with AHI ≥ 5, 26% had periodic breathing. Performance of predicting AHI-categories from risk factors was poor.Sleep-disordered breathing and sleep apnea events while in the ICU are common and are associated with substantial burden of hypoxia and periodic breathing. Detection is feasible using limited bio-signals, such as respiratory effort and SpO2 signals, while risk factors were insufficient to predict AHI severity.

  View details for DOI 10.1007/s11325-022-02698-9

  View details for Web of Science ID 000840628400001

  View details for PubMedID 35971023

  View details for PubMedCentralID PMC9931933

• Development and Validation of a Model to Identify Critical Brain Injuries Using Natural Language Processing of Text Computed Tomography Reports. JAMA network open Torres-Lopez, V. M., Rovenolt, G. E., Olcese, A. J., Garcia, G. E., Chacko, S. M., Robinson, A., Gaiser, E., Acosta, J., Herman, A. L., Kuohn, L. R., Leary, M., Soto, A. L., Zhang, Q., Fatima, S., Falcone, G. J., Payabvash, M. S., Sharma, R., Struck, A. F., Sheth, K. N., Westover, M. B., Kim, J. A. 2022; 5 (8): e2227109

  Abstract

  Clinical text reports from head computed tomography (CT) represent rich, incompletely utilized information regarding acute brain injuries and neurologic outcomes. CT reports are unstructured; thus, extracting information at scale requires automated natural language processing (NLP). However, designing new NLP algorithms for each individual injury category is an unwieldy proposition. An NLP tool that summarizes all injuries in head CT reports would facilitate exploration of large data sets for clinical significance of neuroradiological findings.To automatically extract acute brain pathological data and their features from head CT reports.This diagnostic study developed a 2-part named entity recognition (NER) NLP model to extract and summarize data on acute brain injuries from head CT reports. The model, termed BrainNERD, extracts and summarizes detailed brain injury information for research applications. Model development included building and comparing 2 NER models using a custom dictionary of terms, including lesion type, location, size, and age, then designing a rule-based decoder using NER outputs to evaluate for the presence or absence of injury subtypes. BrainNERD was evaluated against independent test data sets of manually classified reports, including 2 external validation sets. The model was trained on head CT reports from 1152 patients generated by neuroradiologists at the Yale Acute Brain Injury Biorepository. External validation was conducted using reports from 2 outside institutions. Analyses were conducted from May 2020 to December 2021.Performance of the BrainNERD model was evaluated using precision, recall, and F1 scores based on manually labeled independent test data sets.A total of 1152 patients (mean [SD] age, 67.6 [16.1] years; 586 [52%] men), were included in the training set. NER training using transformer architecture and bidirectional encoder representations from transformers was significantly faster than spaCy. For all metrics, the 10-fold cross-validation performance was 93% to 99%. The final test performance metrics for the NER test data set were 98.82% (95% CI, 98.37%-98.93%) for precision, 98.81% (95% CI, 98.46%-99.06%) for recall, and 98.81% (95% CI, 98.40%-98.94%) for the F score. The expert review comparison metrics were 99.06% (95% CI, 97.89%-99.13%) for precision, 98.10% (95% CI, 97.93%-98.77%) for recall, and 98.57% (95% CI, 97.78%-99.10%) for the F score. The decoder test set metrics were 96.06% (95% CI, 95.01%-97.16%) for precision, 96.42% (95% CI, 94.50%-97.87%) for recall, and 96.18% (95% CI, 95.151%-97.16%) for the F score. Performance in external institution report validation including 1053 head CR reports was greater than 96%.These findings suggest that the BrainNERD model accurately extracted acute brain injury terms and their properties from head CT text reports. This freely available new tool could advance clinical research by integrating information in easily gathered head CT reports to expand knowledge of acute brain injury radiographic phenotypes.

  View details for DOI 10.1001/jamanetworkopen.2022.27109

  View details for PubMedID 35972739

  View details for PubMedCentralID PMC9382443

• Age estimation from sleep studies using deep learning predicts life expectancy. NPJ digital medicine Brink-Kjaer, A., Leary, E. B., Sun, H., Westover, M. B., Stone, K. L., Peppard, P. E., Lane, N. E., Cawthon, P. M., Redline, S., Jennum, P., Sorensen, H. B., Mignot, E. 2022; 5 (1): 103

  Abstract

  Sleep disturbances increase with age and are predictors of mortality. Here, we present deep neural networks that estimate age and mortality risk through polysomnograms (PSGs). Aging was modeled using 2500 PSGs and tested in 10,699 PSGs from men and women in seven different cohorts aged between 20 and 90. Ages were estimated with a mean absolute error of 5.8±1.6years, while basic sleep scoring measures had an error of 14.9±6.29years. After controlling for demographics, sleep, and health covariates, each 10-year increment in age estimate error (AEE) was associated with increased all-cause mortality rate of 29% (95% confidence interval: 20-39%). An increase from -10 to +10years in AEE translates to an estimated decreased life expectancy of 8.7years (95% confidence interval: 6.1-11.4years). Greater AEE was mostly reflected in increased sleep fragmentation, suggesting this is an important biomarker of future health independent of sleep apnea.

  View details for DOI 10.1038/s41746-022-00630-9

  View details for PubMedID 35869169

• Automated Scoring of Respiratory Events in Sleep With a Single Effort Belt and Deep Neural Networks IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING Nassi, T. E., Ganglberger, W., Sun, H., Bucklin, A. A., Biswal, S., van Putten, M. M., Thomas, R. J., Westover, M. 2022; 69 (6): 2094-2104

  Abstract

  Automatic detection and analysis of respiratory events in sleep using a single respiratoryeffort belt and deep learning.Using 9,656 polysomnography recordings from the Massachusetts General Hospital (MGH), we trained a neural network (WaveNet) to detect obstructive apnea, central apnea, hypopnea and respiratory-effort related arousals. Performance evaluation included event-based analysis and apnea-hypopnea index (AHI) stratification. The model was further evaluated on a public dataset, the Sleep-Heart-Health-Study-1, containing 8,455 polysomnographic recordings.For binary apnea event detection in the MGH dataset, the neural network obtained a sensitivity of 68%, a specificity of 98%, a precision of 65%, a F1-score of 67%, and an area under the curve for the receiver operating characteristics curve and precision-recall curve of 0.93 and 0.71, respectively. AHI prediction resulted in a mean difference of 0.41 ± 7.8 and a r2 of 0.90. For the multiclass task, we obtained varying performances: 84% of all labeled central apneas were correctly classified, whereas this metric was 51% for obstructive apneas, 40% for respiratory effort related arousals and 23% for hypopneas.Our fully automated method can detect respiratory events and assess the AHI accurately. Differentiation of event types is more difficult and may reflect in part the complexity of human respiratory output and some degree of arbitrariness in the criteria used during manual annotation.The current gold standard of diagnosing sleep-disordered breathing, using polysomnography and manual analysis, is time-consuming, expensive, and only applicable in dedicated clinical environments. Automated analysis using a single effort belt signal overcomes these limitations.

  View details for DOI 10.1109/TBME.2021.3136753

  View details for Web of Science ID 000799622400031

  View details for PubMedID 34928786

  View details for PubMedCentralID PMC9119908

• Prolonged Unconsciousness is Common in COVID-19 and Associated with Hypoxemia. Annals of neurology Waldrop, G., Safavynia, S. A., Barra, M. E., Agarwal, S., Berlin, D. A., Boehme, A. K., Brodie, D., Choi, J. M., Doyle, K., Fins, J. J., Ganglberger, W., Hoffman, K., Mittel, A. M., Roh, D., Mukerji, S. S., Der Nigoghossian, C., Park, S., Schenck, E. J., Salazar-Schicchi, J., Shen, Q., Sholle, E., Velazquez, A. G., Walline, M. C., Westover, M. B., Brown, E. N., Victor, J., Edlow, B. L., Schiff, N. D., Claassen, J. 2022; 91 (6): 740-755

  Abstract

  The purpose of this study was to estimate the time to recovery of command-following and associations between hypoxemia with time to recovery of command-following.In this multicenter, retrospective, cohort study during the initial surge of the United States' pandemic (March-July 2020) we estimate the time from intubation to recovery of command-following, using Kaplan Meier cumulative-incidence curves and Cox proportional hazard models. Patients were included if they were admitted to 1 of 3 hospitals because of severe coronavirus disease 2019 (COVID-19), required endotracheal intubation for at least 7 days, and experienced impairment of consciousness (Glasgow Coma Scale motor score <6).Five hundred seventy-one patients of the 795 patients recovered command-following. The median time to recovery of command-following was 30 days (95% confidence interval [CI] = 27-32 days). Median time to recovery of command-following increased by 16 days for patients with at least one episode of an arterial partial pressure of oxygen (PaO2 ) value ≤55 mmHg (p < 0.001), and 25% recovered ≥10 days after cessation of mechanical ventilation. The time to recovery of command-following  was associated with hypoxemia (PaO2  ≤55 mmHg hazard ratio [HR] = 0.56, 95% CI = 0.46-0.68; PaO2  ≤70 HR = 0.88, 95% CI = 0.85-0.91), and each additional day of hypoxemia decreased the likelihood of recovery, accounting for confounders including sedation. These findings were confirmed among patients without any imagining evidence of structural brain injury (n = 199), and in a non-overlapping second surge cohort (N = 427, October 2020 to April 2021).Survivors of severe COVID-19 commonly recover consciousness weeks after cessation of mechanical ventilation. Long recovery periods are associated with more severe hypoxemia. This relationship is not explained by sedation or brain injury identified on clinical imaging and should inform decisions about life-sustaining therapies. ANN NEUROL 2022;91:740-755.

  View details for DOI 10.1002/ana.26342

  View details for PubMedID 35254675

  View details for PubMedCentralID PMC9082460

• Measuring expertise in identifying interictal epileptiform discharges. Epileptic disorders : international epilepsy journal with videotape Harid, N. M., Jing, J., Hogan, J., Nascimento, F. A., Ouyang, A., Zheng, W. L., Ge, W., Zafar, S. F., Kim, J. A., Alice, D. L., Herlopian, A., Maus, D., Karakis, I., Ng, M., Hong, S., Yu, Z., Kaplan, P. W., Cash, S., Shafi, M., Martz, G., Halford, J. J., Westover, M. B. 2022; 24 (3): 496-506

  Abstract

  Interictal epileptiform discharges on EEG are integral to diagnosing epilepsy. However, EEGs are interpreted by readers with and without specialty training, and there is no accepted method to assess skill in interpretation. We aimed to develop a test to quantify IED recognition skills.A total of 13,262 candidate IEDs were selected from EEGs and scored by eight fellowship-trained reviewers to establish a gold standard. An online test was developed to assess how well readers with different training levels could distinguish candidate waveforms. Sensitivity, false positive rate and calibration were calculated for each reader. A simple mathematical model was developed to estimate each reader's skill and threshold in identifying an IED, and to develop receiver operating characteristics curves for each reader. We investigated the number of IEDs needed to measure skill level with acceptable precision.Twenty-nine raters completed the test; nine experts, seven experienced non-experts and thirteen novices. Median calibration errors for experts, experienced non-experts and novices were -0.056, 0.012, 0.046; median sensitivities were 0.800, 0.811, 0.715; and median false positive rates were 0.177, 0.272, 0.396, respectively. The number of test questions needed to measure those scores was 549. Our analysis identified that novices had a higher noise level (uncertainty) compared to experienced non-experts and experts. Using calculated noise and threshold levels, receiver operating curves were created, showing increasing median area under the curve from novices (0.735), to experienced non-experts (0.852) and experts (0.891).Expert and non-expert readers can be distinguished based on ability to identify IEDs. This type of assessment could also be used to identify and correct differences in thresholds in identifying IEDs.

  View details for DOI 10.1684/epd.2021.1409

  View details for PubMedID 35770748

  View details for PubMedCentralID PMC9340812

• The National Inpatient Sample: A Primer for Neurosurgical Big Data Research and Systematic Review. World neurosurgery Tang, O. Y., Pugacheva, A., Bajaj, A. I., Rivera Perla, K. M., Weil, R. J., Toms, S. A. 2022; 162: e198-e217

  Abstract

  The National Inpatient Sample (NIS) (the largest all-payer inpatient database in the United States) is an important instrument for big data analysis of neurosurgical inquiries. However, earlier research has determined that many NIS studies are limited by common methodological pitfalls. In this study, we provide the first primer of NIS methodological procedures in the setting of neurosurgical research and review all reported neurosurgical studies using the NIS.We designed a protocol for neurosurgical big data research using the NIS, based on our subject matter expertise, NIS documentation, and input and verification from the Healthcare Cost and Utilization Project. We subsequently used a comprehensive search strategy to identify all neurosurgical studies using the NIS in the PubMed and MEDLINE, Embase, and Web of Science databases from inception to August 2021. Studies underwent qualitative categorization (years of NIS studied, neurosurgical subspecialty, age group, and thematic focus of study objective) and analysis of longitudinal trends.We identified a canonical, 4-step protocol for NIS analysis: study population selection; defining additional clinical variables; identification and coding of outcomes; and statistical analysis. Methodological nuances discussed include identifying neurosurgery-specific admissions, addressing missing data, calculating additional severity and hospital-specific metrics, coding perioperative complications, and applying survey weights to make nationwide estimates. Inherent database limitations and common pitfalls of NIS studies discussed include lack of disease process-specific variables and data after the index admission, inability to calculate certain hospital-specific variables after 2011, performing state-level analyses, conflating hospitalization charges and costs, and not following proper statistical methodology for performing survey-weighted regression. In a systematic review, we identified 647 neurosurgical studies using the NIS. Although almost 60% of studies were reported after 2015, <10% of studies analyzed NIS data after 2015. The average sample size of studies was 507,352 patients (standard deviation = 2,739,900). Most studies analyzed cranial procedures (58.1%) and adults (68.1%). The most prevalent topic areas analyzed were surgical outcome trends (35.7%) and health policy and economics (17.8%), whereas patient disparities (9.4%) and surgeon or hospital volume (6.6%) were the least studied.We present a standardized methodology to analyze the NIS, systematically review the state of the NIS neurosurgical literature, suggest potential future directions for neurosurgical big data inquiries, and outline recommendations to improve the design of future neurosurgical data instruments.

  View details for DOI 10.1016/j.wneu.2022.02.113

  View details for PubMedID 35247618

• Antiseizure Medication Treatment and Outcomes in Patients with Subarachnoid Hemorrhage Undergoing Continuous EEG Monitoring. Neurocritical care Zafar, S. F., Rosenthal, E. S., Postma, E. N., Sanches, P., Ayub, M. A., Rajan, S., Kim, J. A., Rubin, D. B., Lee, H., Patel, A. B., Hsu, J., Patorno, E., Westover, M. B. 2022; 36 (3): 857-867

  Abstract

  Patients with aneurysmal subarachnoid hemorrhage (aSAH) with electroencephalographic epileptiform activity (seizures, periodic and rhythmic patterns, and sporadic discharges) are frequently treated with antiseizure medications (ASMs). However, the safety and effectiveness of ASM treatment for epileptiform activity has not been established. We used observational data to investigate the effectiveness of ASM treatment in patients with aSAH undergoing continuous electroencephalography (cEEG) to develop a causal hypothesis for testing in prospective trials.This was a retrospective single-center cohort study of patients with aSAH admitted between 2011 and 2016. Patients underwent ≥ 24 h of cEEG within 4 days of admission. All patients received primary ASM prophylaxis until aneurysm treatment (typically within 24 h of admission). Treatment exposure was defined as reinitiation of ASMs after aneurysm treatment and cEEG initiation. We excluded patients with non-cEEG indications for ASMs (e.g., epilepsy, acute symptomatic seizures). Outcomes measures were 90-day mortality and good functional outcome (modified Rankin Scale scores 0-3). Propensity scores were used to adjust for baseline covariates and disease severity.Ninety-four patients were eligible (40 continued ASM treatment; 54 received prophylaxis only). ASM continuation was not significantly associated with higher 90-day mortality (propensity-adjusted hazard ratio [HR] = 2.01 [95% confidence interval (CI) 0.57-7.02]). ASM continuation was associated with lower likelihood for 90-day good functional outcome (propensity-adjusted HR = 0.39 [95% CI 0.18-0.81]). In a secondary analysis, low-intensity treatment (low-dose single ASM) was not significantly associated with mortality (propensity-adjusted HR = 0.60 [95% CI 0.10-3.59]), although it was associated with a lower likelihood of good outcome (propensity-adjusted HR = 0.37 [95% CI 0.15-0.91]), compared with prophylaxis. High-intensity treatment (high-dose single ASM, multiple ASMs, or anesthetics) was associated with higher mortality (propensity-adjusted HR = 6.80 [95% CI 1.67-27.65]) and lower likelihood for good outcomes (propensity-adjusted HR = 0.30 [95% CI 0.10-0.94]) compared with prophylaxis only.Our findings suggest the testable hypothesis that continuing ASMs in patients with aSAH with cEEG abnormalities does not improve functional outcomes. This hypothesis should be tested in prospective randomized studies.

  View details for DOI 10.1007/s12028-021-01387-x

  View details for PubMedID 34843082

  View details for PubMedCentralID PMC9117405

• Teaching NeuroImage: Sturge-Weber Syndrome in an Adult NEUROLOGY Nascimento, F. A., McLaren, J. R., Westover, M., Zafar, S. F., Stufflebeam, S. M. 2022; 98 (19): 814-815

  View details for DOI 10.1212/WNL.0000000000200512

  View details for Web of Science ID 000794002600008

  View details for PubMedID 35410908

  View details for PubMedCentralID PMC9141624

• Accurate identification of EEG recordings with interictal epileptiform discharges using a hybrid approach: Artificial intelligence supervised by human experts. Epilepsia Kural, M. A., Jing, J., Fürbass, F., Perko, H., Qerama, E., Johnsen, B., Fuchs, S., Westover, M. B., Beniczky, S. 2022; 63 (5): 1064-1073

  Abstract

  To evaluate the diagnostic performance of artificial intelligence (AI)-based algorithms for identifying the presence of interictal epileptiform discharges (IEDs) in routine (20-min) electroencephalography (EEG) recordings.We evaluated two approaches: a fully automated one and a hybrid approach, where three human raters applied an operational IED definition to assess the automated detections grouped into clusters by the algorithms. We used three previously developed AI algorithms: Encevis, SpikeNet, and Persyst. The diagnostic gold standard (epilepsy or not) was derived from video-EEG recordings of patients' habitual clinical episodes. We compared the algorithms with the gold standard at the recording level (epileptic or not). The independent validation data set (not used for training) consisted of 20-min EEG recordings containing sharp transients (epileptiform or not) from 60 patients: 30 with epilepsy (with a total of 340 IEDs) and 30 with nonepileptic paroxysmal events. We compared sensitivity, specificity, overall accuracy, and the review time-burden of the fully automated and hybrid approaches, with the conventional visual assessment of the whole recordings, based solely on unrestricted expert opinion.For all three AI algorithms, the specificity of the fully automated approach was too low for clinical implementation (16.67%; 63.33%; 3.33%), despite the high sensitivity (96.67%; 66.67%; 100.00%). Using the hybrid approach significantly increased the specificity (93.33%; 96.67%; 96.67%) with good sensitivity (93.33%; 56.67%; 76.67%). The overall accuracy of the hybrid methods (93.33%; 76.67%; 86.67%) was similar to the conventional visual assessment of the whole recordings (83.33%; 95% confidence interval [CI]: 71.48-91.70%; p > .5), yet the time-burden of review was significantly lower (p < .001).The hybrid approach, where human raters apply the operational IED criteria to automated detections of AI-based algorithms, has high specificity, good sensitivity, and overall accuracy similar to conventional EEG reading, with a significantly lower time-burden. The hybrid approach is accurate and suitable for clinical implementation.

  View details for DOI 10.1111/epi.17206

  View details for PubMedID 35184276

  View details for PubMedCentralID PMC9148170

• Predicting Neurological Outcome From Electroencephalogram Dynamics in Comatose Patients After Cardiac Arrest With Deep Learning. IEEE transactions on bio-medical engineering Zheng, W. L., Amorim, E., Jing, J., Wu, O., Ghassemi, M., Lee, J. W., Sivaraju, A., Pang, T., Herman, S. T., Gaspard, N., Ruijter, B. J., Tjepkema-Cloostermans, M. C., Hofmeijer, J., van Putten, M. J., Westover, M. B. 2022; 69 (5): 1813-1825

  Abstract

  Most cardiac arrest patients who are successfully resuscitated are initially comatose due to hypoxic-ischemic brain injury. Quantitative electroencephalography (EEG) provides valuable prognostic information. However, prior approaches largely rely on snapshots of the EEG, without taking advantage of temporal information.We present a recurrent deep neural network with the goal of capturing temporal dynamics from longitudinal EEG data to predict long-term neurological outcomes. We utilized a large international dataset of continuous EEG recordings from 1,038 cardiac arrest patients from seven hospitals in Europe and the US. Poor outcome was defined as a Cerebral Performance Category (CPC) score of 3-5, and good outcome as CPC score 0-2 at 3 to 6-months after cardiac arrest. Model performance is evaluated using 5-fold cross validation.The proposed approach provides predictions which improve over time, beginning from an area under the receiver operating characteristic curve (AUC-ROC) of 0.78 (95% CI: 0.72-0.81) at 12 hours, and reaching 0.88 (95% CI: 0.85-0.91) by 66 h after cardiac arrest. At 66 h, (sensitivity, specificity) points of interest on the ROC curve for predicting poor outcomes were (32,99)%, (55,95)%, and (62,90)%, (99,23)%, (95,47)%, and (90,62)%; whereas for predicting good outcome, the corresponding operating points were (17,99)%, (47,95)%, (62,90)%, (99,19)%, (95,48)%, (70,90)%. Moreover, the model provides predicted probabilities that closely match the observed frequencies of good and poor outcomes (calibration error 0.04).These findings suggest that accounting for EEG trend information can substantially improve prediction of neurologic outcomes for patients with coma following cardiac arrest.

  View details for DOI 10.1109/TBME.2021.3139007

  View details for PubMedID 34962860

  View details for PubMedCentralID PMC9087641

• Severe cerebral edema in substance-related cardiac arrest patients. Resuscitation Kulpanowski, A. M., Copen, W. A., Hancock, B. L., Rosenthal, E. S., Schoenfeld, D. A., Dodelson, J. A., Edlow, B. L., Kimberly, W. T., Amorim, E., Westover, M. B., Ning, M. M., Schaefer, P. W., Malhotra, R., Giacino, J. T., Greer, D. M., Wu, O. 2022; 173: 103-111

  Abstract

  Studies of neurologic outcomes have found conflicting results regarding differences between patients with substance-related cardiac arrests (SRCA) and non-SRCA. We investigate the effects of SRCA on severe cerebral edema development, a neuroimaging intermediate endpoint for neurologic injury.327 out-of-hospital comatose cardiac arrest patients were retrospectively analyzed. Demographics and baseline clinical characteristics were examined. SRCA categorization was based on admission toxicology screens. Severe cerebral edema classification was based on radiology reports. Poor clinical outcomes were defined as discharge Cerebral Performance Category scores > 3.SRCA patients (N = 86) were younger (P < 0.001), and more likely to have non-shockable rhythms (P < 0.001), be unwitnessed (P < 0.001), lower Glasgow Coma Scale scores (P < 0.001), absent brainstem reflexes (P < 0.05) and develop severe cerebral edema (P < 0.001) than non-SRCA patients (N = 241). Multivariable analyses found younger age (P < 0.001), female sex (P = 0.008), non-shockable rhythm (P = 0.01) and SRCA (P = 0.05) to be predictors of severe cerebral edema development. Older age (P < 0.001), non-shockable rhythm (P = 0.02), severe cerebral edema (P < 0.001), and absent pupillary light reflexes (P = 0.004) were predictors of poor outcomes. SRCA patients had higher proportion of brain deaths (P < 0.001) compared to non-SRCA patients.SRCA results in higher rates of severe cerebral edema development and brain death. The absence of statistically significant differences in discharge outcomes or survival between SRCA and non-SRCA patients may be related to the higher rate of withdrawal of life-sustaining treatment (WLST) in the non-SRCA group. Future neuroprognostic studies may opt to include neuroimaging markers as intermediate measures of neurologic injury which are not influenced by WLST decisions.

  View details for DOI 10.1016/j.resuscitation.2022.01.033

  View details for PubMedID 35149137

  View details for PubMedCentralID PMC9282938

• How Machine Learning is Powering Neuroimaging to Improve Brain Health. Neuroinformatics Singh, N. M., Harrod, J. B., Subramanian, S., Robinson, M., Chang, K., Cetin-Karayumak, S., Dalca, A. V., Eickhoff, S., Fox, M., Franke, L., Golland, P., Haehn, D., Iglesias, J. E., O'Donnell, L. J., Ou, Y., Rathi, Y., Siddiqi, S. H., Sun, H., Westover, M. B., Whitfield-Gabrieli, S., Gollub, R. L. 2022

  Abstract

  This report presents an overview of how machine learning is rapidly advancing clinical translational imaging in ways thatwill aid in the early detection, prediction, and treatment of diseases that threaten brain health. Towards this goal, we aresharing the information presented at a symposium, "Neuroimaging Indicators of Brain Structure and Function - Closingthe Gap Between Research and Clinical Application", co-hosted by the McCance Center for Brain Health at Mass GeneralHospital and the MIT HST Neuroimaging Training Program on February 12, 2021. The symposium focused on the potentialfor machine learning approaches, applied to increasingly large-scale neuroimaging datasets, to transform healthcare deliveryand change the trajectory of brain health by addressing brain care earlier in the lifespan. While not exhaustive, this overviewuniquely addresses many of the technical challenges from image formation, to analysis and visualization, to synthesisand incorporation into the clinical workflow. Some of the ethical challenges inherent to this work are also explored, as aresome of the regulatory requirements for implementation. We seek to educate, motivate, and inspire graduate students, postdoctoralfellows, and early career investigators to contribute to a future where neuroimaging meaningfully contributes to themaintenance of brain health.

  View details for DOI 10.1007/s12021-022-09572-9

  View details for PubMedID 35347570

• A Primer on EEG Spectrograms. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Ng, M. C., Jing, J., Westover, M. B. 2022; 39 (3): 177-183

  Abstract

  As continuous brain monitoring becomes a routine part of clinical care, continuous EEG has allowed better detection and characterization of nonconvulsive seizures, and patterns along the ictal-interictal continuum in critically ill patients. However, this increased workload has led many to turn to quantitative EEG whose central tool is the "spectrogram." Although in relatively wide use, many clinicians lack a detailed understanding of how spectrograms relate to the underlying "raw" EEG signal. This article provides an approachable set of first principles to help clinicians understand how spectrograms encode information about the raw EEG and how to interpret spectrograms to efficiently infer underlying EEG patterns.

  View details for DOI 10.1097/WNP.0000000000000736

  View details for PubMedID 34510095

  View details for PubMedCentralID PMC8901534

• Decoding the Spectrogram Rainbow. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Ng, M. C., Westover, M. B. 2022; 39 (3): 176

  View details for DOI 10.1097/WNP.0000000000000741

  View details for PubMedID 34510094

  View details for PubMedCentralID PMC8901547

• Combining Transcranial Doppler and EEG Data to Predict Delayed Cerebral Ischemia After Subarachnoid Hemorrhage. Neurology Chen, H. Y., Elmer, J., Zafar, S. F., Ghanta, M., Moura Junior, V., Rosenthal, E. S., Gilmore, E. J., Hirsch, L. J., Zaveri, H. P., Sheth, K. N., Petersen, N. H., Westover, M. B., Kim, J. A. 2022; 98 (5): e459-e469

  Abstract

  Delayed cerebral ischemia (DCI) is the leading complication of subarachnoid hemorrhage (SAH). Because DCI was traditionally thought to be caused by large vessel vasospasm, transcranial Doppler ultrasounds (TCDs) have been the standard of care. Continuous EEG has emerged as a promising complementary monitoring modality and predicts increased DCI risk. Our objective was to determine whether combining EEG and TCD data improves prediction of DCI after SAH. We hypothesize that integrating these diagnostic modalities improves DCI prediction.We retrospectively assessed patients with moderate to severe SAH (2011-2015; Fisher 3-4 or Hunt-Hess 4-5) who had both prospective TCD and EEG acquisition during hospitalization. Middle cerebral artery (MCA) peak systolic velocities (PSVs) and the presence or absence of epileptiform abnormalities (EAs), defined as seizures, epileptiform discharges, and rhythmic/periodic activity, were recorded daily. Logistic regressions were used to identify significant covariates of EAs and TCD to predict DCI. Group-based trajectory modeling (GBTM) was used to account for changes over time by identifying distinct group trajectories of MCA PSV and EAs associated with DCI risk.We assessed 107 patients; DCI developed in 56 (51.9%). Univariate predictors of DCI are presence of high-MCA velocity (PSV ≥200 cm/s, sensitivity 27%, specificity 89%) and EAs (sensitivity 66%, specificity 62%) on or before day 3. Two univariate GBTM trajectories of EAs predicted DCI (sensitivity 64%, specificity 62.75%). Logistic regression and GBTM models using both TCD and EEG monitoring performed better. The best logistic regression and GBTM models used both TCD and EEG data, Hunt-Hess score at admission, and aneurysm treatment as predictors of DCI (logistic regression: sensitivity 90%, specificity 70%; GBTM: sensitivity 89%, specificity 67%).EEG and TCD biomarkers combined provide the best prediction of DCI. The conjunction of clinical variables with the timing of EAs and high MCA velocities improved model performance. These results suggest that TCD and cEEG are promising complementary monitoring modalities for DCI prediction. Our model has potential to serve as a decision support tool in SAH management.This study provides Class II evidence that combined TCD and EEG monitoring can identify delayed cerebral ischemia after SAH.

  View details for DOI 10.1212/WNL.0000000000013126

  View details for PubMedID 34845057

  View details for PubMedCentralID PMC8826465

• One EEG, one read - A manifesto towards reducing interrater variability among experts. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Nascimento, F. A., Jing, J., Beniczky, S., Benbadis, S. R., Gavvala, J. R., Yacubian, E. M., Wiebe, S., Rampp, S., van Putten, M. J., Tripathi, M., Cook, M. J., Kaplan, P. W., Tatum, W. O., Trinka, E., Cole, A. J., Westover, M. B. 2022; 133: 68-70

  View details for DOI 10.1016/j.clinph.2021.10.007

  View details for PubMedID 34814017

  View details for PubMedCentralID PMC8926459

• ATD: Augmenting CP Tensor Decomposition by Self Supervision. Advances in neural information processing systems Yang, C., Qian, C., Singh, N., Xiao, C., Westover, M. B., Solomonik, E., Sun, J. 2022; 35: 32039-32052

  Abstract

  Tensor decompositions are powerful tools for dimensionality reduction and feature interpretation of multidimensional data such as signals. Existing tensor decomposition objectives (e.g., Frobenius norm) are designed for fitting raw data under statistical assumptions, which may not align with downstream classification tasks. In practice, raw input tensor can contain irrelevant information while data augmentation techniques may be used to smooth out class-irrelevant noise in samples. This paper addresses the above challenges by proposing augmented tensor decomposition (ATD), which effectively incorporates data augmentations and self-supervised learning (SSL) to boost downstream classification. To address the non-convexity of the new augmented objective, we develop an iterative method that enables the optimization to follow an alternating least squares (ALS) fashion. We evaluate our proposed ATD on multiple datasets. It can achieve 0.8% ~ 2.5% accuracy gain over tensor-based baselines. Also, our ATD model shows comparable or better performance (e.g., up to 15% in accuracy) over self-supervised and autoencoder baselines while using less than 5% of learnable parameters of these baseline models.

  View details for PubMedID 37994346

  View details for PubMedCentralID PMC10664864

• VE-CAM-S: Visual EEG-Based Grading of Delirium Severity and Associations With Clinical Outcomes. Critical care explorations Tesh, R. A., Sun, H., Jing, J., Westmeijer, M., Neelagiri, A., Rajan, S., Krishnamurthy, P. V., Sikka, P., Quadri, S. A., Leone, M. J., Paixao, L., Panneerselvam, E., Eckhardt, C., Struck, A. F., Kaplan, P. W., Akeju, O., Jones, D., Kimchi, E. Y., Westover, M. B. 2022; 4 (1): e0611

  Abstract

  To develop a physiologic grading system for the severity of acute encephalopathy manifesting as delirium or coma, based on EEG, and to investigate its association with clinical outcomes.This prospective, single-center, observational cohort study was conducted from August 2015 to December 2016 and October 2018 to December 2019.Academic medical center, all inpatient wards.Adult inpatients undergoing a clinical EEG recording; excluded if deaf, severely aphasic, developmentally delayed, non-English speaking (if noncomatose), or if goals of care focused primarily on comfort measures. Four-hundred six subjects were assessed; two were excluded due to technical EEG difficulties.None.A machine learning model, with visually coded EEG features as inputs, was developed to produce scores that correlate with behavioral assessments of delirium severity (Confusion Assessment Method-Severity [CAM-S] Long Form [LF] scores) or coma; evaluated using Spearman R correlation; area under the receiver operating characteristic curve (AUC); and calibration curves. Associations of Visual EEG Confusion Assessment Method Severity (VE-CAM-S) were measured for three outcomes: functional status at discharge (via Glasgow Outcome Score [GOS]), inhospital mortality, and 3-month mortality. Four-hundred four subjects were analyzed (mean [sd] age, 59.8 yr [17.6 yr]; 232 [57%] male; 320 [79%] White; 339 [84%] non-Hispanic); 132 (33%) without delirium or coma, 143 (35%) with delirium, and 129 (32%) with coma. VE-CAM-S scores correlated strongly with CAM-S scores (Spearman correlation 0.67 [0.62-0.73]; p < 0.001) and showed excellent discrimination between levels of delirium (CAM-S LF = 0 vs ≥ 4, AUC 0.85 [0.78-0.92], calibration slope of 1.04 [0.87-1.19] for CAM-S LF ≤ 4 vs ≥ 5). VE-CAM-S scores were strongly associated with important clinical outcomes including inhospital mortality (AUC 0.79 [0.72-0.84]), 3-month mortality (AUC 0.78 [0.71-0.83]), and GOS at discharge (0.76 [0.69-0.82]).VE-CAM-S is a physiologic grading scale for the severity of symptoms in the setting of delirium and coma, based on visually assessed electroencephalography features. VE-CAM-S scores are strongly associated with clinical outcomes.

  View details for DOI 10.1097/CCE.0000000000000611

  View details for PubMedID 35072078

  View details for PubMedCentralID PMC8769081

• Physiological Assessment of Delirium Severity: The Electroencephalographic Confusion Assessment Method Severity Score (E-CAM-S). Critical care medicine van Sleuwen, M., Sun, H., Eckhardt, C., Neelagiri, A., Tesh, R. A., Westmeijer, M., Paixao, L., Rajan, S., Velpula Krishnamurthy, P., Sikka, P., Leone, M. J., Panneerselvam, E., Quadri, S. A., Akeju, O., Kimchi, E. Y., Westover, M. B. 2022; 50 (1): e11-e19

  Abstract

  Delirium is a common and frequently underdiagnosed complication in acutely hospitalized patients, and its severity is associated with worse clinical outcomes. We propose a physiologically based method to quantify delirium severity as a tool that can help close this diagnostic gap: the Electroencephalographic Confusion Assessment Method Severity Score (E-CAM-S).Retrospective cohort study.Single-center tertiary academic medical center.Three-hundred seventy-three adult patients undergoing electroencephalography to evaluate altered mental status between August 2015 and December 2019.None.We developed the E-CAM-S based on a learning-to-rank machine learning model of forehead electroencephalography signals. Clinical delirium severity was assessed using the Confusion Assessment Method Severity (CAM-S). We compared associations of E-CAM-S and CAM-S with hospital length of stay and inhospital mortality. E-CAM-S correlated with clinical CAM-S (R = 0.67; p < 0.0001). For the overall cohort, E-CAM-S and CAM-S were similar in their strength of association with hospital length of stay (correlation = 0.31 vs 0.41, respectively; p = 0.082) and inhospital mortality (area under the curve = 0.77 vs 0.81; p = 0.310). Even when restricted to noncomatose patients, E-CAM-S remained statistically similar to CAM-S in its association with length of stay (correlation = 0.37 vs 0.42, respectively; p = 0.188) and inhospital mortality (area under the curve = 0.83 vs 0.74; p = 0.112). In addition to previously appreciated spectral features, the machine learning framework identified variability in multiple measures over time as important features in electroencephalography-based prediction of delirium severity.The E-CAM-S is an automated, physiologic measure of delirium severity that predicts clinical outcomes with a level of performance comparable to conventional interview-based clinical assessment.

  View details for DOI 10.1097/CCM.0000000000005224

  View details for PubMedID 34582420

  View details for PubMedCentralID PMC8678335

• Using electronic health data to explore effectiveness of ICU EEG and anti-seizure treatment ANNALS OF CLINICAL AND TRANSLATIONAL NEUROLOGY Amerineni, R., Sun, H., Lee, H., Hsu, J., Patorno, E., Westover, M., Zafar, S. F. 2021; 8 (12): 2270-2279

  Abstract

  The purpose of this study was to examine critical care continuous electroencephalography (cEEG) utilization and downstream anti-seizure treatment patterns, their association with outcomes, and generate hypotheses for larger comparative effectiveness studies of cEEG-guided interventions.Single-center retrospective study of critically ill patients (n = 14,523, age ≥18 years). Exposure defined as ≥24 h of cEEG and subsequent anti-seizure medication (ASM) escalation, with or without concomitant anesthetic. Exposure window was the first 7 days of admission. Primary outcome was in-hospital mortality. Multivariable analysis was performed using penalized logistic regression.One thousand and seventy-three patients underwent ≥24 h of cEEG within 7 days of admission. After adjusting for disease severity, ≥24 h of cEEG followed by ASM escalation in patients not on anesthetics (n = 239) was associated with lower in-hospital mortality (OR 0.76 [0.53-1.07]), though the finding did not reach significance. ASM escalation with concomitant anesthetic use (n = 484) showed higher odds for mortality (OR 1.41 [1.03-1.94]). In the seizures/status epilepticus subgroup, post cEEG ASM escalation without anesthetics showed lower odds for mortality (OR 0.43 [0.23-0.74]). Within the same subgroup, ASM escalation with concomitant anesthetic use showed higher odds for mortality (OR 1.34 [0.92-1.91]) though not significant.Based on our findings we propose the following hypotheses for larger comparative effectiveness studies investigating the direct causal effect of cEEG-guided treatment on outcomes: (1) cEEG-guided ASM escalation may improve outcomes in critically ill patients with seizures; (2) cEEG-guided treatment with combination of ASMs and anesthetics may not improve outcomes in all critically ill patients.

  View details for DOI 10.1002/acn3.51478

  View details for Web of Science ID 000720728200001

  View details for PubMedID 34802196

  View details for PubMedCentralID PMC8670316

• Disentangling EEG responses to TMS due to cortical and peripheral activations. Brain stimulation Rocchi, L., Di Santo, A., Brown, K., Ibáñez, J., Casula, E., Rawji, V., Di Lazzaro, V., Koch, G., Rothwell, J. 2021; 14 (1): 4-18

  Abstract

  the use of combined transcranial magnetic stimulation (TMS) and electroencephalography (EEG) for the functional evaluation of the cerebral cortex in health and disease is becoming increasingly common. However, there is still some ambiguity regarding the extent to which brain responses to auditory and somatosensory stimulation contribute to the TMS-evoked potential (TEP).to measure separately the contribution of auditory and somatosensory stimulation caused by TMS, and to assess their contribution to the TEP waveform, when stimulating the motor cortex (M1).19 healthy volunteers underwent 7 blocks of EEG recording. To assess the impact of auditory stimulation on the TEP waveform, we used a standard figure of eight coil, with or without masking with a continuous noise reproducing the specific time-varying frequencies of the TMS click, stimulating at 90% of resting motor threshold. To further characterise auditory responses due to the TMS click, we used either a standard or a sham figure of eight coil placed on a pasteboard cylinder that rested on the scalp, with or without masking. Lastly, we used electrical stimulation of the scalp to investigate the possible contribution of somatosensory activation.auditory stimulation induced a known pattern of responses in electrodes located around the vertex, which could be suppressed by appropriate noise masking. Electrical stimulation of the scalp alone only induced similar, non-specific scalp responses in the in the central electrodes. TMS, coupled with appropriate masking of sensory input, resulted in specific, lateralized responses at the stimulation site, lasting around 300 ms.if careful control of confounding sources is applied, TMS over M1 can generate genuine, lateralized EEG activity. By contrast, sensory evoked responses, if present, are represented by non-specific, late (100-200 ms) components, located at the vertex, possibly due to saliency of the stimuli. Notably, the latter can confound the TEP if masking procedures are not properly used.

  View details for DOI 10.1016/j.brs.2020.10.011

  View details for PubMedID 33127580

• Detection of EEG burst-suppression in neurocritical care patients using an unsupervised machine learning algorithm. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Narula, G., Haeberlin, M., Balsiger, J., Strässle, C., Imbach, L. L., Keller, E. 2021; 132 (10): 2485-2492

  Abstract

  The burst suppression pattern in clinical electroencephalographic (EEG) recordings is an important diagnostic tool because of its association with comas of various etiologies, as with hypoxia, drug related intoxication or deep anesthesia. The detection of bursts and the calculation of burst/suppression ratio are often used to monitor the level of anesthesia during treatment of status epilepticus. However, manual counting of bursts is a laborious process open to inter-rater variation and motivates a need for automatic detection.We describe a novel unsupervised learning algorithm that detects bursts in EEG and generates burst-per-minute estimates for the purpose of monitoring sedation level in an intensive care unit (ICU). We validated the algorithm on 29 hours of burst annotated EEG data from 29 patients suffering from status epilepticus and hemorrhage.We report competitive results in comparison to neural networks learned via supervised learning. The mean absolute error (SD) in bursts per minute was 0.93 (1.38).We present a novel burst suppression detection algorithm that adapts to each patient individually, reports bursts-per-minute quickly, and does not require manual fine-tuning unlike previous approaches to burst-suppression pattern detection.Our algorithm for automatic burst suppression quantification can greatly reduce manual oversight in depth of sedation monitoring.

  View details for DOI 10.1016/j.clinph.2021.07.018

  View details for PubMedID 34454277

• Modified EASIX predicts severe cytokine release syndrome and neurotoxicity after chimeric antigen receptor T cells. Blood advances Pennisi, M., Sanchez-Escamilla, M., Flynn, J. R., Shouval, R., Alarcon Tomas, A., Silverberg, M. L., Batlevi, C., Brentjens, R. J., Dahi, P. B., Devlin, S. M., Diamonte, C., Giralt, S., Halton, E. F., Jain, T., Maloy, M., Mead, E., Palomba, M. L., Ruiz, J., Santomasso, B., Sauter, C. S., Scordo, M., Shah, G. L., Park, J. H., Yanez San Segundo, L., Perales, M. A. 2021; 5 (17): 3397-3406

  Abstract

  Patients who develop chimeric antigen receptor (CAR) T-cell-related severe cytokine release syndrome (CRS) and immune effector cell-associated neurotoxicity syndrome (ICANS) exhibit hemodynamic instability and endothelial activation. The EASIX (Endothelial Activation and Stress Index) score (lactate dehydrogenase [LDH; U/L] × creatinine [mg/dL]/platelets [PLTs; 109 cells/L]) is a marker of endothelial damage that correlates with outcomes in allogeneic hematopoietic cell transplantation. Elevated LDH and low PLTs have been associated with severe CRS and ICANS, as has C-reactive protein (CRP), while increased creatinine is seen only in a minority of advanced severe CRS cases. We hypothesized that EASIX and 2 new modified EASIX formulas (simplified EASIX, which excludes creatinine, and modified EASIX [m-EASIX], which replaces creatinine with CRP [mg/dL]), calculated peri-CAR T-cell infusion, would be associated with development of severe (grade ≥ 3) CRS and ICANS. We included 118 adults, 53 with B-acute lymphoblastic leukemia treated with 1928z CAR T cells (NCT01044069) and 65 with diffuse large B-cell lymphoma treated with axicabtagene ciloleucel or tisagenlecleucel. The 3 formulas showed similar predictive power for severe CRS and ICANS. However, low PLTs and high CRP values were the only variables individually correlated with these toxicities. Moreover, only m-EASIX was a significant predictor of disease response. m-EASIX could discriminate patients who subsequently developed severe CRS preceding the onset of severe symptoms (area under the curve [AUC] at lymphodepletion, 80.4%; at day -1, 73.0%; and at day +1, 75.4%). At day +3, it also had high discriminatory ability for severe ICANS (AUC, 73%). We propose m-EASIX as a clinical tool to potentially guide individualized management of patients at higher risk for severe CAR T-cell-related toxicities.

  View details for DOI 10.1182/bloodadvances.2020003885

  View details for PubMedID 34432870

  View details for PubMedCentralID PMC8525234

• Do Triphasic Waves and Nonconvulsive Status Epilepticus Arise From Similar Mechanisms? A Computational Model. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Ligtenstein, S., Song, J., Jin, J., Sun, H., Paixao, L., Zafar, S., Westover, M. B. 2021; 38 (5): 366-375

  Abstract

  Triphasic waves arising in patients with toxic metabolic encephalopathy (TME) are often considered different from generalized periodic discharges (GPDs) in patients with generalized nonconvulsive status epilepticus (GNCSE). The primary objective of this study was to investigate whether a common mechanism can explain key aspects of both triphasic waves in TME and GPDs in GNCSE.A neural mass model was used for the simulation of EEG patterns in patients with acute hepatic encephalopathy, a common etiology of TME. Increased neuronal excitability and impaired synaptic transmission because of elevated ammonia levels in acute hepatic encephalopathy patients were used to explain how triphasic waves and GNCSE arise. The effect of gamma-aminobutyric acid-ergic drugs on epileptiform activity, simulated with a prolonged duration of the inhibitory postsynaptic potential, was also studied.The simulations show that a model that includes increased neuronal excitability and impaired synaptic transmission can account for both the emergence of GPDs and GNCSE and their suppression by gamma-aminobutyric acid-ergic drugs.The results of this study add to evidence from other studies calling into question the dichotomy between triphasic waves in TME and GPDs in GNCSE and support the hypothesis that all GPDs, including those arising in TME patients, occur via a common mechanism.

  View details for DOI 10.1097/WNP.0000000000000719

  View details for PubMedID 34155185

  View details for PubMedCentralID PMC8429048

• Patterns of Recording Epileptic Spasms in an Electronic Seizure Diary Compared With Video-EEG and Historical Cohorts. Pediatric neurology LaGrant, B., Goldenholz, D. M., Braun, M., Moss, R. E., Grinspan, Z. M. 2021; 122: 27-34

  Abstract

  Use of electronic seizure diaries (e-diaries) by caregivers of children with epileptic spasms is not well understood. We describe the demographic and seizure-related information of children with epileptic spasms captured in a widely used e-diary and explore the potential biases in how caregivers report these data.We analyzed children with epileptic spasms in an e-diary, Seizure Tracker, from 2007 to 2018. We described variables including sex, time of seizure, percentage of spasms occurring as individual spasms (versus in clusters), cluster duration, and number of spasms per cluster. We compared seizure characteristics in the e-diary cohort with published cohorts to identify biases in caregiver-reported epileptic spasms. We also reviewed seizure patterns in a small cohort of children with epileptic spasms monitored on overnight video-electroencephalography (vEEG).There were 314 children in the e-diary cohort and nine children in the vEEG cohort. The e-diary cohort was more likely than expected to report counts divisible by five. The e-diary cohort had a lower proportion of nighttime spasms than expected based on data from published cohorts. The e-diary cohort had a significantly lower percentage of spasms as individual spasms, a greater number of spasms per cluster, and a greater cluster duration relative to the vEEG cohort.Caregivers using e-diaries for epileptic spasms may miss individual spams, be more likely to report long clusters, round counts to the nearest five, and underreport nighttime spasms. Clinicians should be aware of these reporting biases when using e-diary data to guide care for children with epileptic spasms.

  View details for DOI 10.1016/j.pediatrneurol.2021.04.008

  View details for PubMedID 34293636

  View details for PubMedCentralID PMC10164279

• Sleep apnea and respiratory anomaly detection from a wearable band and oxygen saturation SLEEP AND BREATHING Ganglberger, W., Bucklin, A. A., Tesh, R. A., Da Silva Cardoso, M., Sun, H., Leone, M. J., Paixao, L., Panneerselvam, E., Ye, E. M., Thompson, B., Akeju, O., Kuller, D., Thomas, R. J., Westover, M. 2022; 26 (3): 1033-1044

  Abstract

  Sleep-related respiratory abnormalities are typically detected using polysomnography. There is a need in general medicine and critical care for a more convenient method to detect sleep apnea automatically from a simple, easy-to-wear device. The objective was to detect abnormal respiration and estimate the Apnea-Hypopnea Index (AHI) automatically with a wearable respiratory device with and without SpO2 signals using a large (n = 412) dataset serving as ground truth.Simultaneously recorded polysomnography (PSG) and wearable respiratory effort data were used to train and evaluate models in a cross-validation fashion. Time domain and complexity features were extracted, important features were identified, and a random forest model was employed to detect events and predict AHI. Four models were trained: one each using the respiratory features only, a feature from the SpO2 (%)-signal only, and two additional models that use the respiratory features and the SpO2 (%) feature, one allowing a time lag of 30 s between the two signals.Event-based classification resulted in areas under the receiver operating characteristic curves of 0.94, 0.86, and 0.82, and areas under the precision-recall curves of 0.48, 0.32, and 0.51 for the models using respiration and SpO2, respiration-only, and SpO2-only, respectively. Correlation between expert-labelled and predicted AHI was 0.96, 0.78, and 0.93, respectively.A wearable respiratory effort signal with or without SpO2 signal predicted AHI accurately, and best performance was achieved with using both signals.

  View details for DOI 10.1007/s11325-021-02465-2

  View details for Web of Science ID 000686049600001

  View details for PubMedID 34409545

  View details for PubMedCentralID PMC8854446

• HIV increases sleep-based brain age despite antiretroviral therapy. Sleep Leone, M. J., Sun, H., Boutros, C. L., Liu, L., Ye, E., Sullivan, L., Thomas, R. J., Robbins, G. K., Mukerji, S. S., Westover, M. B. 2021; 44 (8)

  Abstract

  Age-related comorbidities and immune activation raise concern for advanced brain aging in people living with HIV (PLWH). The brain age index (BAI) is a machine learning model that quantifies deviations in brain activity during sleep relative to healthy individuals of the same age. High BAI was previously found to be associated with neurological, psychiatric, cardiometabolic diseases, and reduced life expectancy among people without HIV. Here, we estimated the effect of HIV infection on BAI by comparing PLWH and HIV- controls.Clinical data and sleep EEGs from 43 PLWH on antiretroviral therapy (HIV+) and 3,155 controls (HIV-) were collected from Massachusetts General Hospital. The effect of HIV infection on BAI, and on individual EEG features, was estimated using causal inference.The average effect of HIV on BAI was estimated to be +3.35 years (p < 0.01, 95% CI = [0.67, 5.92]) using doubly robust estimation. Compared to HIV- controls, HIV+ participants exhibited a reduction in delta band power during deep sleep and rapid eye movement sleep.We provide causal evidence that HIV contributes to advanced brain aging reflected in sleep EEG. A better understanding is greatly needed of potential therapeutic targets to mitigate the effect of HIV on brain health, potentially including sleep disorders and cardiovascular disease.

  View details for DOI 10.1093/sleep/zsab058

  View details for PubMedID 33783511

  View details for PubMedCentralID PMC8361332

• CD19-Targeted CAR T Cells in Refractory Systemic Lupus Erythematosus. The New England journal of medicine Mougiakakos, D., Krönke, G., Völkl, S., Kretschmann, S., Aigner, M., Kharboutli, S., Böltz, S., Manger, B., Mackensen, A., Schett, G. 2021; 385 (6): 567-569

  View details for DOI 10.1056/NEJMc2107725

  View details for PubMedID 34347960

• Automated Annotation of Epileptiform Burden and Its Association with Outcomes ANNALS OF NEUROLOGY Zafar, S. F., Rosenthal, E. S., Jing, J., Ge, W., Tabaeizadeh, M., Nour, H., Shoukat, M., Sun, H., Javed, F., Kassa, S., Edhi, M., Bordbar, E., Gallagher, J., Moura, V., Ghanta, M., Shao, Y., An, S., Sun, J., Cole, A. J., Westover, M. 2021; 90 (2): 300-311

  Abstract

  This study was undertaken to determine the dose-response relation between epileptiform activity burden and outcomes in acutely ill patients.A single center retrospective analysis was made of 1,967 neurologic, medical, and surgical patients who underwent >16 hours of continuous electroencephalography (EEG) between 2011 and 2017. We developed an artificial intelligence algorithm to annotate 11.02 terabytes of EEG and quantify epileptiform activity burden within 72 hours of recording. We evaluated burden (1) in the first 24 hours of recording, (2) in the 12-hours epoch with highest burden (peak burden), and (3) cumulatively through the first 72 hours of monitoring. Machine learning was applied to estimate the effect of epileptiform burden on outcome. Outcome measure was discharge modified Rankin Scale, dichotomized as good (0-4) versus poor (5-6).Peak epileptiform burden was independently associated with poor outcomes (p < 0.0001). Other independent associations included age, Acute Physiology and Chronic Health Evaluation II score, seizure on presentation, and diagnosis of hypoxic-ischemic encephalopathy. Model calibration error was calculated across 3 strata based on the time interval between last EEG measurement (up to 72 hours of monitoring) and discharge: (1) <5 days between last measurement and discharge, 0.0941 (95% confidence interval [CI] = 0.0706-0.1191); 5 to 10 days between last measurement and discharge, 0.0946 (95% CI = 0.0631-0.1290); >10 days between last measurement and discharge, 0.0998 (95% CI = 0.0698-0.1335). After adjusting for covariates, increase in peak epileptiform activity burden from 0 to 100% increased the probability of poor outcome by 35%.Automated measurement of peak epileptiform activity burden affords a convenient, consistent, and quantifiable target for future multicenter randomized trials investigating whether suppressing epileptiform activity improves outcomes. ANN NEUROL 2021;90:300-311.

  View details for DOI 10.1002/ana.26161

  View details for Web of Science ID 000674913900001

  View details for PubMedID 34231244

  View details for PubMedCentralID PMC8516549

• Clinical Electroencephalography Findings and Considerations in Hospitalized Patients With Coronavirus SARS-CoV-2. The Neurohospitalist Ayub, N., Cohen, J., Jing, J., Jain, A., Tesh, R., Mukerji, S. S., Zafar, S. F., Westover, M. B., Kimchi, E. Y. 2021; 11 (3): 204-213

  Abstract

  Reports have suggested that severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes neurologic manifestations including encephalopathy and seizures. However, there has been relatively limited electrophysiology data to contextualize these specific concerns and to understand their associated clinical factors. Our objective was to identify EEG abnormalities present in patients with SARS-CoV-2, and to determine whether they reflect new or preexisting brain pathology.We studied a consecutive series of hospitalized patients with SARS-CoV-2 who received an EEG, obtained using tailored safety protocols. Data from EEG reports and clinical records were analyzed to identify EEG abnormalities and possible clinical associations, including neurologic symptoms, new or preexisting brain pathology, and sedation practices.We identified 37 patients with SARS-CoV-2 who underwent EEG, of whom 14 had epileptiform findings (38%). Patients with epileptiform findings were more likely to have preexisting brain pathology (6/14, 43%) than patients without epileptiform findings (2/23, 9%; p = 0.042). There were no clear differences in rates of acute brain pathology. One case of nonconvulsive status epilepticus was captured, but was not clearly a direct consequence of SARS-CoV-2. Abnormalities of background rhythms were common, as may be seen in systemic illness, and in part associated with recent sedation (p = 0.022).Epileptiform abnormalities were common in patients with SARS-CoV-2 referred for EEG, but particularly in the context of preexisting brain pathology and sedation. These findings suggest that neurologic manifestations during SARS-CoV-2 infection may not solely relate to the infection itself, but rather may also reflect patients' broader, preexisting neurologic vulnerabilities.

  View details for DOI 10.1177/1941874420972237

  View details for PubMedID 34163546

  View details for PubMedCentralID PMC8182395

• Application of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations. PloS one MacKay, E. J., Stubna, M. D., Chivers, C., Draugelis, M. E., Hanson, W. J., Desai, N. D., Groeneveld, P. W. 2021; 16 (6): e0252585

  Abstract

  This study aimed to develop and validate a claims-based, machine learning algorithm to predict clinical outcomes across both medical and surgical patient populations.This retrospective, observational cohort study, used a random 5% sample of 770,777 fee-for-service Medicare beneficiaries with an inpatient hospitalization between 2009-2011. The machine learning algorithms tested included: support vector machine, random forest, multilayer perceptron, extreme gradient boosted tree, and logistic regression. The extreme gradient boosted tree algorithm outperformed the alternatives and was the machine learning method used for the final risk model. Primary outcome was 30-day mortality. Secondary outcomes were: rehospitalization, and any of 23 adverse clinical events occurring within 30 days of the index admission date.The machine learning algorithm performance was evaluated by both the area under the receiver operating curve (AUROC) and Brier Score. The risk model demonstrated high performance for prediction of: 30-day mortality (AUROC = 0.88; Brier Score = 0.06), and 17 of the 23 adverse events (AUROC range: 0.80-0.86; Brier Score range: 0.01-0.05). The risk model demonstrated moderate performance for prediction of: rehospitalization within 30 days (AUROC = 0.73; Brier Score: = 0.07) and six of the 23 adverse events (AUROC range: 0.74-0.79; Brier Score range: 0.01-0.02). The machine learning risk model performed comparably on a second, independent validation dataset, confirming that the risk model was not overfit.We have developed and validated a robust, claims-based, machine learning risk model that is applicable to both medical and surgical patient populations and demonstrates comparable predictive accuracy to existing risk models.

  View details for DOI 10.1371/journal.pone.0252585

  View details for PubMedID 34081720

  View details for PubMedCentralID PMC8174683

• Emergent Admissions to the Epilepsy Monitoring Unit in the Setting of COVID-19 Pandemic-related, State-mandated Restrictions: Clinical Decision Making and Outcomes. The Neurodiagnostic journal Zepeda, R., Lee, Y., Agostini, M., Alick Lindstrom, S., Dave, H., Dieppa, M., Ding, K., Doyle, A., Harvey, J., Hays, R., Perven, G., Podkorytova, I., Das, R. R. 2021; 61 (2): 95-103

  Abstract

  Due to the coronavirus disease 2019 (COVID-19) pandemic, the state of Texas-limited elective procedures to conserve beds and personal protective equipment (PPE); therefore, between March 22 and May 18, 2020, admission to the epilepsy monitoring unit (EMU) was limited only to urgent and emergent cases. We evaluated clinical characteristics and outcomes of these patients who were admitted to the EMU. Nineteen patients were admitted (one patient twice) with average age of 36.26 years (11 female) and average length of stay 3 days (range: 2-9 days). At least one event was captured on continuous EEG (cEEG) and video monitoring in all 20 admissions (atypical in one). One patient had both epileptic (ES) and psychogenic non-epileptic seizures (PNES) while 10 had PNES and 9 had ES. In 8 of 9 patients with ES, medications were changed, while in 5 patients with PNES, anti-epileptic drugs (AED) were stopped; the remaining 5 were not on medications. Of the 14 patients who had seen an epileptologist pre-admission, 13 (or 93%) had their diagnosis confirmed by EMU stay; a statistically significant finding. While typically an elective admission, in the setting of the COVID-19 pandemic, urgent and emergent EMU admissions were required for increased seizure or event frequency. In the vast majority of patients (13 of 19), admission lead to medication changes to either better control seizures or to change therapeutics as appropriate when PNES was identified.

  View details for DOI 10.1080/21646821.2021.1918512

  View details for PubMedID 34110971

• Development and Prospective Validation of a Deep Learning Algorithm for Predicting Need for Mechanical Ventilation. Chest Shashikumar, S. P., Wardi, G., Paul, P., Carlile, M., Brenner, L. N., Hibbert, K. A., North, C. M., Mukerji, S. S., Robbins, G. K., Shao, Y. P., Westover, M. B., Nemati, S., Malhotra, A. 2021; 159 (6): 2264-2273

  Abstract

  Objective and early identification of hospitalized patients, and particularly those with novel coronavirus disease 2019 (COVID-19), who may require mechanical ventilation (MV) may aid in delivering timely treatment.Can a transparent deep learning (DL) model predict the need for MV in hospitalized patients and those with COVID-19 up to 24 h in advance?We trained and externally validated a transparent DL algorithm to predict the future need for MV in hospitalized patients, including those with COVID-19, using commonly available data in electronic health records. Additionally, commonly used clinical criteria (heart rate, oxygen saturation, respiratory rate, Fio2, and pH) were used to assess future need for MV. Performance of the algorithm was evaluated using the area under receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value.We obtained data from more than 30,000 ICU patients (including more than 700 patients with COVID-19) from two academic medical centers. The performance of the model with a 24-h prediction horizon at the development and validation sites was comparable (AUC, 0.895 vs 0.882, respectively), providing significant improvement over traditional clinical criteria (P < .001). Prospective validation of the algorithm among patients with COVID-19 yielded AUCs in the range of 0.918 to 0.943.A transparent deep learning algorithm improves on traditional clinical criteria to predict the need for MV in hospitalized patients, including in those with COVID-19. Such an algorithm may help clinicians to optimize timing of tracheal intubation, to allocate resources and staff better, and to improve patient care.

  View details for DOI 10.1016/j.chest.2020.12.009

  View details for PubMedID 33345948

  View details for PubMedCentralID PMC8027289

• Responsive neurostimulation for focal motor status epilepticus ANNALS OF CLINICAL AND TRANSLATIONAL NEUROLOGY Yang, J. C., Harid, N. M., Nascimento, F. A., Kokkinos, V., Shaughnessy, A., Lam, A. D., Westover, M., Leslie-Mazwi, T. M., Hochberg, L. R., Rosenthal, E. S., Cole, A. J., Richardson, R. M., Cash, S. S. 2021; 8 (6): 1353-1361

  Abstract

  No clear evidence-based treatment paradigm currently exists for refractory and super-refractory status epilepticus, which can result in significant mortality and morbidity. While patients are typically treated with antiepileptic drugs and anesthetics, neurosurgical neuromodulation techniques can also be considered. We present a novel case in which responsive neurostimulation was used to effectively treat a patient who had developed super-refractory status epilepticus, later consistent with epilepsia partialis continua, that was refractory to antiepileptic drugs, immunomodulatory therapies, and transcranial magnetic stimulation. This case demonstrates how regional therapy provided by responsive neurostimulation can be effective in treating super-refractory status epilepticus through neuromodulation of seizure networks.

  View details for DOI 10.1002/acn3.51318

  View details for Web of Science ID 000647466200001

  View details for PubMedID 33955717

  View details for PubMedCentralID PMC8164849

• Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL. IEEE journal of biomedical and health informatics Strodthoff, N., Wagner, P., Schaeffter, T., Samek, W. 2021; 25 (5): 1519-1528

  Abstract

  Electrocardiography (ECG) is a very common, non-invasive diagnostic procedure and its interpretation is increasingly supported by algorithms. The progress in the field of automatic ECG analysis has up to now been hampered by a lack of appropriate datasets for training as well as a lack of well-defined evaluation procedures to ensure comparability of different algorithms. To alleviate these issues, we put forward first benchmarking results for the recently published, freely accessible clinical 12-lead ECG dataset PTB-XL, covering a variety of tasks from different ECG statement prediction tasks to age and sex prediction. Among the investigated deep-learning-based timeseries classification algorithms, we find that convolutional neural networks, in particular resnet- and inception-based architectures, show the strongest performance across all tasks. We find consistent results on the ICBEB2018 challenge ECG dataset and discuss prospects of transfer learning using classifiers pretrained on PTB-XL. These benchmarking results are complemented by deeper insights into the classification algorithm in terms of hidden stratification, model uncertainty and an exploratory interpretability analysis, which provide connecting points for future research on the dataset. Our results emphasize the prospects of deep-learning-based algorithms in the field of ECG analysis, not only in terms of quantitative accuracy but also in terms of clinically equally important further quality metrics such as uncertainty quantification and interpretability. With this resource, we aim to establish the PTB-XL dataset as a resource for structured benchmarking of ECG analysis algorithms and encourage other researchers in the field to join these efforts.

  View details for DOI 10.1109/JBHI.2020.3022989

  View details for PubMedID 32903191

• Rapid eye movement sleep disturbance in patients with refractory epilepsy: A polysomnographic study. Sleep medicine Yeh, W. C., Lai, C. L., Wu, M. N., Lin, H. C., Lee, K. W., Li, Y. S., Hsu, C. Y. 2021; 81: 101-108

  Abstract

  Patients with epilepsy have disrupted sleep architecture and a higher prevalence of sleep disturbance. Moreover, obstructive sleep apnea (OSA) is more common among patients with refractory epilepsy. Few studies have compared subjective sleep quality, sleep architecture, and prevalence of OSA between patients with refractory epilepsy and those with medically controlled epilepsy. Therefore, this study aimed to evaluate the differences in sleep quality, sleep architecture, and prevalence of OSA between patients with refractory epilepsy and patients with medically controlled epilepsy.This retrospective case-control study included 38 patients with refractory epilepsy and 96 patients with medically controlled epilepsy. Sleep parameters and indices of sleep-related breathing disorders were recorded by standard in-laboratory polysomnography. The scores from sleep questionnaires on sleep quality and daytime sleepiness were compared between the two groups.Patients with refractory epilepsy versus medically controlled epilepsy had statistically significantly decreased rapid eye movement (REM) sleep (13.5 ± 6.1% vs. 16.2 ± 6.1%) and longer REM latency (152.2 ± 84.1 min vs. 117.2 ± 61.9 min). Further, no differences were found in the prevalence of sleep-related breathing disorders, subjective sleep quality, prevalence of daytime sleepiness, and quality of life. Although not statistically significant, patients with refractory epilepsy have a lower rate of OSA compared with those with medically controlled epilepsy (21.1% vs. 30.2%).Patients with refractory epilepsy had more disrupted REM sleep regulation than those with medically controlled epilepsy. Although patients with epilepsy have a higher risk of OSA, in this study patients with refractory epilepsy were not susceptible to OSA.

  View details for DOI 10.1016/j.sleep.2021.02.007

  View details for PubMedID 33647761

• Algorithm for automatic detection of self-similarity and prediction of residual central respiratory events during continuous positive airway pressure. Sleep Oppersma, E., Ganglberger, W., Sun, H., Thomas, R. J., Westover, M. B. 2021; 44 (4)

  Abstract

  Sleep-disordered breathing is a significant risk factor for cardiometabolic and neurodegenerative diseases. High loop gain (HLG) is a driving mechanism of central sleep apnea or periodic breathing. This study presents a computational approach that identifies "expressed/manifest" HLG via a cyclical self-similarity feature in effort-based respiration signals.Working under the assumption that HLG increases the risk of residual central respiratory events during continuous positive airway pressure (CPAP), the full night similarity, computed during diagnostic non-CPAP polysomnography (PSG), was used to predict residual central events during CPAP (REC), which we defined as central apnea index (CAI) higher than 10. Central apnea labels are obtained both from manual scoring by sleep technologists and from an automated algorithm developed for this study. The Massachusetts General Hospital sleep database was used, including 2466 PSG pairs of diagnostic and CPAP titration PSG recordings.Diagnostic CAI based on technologist labels predicted REC with an area under the curve (AUC) of 0.82 ± 0.03. Based on automatically generated labels, the combination of full night similarity and automatically generated CAI resulted in an AUC of 0.85 ± 0.02. A subanalysis was performed on a population with technologist-labeled diagnostic CAI higher than 5. Full night similarity predicted REC with an AUC of 0.57 ± 0.07 for manual and 0.65 ± 0.06 for automated labels.The proposed self-similarity feature, as a surrogate estimate of expressed respiratory HLG and computed from easily accessible effort signals, can detect periodic breathing regardless of admixed obstructive features such as flow limitation and can aid the prediction of REC.

  View details for DOI 10.1093/sleep/zsaa215

  View details for PubMedID 33057718

  View details for PubMedCentralID PMC8631077

• Clinical, Imaging, and Lab Correlates of Severe COVID-19 Leukoencephalopathy AMERICAN JOURNAL OF NEURORADIOLOGY Rapalino, O., Pourvaziri, A., Maher, M., Jaramillo-Cardoso, A., Edlow, B. L., Conklin, J., Huang, S., Westover, B., Romero, J. M., Halpern, E., Gupta, R., Pomerantz, S., Schaefer, P., Gonzalez, R. G., Mukerji, S. S., Lev, M. H. 2021; 42 (4): 632-638

  Abstract

  Patients infected with the Severe Acute Respiratory Syndrome coronavirus 2 (SARS-CoV-2) can develop a spectrum of neurological disorders, including a leukoencephalopathy of variable severity. Our aim was to characterize imaging, lab, and clinical correlates of severe coronavirus disease 2019 (COVID-19) leukoencephalopathy, which may provide insight into the SARS-CoV-2 pathophysiology.Twenty-seven consecutive patients positive for SARS-CoV-2 who had brain MR imaging following intensive care unit admission were included. Seven (7/27, 26%) developed an unusual pattern of "leukoencephalopathy with reduced diffusivity" on diffusion-weighted MR imaging. The remaining patients did not exhibit this pattern. Clinical and laboratory indices, as well as neuroimaging findings, were compared between groups.The reduced-diffusivity group had a significantly higher body mass index (36 versus 28 kg/m2, P < .01). Patients with reduced diffusivity trended toward more frequent acute renal failure (7/7, 100% versus 9/20, 45%; P = .06) and lower estimated glomerular filtration rate values (49 versus 85 mL/min; P = .06) at the time of MRI. Patients with reduced diffusivity also showed lesser mean values of the lowest hemoglobin levels (8.1 versus 10.2 g/dL, P < .05) and higher serum sodium levels (147 versus 139 mmol/L, P = .04) within 24 hours before MR imaging. The reduced-diffusivity group showed a striking and highly reproducible distribution of confluent, predominantly symmetric, supratentorial, and middle cerebellar peduncular white matter lesions (P < .001).Our findings highlight notable correlations between severe COVID-19 leukoencephalopathy with reduced diffusivity and obesity, acute renal failure, mild hypernatremia, anemia, and an unusual brain MR imaging white matter lesion distribution pattern. Together, these observations may shed light on possible SARS-CoV-2 pathophysiologic mechanisms associated with leukoencephalopathy, including borderzone ischemic changes, electrolyte transport disturbances, and silent hypoxia in the setting of the known cytokine storm syndrome that accompanies severe COVID-19.

  View details for DOI 10.3174/ajnr.A6966

  View details for Web of Science ID 000640547900011

  View details for PubMedID 33414226

  View details for PubMedCentralID PMC8040983

• Electroencephalographic Abnormalities are Common in COVID-19 and are Associated with Outcomes ANNALS OF NEUROLOGY Lin, L., Al-Faraj, A., Ayub, N., Bravo, P., Das, S., Ferlini, L., Karakis, I., Lee, J., Mukerji, S. S., Newey, C. R., Pathmanathan, J., Abdennadher, M., Casassa, C., Gaspard, N., Goldenholz, D. M., Gilmore, E. J., Jing, J., Kim, J. A., Kimchi, E. Y., Ladha, H. S., Tobochnik, S., Zafar, S., Hirsch, L. J., Westover, M., Shafi, M. M. 2021; 89 (5): 872-883

  Abstract

  The aim was to determine the prevalence and risk factors for electrographic seizures and other electroencephalographic (EEG) patterns in patients with Coronavirus disease 2019 (COVID-19) undergoing clinically indicated continuous electroencephalogram (cEEG) monitoring and to assess whether EEG findings are associated with outcomes.We identified 197 patients with COVID-19 referred for cEEG at 9 participating centers. Medical records and EEG reports were reviewed retrospectively to determine the incidence of and clinical risk factors for seizures and other epileptiform patterns. Multivariate Cox proportional hazards analysis assessed the relationship between EEG patterns and clinical outcomes.Electrographic seizures were detected in 19 (9.6%) patients, including nonconvulsive status epilepticus (NCSE) in 11 (5.6%). Epileptiform abnormalities (either ictal or interictal) were present in 96 (48.7%). Preceding clinical seizures during hospitalization were associated with both electrographic seizures (36.4% in those with vs 8.1% in those without prior clinical seizures, odds ratio [OR] 6.51, p = 0.01) and NCSE (27.3% vs 4.3%, OR 8.34, p = 0.01). A pre-existing intracranial lesion on neuroimaging was associated with NCSE (14.3% vs 3.7%; OR 4.33, p = 0.02). In multivariate analysis of outcomes, electrographic seizures were an independent predictor of in-hospital mortality (hazard ratio [HR] 4.07 [1.44-11.51], p < 0.01). In competing risks analysis, hospital length of stay increased in the presence of NCSE (30 day proportion discharged with vs without NCSE: HR 0.21 [0.03-0.33] vs 0.43 [0.36-0.49]).This multicenter retrospective cohort study demonstrates that seizures and other epileptiform abnormalities are common in patients with COVID-19 undergoing clinically indicated cEEG and are associated with adverse clinical outcomes. ANN NEUROL 2021;89:872-883.

  View details for DOI 10.1002/ana.26060

  View details for Web of Science ID 000631883100001

  View details for PubMedID 33704826

  View details for PubMedCentralID PMC8104061

• Slow-Wave Sleep and MRI Markers of Brain Aging in a Community-Based Sample. Neurology Baril, A. A., Beiser, A. S., Mysliwiec, V., Sanchez, E., DeCarli, C. S., Redline, S., Gottlieb, D. J., Maillard, P., Romero, J. R., Satizabal, C. L., Zucker, J. M., Seshadri, S., Pase, M. P., Himali, J. J. 2021; 96 (10): e1462-e1469

  Abstract

  To test the hypothesis that reduced slow-wave sleep, or N3 sleep, which is thought to underlie the restorative functions of sleep, is associated with MRI markers of brain aging, we evaluated this relationship in the community-based Framingham Heart Study Offspring cohort using polysomnography and brain MRI.We studied 492 participants (age 58.8 ± 8.8 years, 49.4% male) free of neurological diseases who completed a brain MRI scan and in-home overnight polysomnography to assess slow-wave sleep (absolute duration and percentage of total sleep). Volumes of total brain, total cortical, frontal cortical, subcortical gray matter, hippocampus, and white matter hyperintensities were investigated as a percentage of intracranial volume, and the presence of covert brain infarcts was evaluated. Linear and logistic regression models were adjusted for age, age squared, sex, time interval between polysomnography and MRI (3.3 ± 1.0 years), APOE ε4 carrier status, stroke risk factors, sleeping pill use, body mass index, and depression.Less slow-wave sleep was associated with lower cortical brain volume (absolute duration, β [standard error] = 0.20 [0.08], p = 0.015; percentage, 0.16 [0.08], p = 0.044), lower subcortical brain volume (percentage, 0.03 [0.02], p = 0.034), and higher white matter hyperintensities volume (absolute duration, -0.12 [0.05], p = 0.010; percentage, -0.10 [0.04], p = 0.033). Slow-wave sleep duration was not associated with hippocampal volume or the presence of covert brain infarcts.Loss of slow-wave sleep might facilitate accelerated brain aging, as evidence by its association with MRI markers suggestive of brain atrophy and injury. Alternatively, subtle injuries and accelerated aging might reduce the ability of the brain to produce slow-wave sleep.

  View details for DOI 10.1212/WNL.0000000000011377

  View details for PubMedID 33361258

  View details for PubMedCentralID PMC8055313

• DDESVSFS: A simple, rapid and comprehensive screening tool for the Differential Diagnosis of Epileptic Seizures VS Functional Seizures. Epilepsy research Janocko, N. J., Jing, J., Fan, Z., Teagarden, D. L., Villarreal, H. K., Morton, M. L., Groover, O., Loring, D. W., Drane, D. L., Westover, M. B., Karakis, I. 2021; 171: 106563

  Abstract

  Functional seizures (FS) are often misclassified as epileptic seizures (ES). This study aimed to create an easy to use but comprehensive screening tool to guide further evaluation of patients presenting with this diagnostic dilemma.Demographic, clinical and diagnostic data were collected on patients admitted for video-EEG monitoring for clarification of their diagnosis. Upon discharge, patients were classified as having ES vs FS. Using the collected characteristics and video-EEG diagnosis, we created a multivariable logistic regression model to identify predictors of ES. Then, we trained an integer-coefficient model with the most frequently selected predictors, creating a pointing system coined DDESVSFS, with scores ranging from -17 to +8 points.43 patients with FS and 165 patients with ES were recruited. In the final integer-coefficient model, 8 predictors were identified as significant in differentiating ES from FS: normal electroencephalogram (-3 points), predisposing factors for FS (-3 points), increased number of comorbidities (-3 points), semiology suggestive of FS (-4 points), increased seizure frequency (-4 points), longer disease duration (+3 points), antiepileptic polypharmacy (+2 points) and compliance with antiepileptic drugs (+3 points). Cumulative scores of ≤ -9 points carried <5% predictive value for ES, while cumulative scores of ≥ -1 points carried >95% predictive value. The model performed well (AUC: 0.923, sensitivity: 0.945, specificity: 0.698).We propose DDESVSFS as a simple, rapid and comprehensive prediction score for the Differential Diagnosis of Epileptic Seizures VS Functional Seizures. Large prospective studies are needed to evaluate its utility in clinical practice.

  View details for DOI 10.1016/j.eplepsyres.2021.106563

  View details for PubMedID 33517166

  View details for PubMedCentralID PMC8092190

• Susceptibility-weighted imaging reveals cerebral microvascular injury in severe COVID-19. Journal of the neurological sciences Conklin, J., Frosch, M. P., Mukerji, S. S., Rapalino, O., Maher, M. D., Schaefer, P. W., Lev, M. H., Gonzalez, R. G., Das, S., Champion, S. N., Magdamo, C., Sen, P., Harrold, G. K., Alabsi, H., Normandin, E., Shaw, B., Lemieux, J. E., Sabeti, P. C., Branda, J. A., Brown, E. N., Westover, M. B., Huang, S. Y., Edlow, B. L. 2021; 421: 117308

  Abstract

  We evaluated the incidence, distribution, and histopathologic correlates of microvascular brain lesions in patients with severe COVID-19. Sixteen consecutive patients admitted to the intensive care unit with severe COVID-19 undergoing brain MRI for evaluation of coma or neurologic deficits were retrospectively identified. Eleven patients had punctate susceptibility-weighted imaging (SWI) lesions in the subcortical and deep white matter, eight patients had >10 SWI lesions, and four patients had lesions involving the corpus callosum. The distribution of SWI lesions was similar to that seen in patients with hypoxic respiratory failure, sepsis, and disseminated intravascular coagulation. Brain autopsy in one patient revealed that SWI lesions corresponded to widespread microvascular injury, characterized by perivascular and parenchymal petechial hemorrhages and microscopic ischemic lesions. Collectively, these radiologic and histopathologic findings add to growing evidence that patients with severe COVID-19 are at risk for multifocal microvascular hemorrhagic and ischemic lesions in the subcortical and deep white matter.

  View details for DOI 10.1016/j.jns.2021.117308

  View details for PubMedID 33497950

  View details for PubMedCentralID PMC7832284

• CoVA: An Acuity Score for Outpatient Screening that Predicts Coronavirus Disease 2019 Prognosis. The Journal of infectious diseases Sun, H., Jain, A., Leone, M. J., Alabsi, H. S., Brenner, L. N., Ye, E., Ge, W., Shao, Y. P., Boutros, C. L., Wang, R., Tesh, R. A., Magdamo, C., Collens, S. I., Ganglberger, W., Bassett, I. V., Meigs, J. B., Kalpathy-Cramer, J., Li, M. D., Chu, J. T., Dougan, M. L., Stratton, L. W., Rosand, J., Fischl, B., Das, S., Mukerji, S. S., Robbins, G. K., Westover, M. B. 2021; 223 (1): 38-46

  Abstract

  We sought to develop an automatable score to predict hospitalization, critical illness, or death for patients at risk for coronavirus disease 2019 (COVID-19) presenting for urgent care.We developed the COVID-19 Acuity Score (CoVA) based on a single-center study of adult outpatients seen in respiratory illness clinics or the emergency department. Data were extracted from the Partners Enterprise Data Warehouse, and split into development (n = 9381, 7 March-2 May) and prospective (n = 2205, 3-14 May) cohorts. Outcomes were hospitalization, critical illness (intensive care unit or ventilation), or death within 7 days. Calibration was assessed using the expected-to-observed event ratio (E/O). Discrimination was assessed by area under the receiver operating curve (AUC).In the prospective cohort, 26.1%, 6.3%, and 0.5% of patients experienced hospitalization, critical illness, or death, respectively. CoVA showed excellent performance in prospective validation for hospitalization (expected-to-observed ratio [E/O]: 1.01; AUC: 0.76), for critical illness (E/O: 1.03; AUC: 0.79), and for death (E/O: 1.63; AUC: 0.93). Among 30 predictors, the top 5 were age, diastolic blood pressure, blood oxygen saturation, COVID-19 testing status, and respiratory rate.CoVA is a prospectively validated automatable score for the outpatient setting to predict adverse events related to COVID-19 infection.

  View details for DOI 10.1093/infdis/jiaa663

  View details for PubMedID 33098643

  View details for PubMedCentralID PMC7665643

• Rapid annotation of seizures and interictal-ictal-injury continuum EEG patterns JOURNAL OF NEUROSCIENCE METHODS Jing, J., D'Angremont, E., Zafar, S., Rosenthal, E. S., Tabaeizadeh, M., Ebrahim, S., Dauwels, J., Westover, M. 2021; 347: 108956

  Abstract

  Manual annotation of seizures and interictal-ictal-injury continuum (IIIC) patterns in continuous EEG (cEEG) recorded from critically ill patients is a time-intensive process for clinicians and researchers. In this study, we evaluated the accuracy and efficiency of an automated clustering method to accelerate expert annotation of cEEG.We learned a local dictionary from 97 ICU patients by applying k-medoids clustering to 592 features in the time and frequency domains. We utilized changepoint detection (CPD) to segment the cEEG recordings. We then computed a bag-of-words (BoW) representation for each segment. We further clustered the segments by affinity propagation. EEG experts scored the resulting clusters for each patient by labeling only the cluster medoids. We trained a random forest classifier to assess validity of the clusters.Mean pairwise agreement of 62.6% using this automated method was not significantly different from interrater agreements using manual labeling (63.8%), demonstrating the validity of the method. We also found that it takes experts using our method 5.31 ± 4.44 min to label the 30.19 ± 3.84 h of cEEG data, more than 45 times faster than unaided manual review, demonstrating efficiency.Previous studies of EEG data labeling have generally yielded similar human expert interrater agreements, and lower agreements with automated methods.Our results suggest that long EEG recordings can be rapidly annotated by experts many times faster than unaided manual review through the use of an advanced clustering method.

  View details for DOI 10.1016/j.jneumeth.2020.108956

  View details for Web of Science ID 000600848600009

  View details for PubMedID 33099261

  View details for PubMedCentralID PMC7744406

• Night-to-night variability of sleep electroencephalography-based brain age measurements. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Hogan, J., Sun, H., Paixao, L., Westmeijer, M., Sikka, P., Jin, J., Tesh, R., Cardoso, M., Cash, S. S., Akeju, O., Thomas, R., Westover, M. B. 2021; 132 (1): 1-12

  Abstract

  Brain Age Index (BAI), calculated from sleep electroencephalography (EEG), has been proposed as a biomarker of brain health. This study quantifies night-to-night variability of BAI and establishes probability thresholds for inferring underlying brain pathology based on a patient's BAI.86 patients with multiple nights of consecutive EEG recordings were selected from Epilepsy Monitoring Unit patients whose EEGs reported as within normal limits. While EEGs with epileptiform activity were excluded, the majority of patients included in the study had a diagnosis of chronic epilepsy. BAI was calculated for each 12-hour segment of patient data using a previously established algorithm, and the night-to-night variability in BAI was measured.The within-patient night-to-night standard deviation in BAI was 7.5 years. Estimates of BAI derived by averaging over 2, 3, and 4 nights had standard deviations of 4.7, 3.7, and 3.0 years, respectively.Averaging BAI over n nights reduces night-to-night variability of BAI by a factor of n, rendering BAI a more suitable biomarker of brain health at the individual level. A brain age risk lookup table of results provides thresholds above which a patient has a high probability of excess BAI.With increasing ease of EEG acquisition, including wearable technology, BAI has the potential to track brain health and detect deviations from normal physiologic function. The measure of night-to-night variability and how this is reduced by averaging across multiple nights provides a basis for using BAI in patients' homes to identify patients who should undergo further investigation or monitoring.

  View details for DOI 10.1016/j.clinph.2020.09.029

  View details for PubMedID 33248430

  View details for PubMedCentralID PMC7855943

• American Clinical Neurophysiology Society's Standardized Critical Care EEG Terminology: 2021 Version. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Hirsch, L. J., Fong, M. W., Leitinger, M., LaRoche, S. M., Beniczky, S., Abend, N. S., Lee, J. W., Wusthoff, C. J., Hahn, C. D., Westover, M. B., Gerard, E. E., Herman, S. T., Haider, H. A., Osman, G., Rodriguez-Ruiz, A., Maciel, C. B., Gilmore, E. J., Fernandez, A., Rosenthal, E. S., Claassen, J., Husain, A. M., Yoo, J. Y., So, E. L., Kaplan, P. W., Nuwer, M. R., van Putten, M., Sutter, R., Drislane, F. W., Trinka, E., Gaspard, N. 2021; 38 (1): 1–29

  View details for DOI 10.1097/WNP.0000000000000806

  View details for PubMedID 33475321

• Early brain biomarkers of post-traumatic seizures: initial report of the multicentre epilepsy bioinformatics study for antiepileptogenic therapy (EpiBioS4Rx) prospective study. Journal of neurology, neurosurgery, and psychiatry Lutkenhoff, E. S., Shrestha, V., Ruiz Tejeda, J., Real, C., McArthur, D. L., Duncan, D., La Rocca, M., Garner, R., Toga, A. W., Vespa, P. M., Monti, M. M. 2020; 91 (11): 1154-1157

  Abstract

  Traumatic brain injury (TBI) causes early seizures and is the leading cause of post-traumatic epilepsy. We prospectively assessed structural imaging biomarkers differentiating patients who develop seizures secondary to TBI from patients who do not.Multicentre prospective cohort study starting in 2018. Imaging data are acquired around day 14 post-injury, detection of seizure events occurred early (within 1 week) and late (up to 90 days post-TBI).From a sample of 96 patients surviving moderate-to-severe TBI, we performed shape analysis of local volume deficits in subcortical areas (analysable sample: 57 patients; 35 no seizure, 14 early, 8 late) and cortical ribbon thinning (analysable sample: 46 patients; 29 no seizure, 10 early, 7 late). Right hippocampal volume deficit and inferior temporal cortex thinning demonstrated a significant effect across groups. Additionally, the degree of left frontal and temporal pole thinning, and clinical score at the time of the MRI, could differentiate patients experiencing early seizures from patients not experiencing them with 89% accuracy.Although this is an initial report, these data show that specific areas of localised volume deficit, as visible on routine imaging data, are associated with the emergence of seizures after TBI.

  View details for DOI 10.1136/jnnp-2020-322780

  View details for PubMedID 32848013

  View details for PubMedCentralID PMC7572686

• Persistent abnormalities in Rolandic thalamocortical white matter circuits in childhood epilepsy with centrotemporal spikes. Epilepsia Thorn, E. L., Ostrowski, L. M., Chinappen, D. M., Jing, J., Westover, M. B., Stufflebeam, S. M., Kramer, M. A., Chu, C. J. 2020; 61 (11): 2500-2508

  Abstract

  Childhood epilepsy with centrotemporal spikes (CECTS) is a common, focal, transient, developmental epilepsy syndrome characterized by unilateral or bilateral, independent epileptiform spikes in the Rolandic regions of unknown etiology. Given that CECTS presents during a period of dramatic white matter maturation and thatspikes in CECTS are activated during non-rapid eye movement (REM) sleep, we hypothesized that children with CECTS would have aberrant development of white matter connectivity between the thalamus and the Rolandic cortex. We further tested whether Rolandic thalamocortical structural connectivity correlates with spike rate during non-REM sleep.Twenty-three children with CECTS (age = 8-15 years) and 19 controls (age = 7-15 years) underwent 3-T structural and diffusion-weighted magnetic resonance imaging and 72-electrode electroencephalographic recordings. Thalamocortical structural connectivity to Rolandic and non-Rolandic cortices was quantified using probabilistic tractography. Developmental changes in connectivity were compared between groups using bootstrap analyses. Longitudinal analysis was performed in four subjects with 1-year follow-up data. Spike rate was quantified during non-REM sleep using manual and automated techniques and compared to Rolandic connectivity using regression analyses.Children with CECTS had aberrant development of thalamocortical connectivity to the Rolandic cortex compared to controls (P = .01), where the expected increase in connectivity with age was not observed in CECTS. There was no difference in the development of thalamocortical connectivity to non-Rolandic regions between CECTS subjects and controls (P = .19). Subjects with CECTS observed longitudinally had reductions in thalamocortical connectivity to the Rolandic cortex over time. No definite relationship was found between Rolandic connectivity and non-REM spike rate (P > .05).These data provide evidence that abnormal maturation of thalamocortical white matter circuits to the Rolandic cortex is a feature of CECTS. Our data further suggest that the abnormalities in these tracts do not recover, but are increasingly dysmature over time, implicating a permanent but potentially compensatory process contributing to disease resolution.

  View details for DOI 10.1111/epi.16681

  View details for PubMedID 32944938

  View details for PubMedCentralID PMC7722074

• Association of epileptiform abnormalities and seizures in Alzheimer disease. Neurology Lam, A. D., Sarkis, R. A., Pellerin, K. R., Jing, J., Dworetzky, B. A., Hoch, D. B., Jacobs, C. S., Lee, J. W., Weisholtz, D. S., Zepeda, R., Westover, M. B., Cole, A. J., Cash, S. S. 2020; 95 (16): e2259-e2270

  Abstract

  To examine the relationship between scalp EEG biomarkers of hyperexcitability in Alzheimer disease (AD) and to determine how these electric biomarkers relate to the clinical expression of seizures in AD.In this cross-sectional study, we performed 24-hour ambulatory scalp EEGs on 43 cognitively normal elderly healthy controls (HC), 41 participants with early-stage AD with no history or risk factors for epilepsy (AD-NoEp), and 15 participants with early-stage AD with late-onset epilepsy related to AD (AD-Ep). Two epileptologists blinded to diagnosis visually reviewed all EEGs and annotated all potential epileptiform abnormalities. A panel of 9 epileptologists blinded to diagnosis was then surveyed to generate a consensus interpretation of epileptiform abnormalities in each EEG.Epileptiform abnormalities were seen in 53% of AD-Ep, 22% of AD-NoEp, and 4.7% of HC. Specific features of epileptiform discharges, including high frequency, robust morphology, right temporal location, and occurrence during wakefulness and REM, were associated with clinical seizures in AD. Multiple EEG biomarkers concordantly demonstrated a pattern of left temporal lobe hyperexcitability in early stages of AD, whereas clinical seizures in AD were often associated with bitemporal hyperexcitability. Frequent small sharp spikes were specifically associated with epileptiform EEGs and thus identified as a potential biomarker of hyperexcitability in AD.Epileptiform abnormalities are common in AD but not all equivalent. Specific features of epileptiform discharges are associated with clinical seizures in AD. Given the difficulty recognizing clinical seizures in AD, these EEG features could provide guidance on which patients with AD are at high risk for clinical seizures.

  View details for DOI 10.1212/WNL.0000000000010612

  View details for PubMedID 32764101

  View details for PubMedCentralID PMC7713786

• Burst Suppression: Causes and Effects on Mortality in Critical Illness. Neurocritical care Hogan, J., Sun, H., Aboul Nour, H., Jing, J., Tabaeizadeh, M., Shoukat, M., Javed, F., Kassa, S., Edhi, M. M., Bordbar, E., Gallagher, J., Junior, V. M., Ghanta, M., Shao, Y. P., Akeju, O., Cole, A. J., Rosenthal, E. S., Zafar, S., Westover, M. B. 2020; 33 (2): 565-574

  Abstract

  Burst suppression in mechanically ventilated intensive care unit (ICU) patients is associated with increased mortality. However, the relative contributions of propofol use and critical illness itself to burst suppression; of burst suppression, propofol, and critical illness to mortality; and whether preventing burst suppression might reduce mortality, have not been quantified.The dataset contains 471 adults from seven ICUs, after excluding anoxic encephalopathy due to cardiac arrest or intentional burst suppression for therapeutic reasons. We used multiple prediction and causal inference methods to estimate the effects connecting burst suppression, propofol, critical illness, and in-hospital mortality in an observational retrospective study. We also estimated the effects mediated by burst suppression. Sensitivity analysis was used to assess for unmeasured confounding.The expected outcomes in a "counterfactual" randomized controlled trial (cRCT) that assigned patients to mild versus severe illness are expected to show a difference in burst suppression burden of 39%, 95% CI [8-66]%, and in mortality of 35% [29-41]%. Assigning patients to maximal (100%) burst suppression burden is expected to increase mortality by 12% [7-17]% compared to 0% burden. Burst suppression mediates 10% [2-21]% of the effect of critical illness on mortality. A high cumulative propofol dose (1316 mg/kg) is expected to increase burst suppression burden by 6% [0.8-12]% compared to a low dose (284 mg/kg). Propofol exposure has no significant direct effect on mortality; its effect is entirely mediated through burst suppression.Our analysis clarifies how important factors contribute to mortality in ICU patients. Burst suppression appears to contribute to mortality but is primarily an effect of critical illness rather than iatrogenic use of propofol.

  View details for DOI 10.1007/s12028-020-00932-4

  View details for PubMedID 32096120

  View details for PubMedCentralID PMC7483190

• A Theoretical Paradigm for Evaluating Risk-Benefit of Status Epilepticus Treatment. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Amorim, E., McGraw, C. M., Westover, M. B. 2020; 37 (5): 385-392

  Abstract

  Aggressive treatment of status epilepticus with anesthetic drugs can provide rapid seizure control, but it might lead to serious medical complications and worse outcomes. Using a decision analysis approach, this concise review provides a framework for individualized decision making about aggressive and nonaggressive treatment in status epilepticus. The authors propose and review the most relevant parameters guiding the risk-benefit analysis of treatment aggressiveness in status epilepticus and present real-world-based case examples to illustrate how these tools could be used at the bedside and serve to guide future research in refractory status epilepticus treatment.

  View details for DOI 10.1097/WNP.0000000000000753

  View details for PubMedID 32890059

  View details for PubMedCentralID PMC7516305

• Cost-effectiveness analysis of multimodal prognostication in cardiac arrest with EEG monitoring NEUROLOGY Amorim, E., Mo, S. S., Palacios, S., Ghassemi, M. M., Weng, W., Cash, S. S., Bianchi, M. T., Westover, M. 2020; 95 (5): E563-E575

  Abstract

  To determine cost-effectiveness parameters for EEG monitoring in cardiac arrest prognostication.We conducted a cost-effectiveness analysis to estimate the cost per quality-adjusted life-year (QALY) gained by adding continuous EEG monitoring to standard cardiac arrest prognostication using the American Academy of Neurology Practice Parameter (AANPP) decision algorithm: neurologic examination, somatosensory evoked potentials, and neuron-specific enolase. We explored lifetime cost-effectiveness in a closed system that incorporates revenue back into the medical system (return) from payers who survive a cardiac arrest with good outcome and contribute to the health system during the remaining years of life. Good outcome was defined as a Cerebral Performance Category (CPC) score of 1-2 and poor outcome as CPC of 3-5.An improvement in specificity for poor outcome prediction of 4.2% would be sufficient to make continuous EEG monitoring cost-effective (baseline AANPP specificity = 83.9%). In sensitivity analysis, the effect of increased sensitivity on the cost-effectiveness of EEG depends on the utility (u) assigned to a poor outcome. For patients who regard surviving with a poor outcome (CPC 3-4) worse than death (u = -0.34), an increased sensitivity for poor outcome prediction of 13.8% would make AANPP + EEG monitoring cost-effective (baseline AANPP sensitivity = 76.3%). In the closed system, an improvement in sensitivity of 1.8% together with an improvement in specificity of 3% was sufficient to make AANPP + EEG monitoring cost-effective, assuming lifetime return of 50% (USD $70,687).Incorporating continuous EEG monitoring into cardiac arrest prognostication is cost-effective if relatively small improvements in sensitivity and specificity are achieved.

  View details for DOI 10.1212/WNL.0000000000009916

  View details for Web of Science ID 000582379300020

  View details for PubMedID 32661097

  View details for PubMedCentralID PMC7455344

• Improved tracking of sevoflurane anesthetic states with drug-specific machine learning models. Journal of neural engineering Kashkooli, K., Polk, S. L., Hahm, E. Y., Murphy, J., Ethridge, B. R., Gitlin, J., Ibala, R., Mekonnen, J., Pedemonte, J. C., Sun, H., Westover, M. B., Barbieri, R., Akeju, O., Chamadia, S. 2020; 17 (4): 046020

  Abstract

  The ability to monitor anesthetic states using automated approaches is expected to reduce inaccurate drug dosing and side-effects. Commercially available anesthetic state monitors perform poorly when ketamine is administered as an anesthetic-analgesic adjunct. Poor performance is likely because the models underlying these monitors are not optimized for the electroencephalogram (EEG) oscillations that are unique to the co-administration of ketamine.In this work, we designed two k-nearest neighbors algorithms for anesthetic state prediction.The first algorithm was trained only on sevoflurane EEG data, making it sevoflurane-specific. This algorithm enabled discrimination of the sevoflurane general anesthesia (GA) state from sedated and awake states (true positive rate = 0.87, [95% CI, 0.76, 0.97]). However, it did not enable discrimination of the sevoflurane-plus-ketamine GA state from sedated and awake states (true positive rate = 0.43, [0.19, 0.67]). In our second algorithm, we implemented a cross drug training paradigm by including both sevoflurane and sevoflurane-plus-ketamine EEG data in our training set. This algorithm enabled discrimination of the sevoflurane-plus-ketamine GA state from sedated and awake states (true positive rate = 0.91, [0.84, 0.98]).Instead of a one-algorithm-fits-all-drugs approach to anesthetic state monitoring, our results suggest that drug-specific models are necessary to improve the performance of automated anesthetic state monitors.

  View details for DOI 10.1088/1741-2552/ab98da

  View details for PubMedID 32485685

  View details for PubMedCentralID PMC7540939

• Electroencephalogram Burst-suppression during Cardiopulmonary Bypass in Elderly Patients Mediates Postoperative Delirium. Anesthesiology Pedemonte, J. C., Plummer, G. S., Chamadia, S., Locascio, J. J., Hahm, E., Ethridge, B., Gitlin, J., Ibala, R., Mekonnen, J., Colon, K. M., Westover, M. B., D'Alessandro, D. A., Tolis, G., Houle, T., Shelton, K. T., Qu, J., Akeju, O. 2020; 133 (2): 280-292

  Abstract

  Intraoperative burst-suppression is associated with postoperative delirium. Whether this association is causal remains unclear. Therefore, the authors investigated whether burst-suppression during cardiopulmonary bypass (CPB) mediates the effects of known delirium risk factors on postoperative delirium.This was a retrospective cohort observational substudy of the Minimizing ICU [intensive care unit] Neurological Dysfunction with Dexmedetomidine-induced Sleep (MINDDS) trial. The authors analyzed data from patients more than 60 yr old undergoing cardiac surgery (n = 159). Univariate and multivariable regression analyses were performed to assess for associations and enable causal inference. Delirium risk factors were evaluated using the abbreviated Montreal Cognitive Assessment and Patient-Reported Outcomes Measurement Information System questionnaires for applied cognition, physical function, global health, sleep, and pain. The authors also analyzed electroencephalogram data (n = 141).The incidence of delirium in patients with CPB burst-suppression was 25% (15 of 60) compared with 6% (5 of 81) in patients without CPB burst-suppression. In univariate analyses, age (odds ratio, 1.08 [95% CI, 1.03 to 1.14]; P = 0.002), lowest CPB temperature (odds ratio, 0.79 [0.66 to 0.94]; P = 0.010), alpha power (odds ratio, 0.65 [0.54 to 0.80]; P < 0.001), and physical function (odds ratio, 0.95 [0.91 to 0.98]; P = 0.007) were associated with CPB burst-suppression. In separate univariate analyses, age (odds ratio, 1.09 [1.02 to 1.16]; P = 0.009), abbreviated Montreal Cognitive Assessment (odds ratio, 0.80 [0.66 to 0.97]; P = 0.024), alpha power (odds ratio, 0.75 [0.59 to 0.96]; P = 0.025), and CPB burst-suppression (odds ratio, 3.79 [1.5 to 9.6]; P = 0.005) were associated with delirium. However, only physical function (odds ratio, 0.96 [0.91 to 0.99]; P = 0.044), lowest CPB temperature (odds ratio, 0.73 [0.58 to 0.88]; P = 0.003), and electroencephalogram alpha power (odds ratio, 0.61 [0.47 to 0.76]; P < 0.001) were retained as predictors in the burst-suppression multivariable model. Burst-suppression (odds ratio, 4.1 [1.5 to 13.7]; P = 0.012) and age (odds ratio, 1.07 [0.99 to 1.15]; P = 0.090) were retained as predictors in the delirium multivariable model. Delirium was associated with decreased electroencephalogram power from 6.8 to 24.4 Hertz.The inference from the present study is that CPB burst-suppression mediates the effects of physical function, lowest CPB temperature, and electroencephalogram alpha power on delirium.

  View details for DOI 10.1097/ALN.0000000000003328

  View details for PubMedID 32349072

  View details for PubMedCentralID PMC7365754

• A New Neural Mass Model Driven Method and Its Application in Early Epileptic Seizure Detection. IEEE transactions on bio-medical engineering Song, J. L., Li, Q., Zhang, B., Westover, M. B., Zhang, R. 2020; 67 (8): 2194-2205

  Abstract

  Despite numerous neural computational models proposed to explain physiological and pathological mechanisms of brain activity, a large gap remains between theory and application of the models. Building on the successful application of data-driven methods in epileptic seizure detection, we aim to build a bridge between data and models in this paper.We first propose a novel model-driven seizure detection method based on dynamic features in epileptic EEGs, where the rationale for dynamic features in epileptic EEGs can be clarified in theory by characterizing the variation of parameters of the model. Then we apply the proposed D&F-model-driven method to the problem of early epileptic seizure detection, where the evolution of model parameters selected and optimized by the proposed method is measured and used to detect the starting point of the seizure.Numerical results on two open EEG databases demonstrate that our proposed method does a good job of early epileptic seizure detection. The average detection sensitivity, false positive rate and early detection period attain 100%, 0.1/h, and 7.1 s respectively.This paper provides a strategy to characterize EEG signals using a NMM-related method and the model parameters optimized by real EEG may then serve as features in their own right for early seizure detection.An useful attempt to early detect epileptic seizures by combining the neural mass model with data analysis.

  View details for DOI 10.1109/TBME.2019.2957392

  View details for PubMedID 31804924

  View details for PubMedCentralID PMC9371613

• MRI-EEG correlation for outcome prediction in postanoxic myoclonus A multicenter study NEUROLOGY Beuchat, I., Sivaraju, A., Amorim, E., Gilmore, E. J., Dunet, V., Rossetti, A. O., Westover, M., Hsu, L., Scirica, B. M., Silva, D., Tang, K., Lee, J. 2020; 95 (4): E335-E341

  Abstract

  To examine the prognostic ability of the combination of EEG and MRI in identifying patients with good outcome in postanoxic myoclonus (PAM) after cardiac arrest (CA).Adults with PAM who had an MRI within 20 days after CA were identified in 4 prospective CA registries. The primary outcome measure was coma recovery to command following by hospital discharge. Clinical examination included brainstem reflexes and motor activity. EEG was assessed for best background continuity, reactivity, presence of epileptiform activity, and burst suppression with identical bursts (BSIB). MRI was examined for presence of diffusion restriction or fluid-attenuated inversion recovery changes consistent with anoxic brain injury. A prediction model was developed using optimal combination of variables.Among 78 patients, 11 (14.1%) recovered at discharge and 6 (7.7%) had good outcome (Cerebral Performance Category < 3) at 3 months. Patients who followed commands were more likely to have pupillary and corneal reflexes, flexion or better motor response, EEG continuity and reactivity, no BSIB, and no anoxic injury on MRI. The combined EEG/MRI variable of continuous background and no anoxic changes on MRI was associated with coma recovery at hospital discharge with sensitivity 91% (95% confidence interval [CI], 0.59-1.00), specificity 99% (95% CI, 0.92-1.00), positive predictive value 91% (95% CI, 0.59-1.00), and negative predictive value 99% (95% CI, 0.92-1.00).EEG and MRI are complementary and identify both good and poor outcome in patients with PAM with high accuracy. An MRI should be considered in patients with myoclonus showing continuous or reactive EEGs.

  View details for DOI 10.1212/WNL.0000000000009610

  View details for Web of Science ID 000582378300019

  View details for PubMedID 32482841

  View details for PubMedCentralID PMC7455317

• Cerebral Microvascular Injury in Severe COVID-19. medRxiv : the preprint server for health sciences Conklin, J., Frosch, M. P., Mukerji, S., Rapalino, O., Maher, M., Schaefer, P. W., Lev, M. H., Gonzalez, R. G., Das, S., Champion, S. N., Magdamo, C., Sen, P., Harrold, G. K., Alabsi, H., Normandin, E., Shaw, B., Lemieux, J., Sabeti, P., Branda, J. A., Brown, E. N., Westover, M. B., Huang, S. Y., Edlow, B. L. 2020

  Abstract

  Microvascular lesions are common in patients with severe COVID-19. Radiologic-pathologic correlation in one case suggests a combination of microvascular hemorrhagic and ischemic lesions that may reflect an underlying hypoxic mechanism of injury, which requires validation in larger studies.To determine the incidence, distribution, and clinical and histopathologic correlates of microvascular lesions in patients with severe COVID-19.Observational, retrospective cohort study: March to May 2020.Single academic medical center.Consecutive patients (16) admitted to the intensive care unit with severe COVID-19, undergoing brain MRI for evaluation of coma or focal neurologic deficits.Not applicable.Hypointense microvascular lesions identified by a prototype ultrafast high-resolution susceptibility-weighted imaging (SWI) MRI sequence, counted by two neuroradiologists and categorized by neuroanatomic location. Clinical and laboratory data (most recent measurements before brain MRI). Brain autopsy and cerebrospinal fluid PCR for SARS-CoV 2 in one patient who died from severe COVID-19.Eleven of 16 patients (69%) had punctate and linear SWI lesions in the subcortical and deep white matter, and eight patients (50%) had >10 SWI lesions. In 4/16 patients (25%), lesions involved the corpus callosum. Brain autopsy in one patient revealed that SWI lesions corresponded to widespread microvascular injury, characterized by perivascular and parenchymal petechial hemorrhages and microscopic ischemic lesions.SWI lesions are common in patients with neurological manifestations of severe COVID-19 (coma and focal neurologic deficits). The distribution of lesions is similar to that seen in patients with hypoxic respiratory failure, sepsis, and disseminated intravascular coagulation. Collectively, these radiologic and histopathologic findings suggest that patients with severe COVID-19 are at risk for multifocal microvascular hemorrhagic and ischemic lesions in the subcortical and deep white matter.

  View details for DOI 10.1101/2020.07.21.20159376

  View details for PubMedID 32743599

  View details for PubMedCentralID PMC7386523

• Sleep staging from electrocardiography and respiration with deep learning. Sleep Sun, H., Ganglberger, W., Panneerselvam, E., Leone, M. J., Quadri, S. A., Goparaju, B., Tesh, R. A., Akeju, O., Thomas, R. J., Westover, M. B. 2020; 43 (7)

  Abstract

  Sleep is reflected not only in the electroencephalogram but also in heart rhythms and breathing patterns. We hypothesized that it is possible to accurately stage sleep based on the electrocardiogram (ECG) and respiratory signals.Using a dataset including 8682 polysomnograms, we develop deep neural networks to stage sleep from ECG and respiratory signals. Five deep neural networks consisting of convolutional networks and long- and short-term memory networks are trained to stage sleep using heart and breathing, including the timing of R peaks from ECG, abdominal and chest respiratory effort, and the combinations of these signals.ECG in combination with the abdominal respiratory effort achieved the best performance for staging all five sleep stages with a Cohen's kappa of 0.585 (95% confidence interval ±0.017); and 0.760 (±0.019) for discriminating awake vs. rapid eye movement vs. nonrapid eye movement sleep. Performance is better for younger ages, whereas it is robust for body mass index, apnea severity, and commonly used outpatient medications.Our results validate that ECG and respiratory effort provide substantial information about sleep stages in a large heterogeneous population. This opens new possibilities in sleep research and applications where electroencephalography is not readily available or may be infeasible.

  View details for DOI 10.1093/sleep/zsz306

  View details for PubMedID 31863111

  View details for PubMedCentralID PMC7355395

• Development and Validation of Forecasting Next Reported Seizure Using e-Diaries ANNALS OF NEUROLOGY Goldenholz, D. M., Goldenholz, S. R., Romero, J., Moss, R., Sun, H., Westover, B. 2020; 88 (3): 588-595

  Abstract

  There are no validated methods for predicting the timing of seizures. Using machine learning, we sought to forecast 24-hour risk of self-reported seizure from e-diaries.Data from 5,419 patients on SeizureTracker.com (including seizure count, type, and duration) were split into training (3,806 patients/1,665,215 patient-days) and testing (1,613 patients/549,588 patient-days) sets with no overlapping patients. An artificial intelligence (AI) program, consisting of recurrent networks followed by a multilayer perceptron ("deep learning" model), was trained to produce risk forecasts. Forecasts were made from a sliding window of 3-month diary history for each day of each patient's diary. After training, the model parameters were held constant and the testing set was scored. A rate-matched random (RMR) forecast was compared to the AI. Comparisons were made using the area under the receiver operating characteristic curve (AUC), a measure of binary discrimination performance, and the Brier score, a measure of forecast calibration. The Brier skill score (BSS) measured the improvement of the AI Brier score compared to the benchmark RMR Brier score. Confidence intervals (CIs) on performance statistics were obtained via bootstrapping.The AUC was 0.86 (95% CI = 0.85-0.88) for AI and 0.83 (95% CI = 0.81-0.85) for RMR, favoring AI (p < 0.001). Overall (all patients combined), BSS was 0.27 (95% CI = 0.23-0.31), also favoring AI (p < 0.001).The AI produced a valid forecast superior to a chance forecaster, and provided meaningful forecasts in the majority of patients. Future studies will be needed to quantify the clinical value of these forecasts for patients. ANN NEUROL 2020;88:588-595.

  View details for DOI 10.1002/ana.25812

  View details for Web of Science ID 000546434100001

  View details for PubMedID 32567720

  View details for PubMedCentralID PMC7720795

• Self-reported olfactory loss associates with outpatient clinical course in COVID-19. International forum of allergy & rhinology Yan, C. H., Faraji, F., Prajapati, D. P., Ostrander, B. T., DeConde, A. S. 2020; 10 (7): 821-831

  Abstract

  Rapid spread of the severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2) virus has left many health systems around the world overwhelmed, forcing triaging of scarce medical resources. Identifying indicators of hospital admission for coronavirus disease 2019 (COVID-19) patients early in the disease course could aid the efficient allocation of medical interventions. Self-reported olfactory impairment has recently been recognized as a hallmark of COVID-19 and may be an important predictor of clinical outcome.A retrospective review of all patients presenting to a San Diego Hospital system with laboratory-confirmed positive COVID-19 infection was conducted with evaluation of olfactory and gustatory function and clinical disease course. Univariable and multivariable logistic regression were performed to identify risk factors for hospital admission and anosmia.A total of 169 patients tested positive for COVID-19 disease between March 3 and April 8, 2020. Olfactory and gustatory data were obtained for 128 (75.7%) of 169 subjects, of which 26 (20.1%) of 128 required hospitalization. Admission for COVID-19 was associated with intact sense of smell and taste, increased age, diabetes, and subjective and objective parameters associated with respiratory failure. On adjusted analysis, anosmia was strongly and independently associated with outpatient care (adjusted odds ratio [aOR] 0.09; 95% CI, 0.01-0.74), whereas positive findings of pulmonary infiltrates and/or pleural effusion on chest radiograph (aOR 8.01; 95% CI, 1.12-57.49) was strongly and independently associated with admission.Normosmia is an independent predictor of admission in COVID-19 cases. Smell loss in COVID-19 may be associated with a milder clinical course.

  View details for DOI 10.1002/alr.22592

  View details for PubMedID 32329222

  View details for PubMedCentralID PMC7264572

• Risk prediction of delirium in hospitalized patients using machine learning: An implementation and prospective evaluation study. Journal of the American Medical Informatics Association : JAMIA Jauk, S., Kramer, D., Großauer, B., Rienmüller, S., Avian, A., Berghold, A., Leodolter, W., Schulz, S. 2020; 27 (9): 1383-1392

  Abstract

  Machine learning models trained on electronic health records have achieved high prognostic accuracy in test datasets, but little is known about their embedding into clinical workflows. We implemented a random forest-based algorithm to identify hospitalized patients at high risk for delirium, and evaluated its performance in a clinical setting.Delirium was predicted at admission and recalculated on the evening of admission. The defined prediction outcome was a delirium coded for the recent hospital stay. During 7 months of prospective evaluation, 5530 predictions were analyzed. In addition, 119 predictions for internal medicine patients were compared with ratings of clinical experts in a blinded and nonblinded setting.During clinical application, the algorithm achieved a sensitivity of 74.1% and a specificity of 82.2%. Discrimination on prospective data (area under the receiver-operating characteristic curve = 0.86) was as good as in the test dataset, but calibration was poor. The predictions correlated strongly with delirium risk perceived by experts in the blinded (r = 0.81) and nonblinded (r = 0.62) settings. A major advantage of our setting was the timely prediction without additional data entry.The implemented machine learning algorithm achieved a stable performance predicting delirium in high agreement with expert ratings, but improvement of calibration is needed. Future research should evaluate the acceptance of implemented machine learning algorithms by health professionals.Our study provides new insights into the implementation process of a machine learning algorithm into a clinical workflow and demonstrates its predictive power for delirium.

  View details for DOI 10.1093/jamia/ocaa113

  View details for PubMedID 32968811

  View details for PubMedCentralID PMC7647341

• COVID-19 and Thrombotic or Thromboembolic Disease: Implications for Prevention, Antithrombotic Therapy, and Follow-Up: JACC State-of-the-Art Review. Journal of the American College of Cardiology Bikdeli, B., Madhavan, M. V., Jimenez, D., Chuich, T., Dreyfus, I., Driggin, E., Nigoghossian, C. D., Ageno, W., Madjid, M., Guo, Y., Tang, L. V., Hu, Y., Giri, J., Cushman, M., Quéré, I., Dimakakos, E. P., Gibson, C. M., Lippi, G., Favaloro, E. J., Fareed, J., Caprini, J. A., Tafur, A. J., Burton, J. R., Francese, D. P., Wang, E. Y., Falanga, A., McLintock, C., Hunt, B. J., Spyropoulos, A. C., Barnes, G. D., Eikelboom, J. W., Weinberg, I., Schulman, S., Carrier, M., Piazza, G., Beckman, J. A., Steg, P. G., Stone, G. W., Rosenkranz, S., Goldhaber, S. Z., Parikh, S. A., Monreal, M., Krumholz, H. M., Konstantinides, S. V., Weitz, J. I., Lip, G. Y. 2020; 75 (23): 2950-2973

  Abstract

  Coronavirus disease-2019 (COVID-19), a viral respiratory illness caused by the severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2), may predispose patients to thrombotic disease, both in the venous and arterial circulations, because of excessive inflammation, platelet activation, endothelial dysfunction, and stasis. In addition, many patients receiving antithrombotic therapy for thrombotic disease may develop COVID-19, which can have implications for choice, dosing, and laboratory monitoring of antithrombotic therapy. Moreover, during a time with much focus on COVID-19, it is critical to consider how to optimize the available technology to care for patients without COVID-19 who have thrombotic disease. Herein, the authors review the current understanding of the pathogenesis, epidemiology, management, and outcomes of patients with COVID-19 who develop venous or arterial thrombosis, of those with pre-existing thrombotic disease who develop COVID-19, or those who need prevention or care for their thrombotic disease during the COVID-19 pandemic.

  View details for DOI 10.1016/j.jacc.2020.04.031

  View details for PubMedID 32311448

  View details for PubMedCentralID PMC7164881

• COVID-19 and its implications for thrombosis and anticoagulation. Blood Connors, J. M., Levy, J. H. 2020; 135 (23): 2033-2040

  Abstract

  Severe acute respiratory syndrome coronavirus 2, coronavirus disease 2019 (COVID-19)-induced infection can be associated with a coagulopathy, findings consistent with infection-induced inflammatory changes as observed in patients with disseminated intravascular coagulopathy (DIC). The lack of prior immunity to COVID-19 has resulted in large numbers of infected patients across the globe and uncertainty regarding management of the complications that arise in the course of this viral illness. The lungs are the target organ for COVID-19; patients develop acute lung injury that can progress to respiratory failure, although multiorgan failure can also occur. The initial coagulopathy of COVID-19 presents with prominent elevation of D-dimer and fibrin/fibrinogen-degradation products, whereas abnormalities in prothrombin time, partial thromboplastin time, and platelet counts are relatively uncommon in initial presentations. Coagulation test screening, including the measurement of D-dimer and fibrinogen levels, is suggested. COVID-19-associated coagulopathy should be managed as it would be for any critically ill patient, following the established practice of using thromboembolic prophylaxis for critically ill hospitalized patients, and standard supportive care measures for those with sepsis-induced coagulopathy or DIC. Although D-dimer, sepsis physiology, and consumptive coagulopathy are indicators of mortality, current data do not suggest the use of full-intensity anticoagulation doses unless otherwise clinically indicated. Even though there is an associated coagulopathy with COVID-19, bleeding manifestations, even in those with DIC, have not been reported. If bleeding does occur, standard guidelines for the management of DIC and bleeding should be followed.

  View details for DOI 10.1182/blood.2020006000

  View details for PubMedID 32339221

  View details for PubMedCentralID PMC7273827

• Adaptive Sedation Monitoring From EEG in ICU Patients With Online Learning IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING Zheng, W., Sun, H., Akeju, O., Westover, M. 2020; 67 (6): 1696-1706

  Abstract

  Sedative medications are routinely administered to provide comfort and facilitate clinical care in critically ill ICU patients. Prior work shows that brain monitoring using electroencephalography (EEG) to track sedation levels may help medical personnel to optimize drug dosing and avoid the adverse effects of oversedation and undersedation. However, the performance of sedation monitoring methods proposed to date deal poorly with individual variability across patients, leading to inconsistent performance. To address this challenge we develop an online learning approach based on Adaptive Regularization of Weight Vectors (AROW). Our approach adaptively updates a sedation level prediction algorithm under a continuously evolving data distribution. The prediction model is gradually calibrated for individual patients in response to EEG observations and routine clinical assessments over time. The evaluations are performed on a population of 172 sedated ICU patients whose sedation levels were assessed using the Richmond Agitation-Sedation Scale (scores between -5 = comatose and 0 = awake). The proposed adaptive model achieves better performance than the same model without adaptation (average accuracies with tolerance of one level difference: 68.76% vs. 61.10%). Moreover, our approach is shown to be robust to sudden changes caused by label noise. Medication administrations have different effects on model performance. We find that the model performs best in patients receiving only propofol, compared to patients receiving no sedation or multiple simultaneous sedative medications.

  View details for DOI 10.1109/TBME.2019.2943062

  View details for Web of Science ID 000537293200017

  View details for PubMedID 31545708

  View details for PubMedCentralID PMC7085963

• Burden of Epileptiform Activity Predicts Discharge Neurologic Outcomes in Severe Acute Ischemic Stroke. Neurocritical care Tabaeizadeh, M., Aboul Nour, H., Shoukat, M., Sun, H., Jin, J., Javed, F., Kassa, S., Edhi, M., Bordbar, E., Gallagher, J., Moura, V. J., Ghanta, M., Shao, Y. P., Cole, A. J., Rosenthal, E. S., Westover, M. B., Zafar, S. F. 2020; 32 (3): 697-706

  Abstract

  Clinical seizures following acute ischemic stroke (AIS) appear to contribute to worse neurologic outcomes. However, the effect of electrographic epileptiform abnormalities (EAs) more broadly is less clear. Here, we evaluate the impact of EAs, including electrographic seizures and periodic and rhythmic patterns, on outcomes in patients with AIS.This is a retrospective study of all patients with AIS aged ≥ 18 years who underwent at least 18 h of continuous electroencephalogram (EEG) monitoring at a single center between 2012 and 2017. EAs were classified according to American Clinical Neurophysiology Society (ACNS) nomenclature and included seizures and periodic and rhythmic patterns. EA burden for each 24-h epoch was defined using the following cutoffs: EA presence, maximum daily burden < 10% versus > 10%, maximum daily burden < 50% versus > 50%, and maximum daily burden using categories from ACNS nomenclature ("rare" < 1%; "occasional" 1-9%; "frequent" 10-49%; "abundant" 50-89%; "continuous" > 90%). Maximum EA frequency for each epoch was dichotomized into ≥ 1.5 Hz versus < 1.5 Hz. Poor neurologic outcome was defined as a modified Rankin Scale score of 4-6 (vs. 0-3 as good outcome) at hospital discharge.One hundred and forty-three patients met study inclusion criteria. Sixty-seven patients (46.9%) had EAs. One hundred and twenty-four patients (86.7%) had poor outcome. On univariate analysis, the presence of EAs (OR 3.87 [1.27-11.71], p = 0.024) and maximum daily burden > 10% (OR 12.34 [2.34-210], p = 0.001) and > 50% (OR 8.26 [1.34-122], p = 0.035) were associated with worse outcomes. On multivariate analysis, after adjusting for clinical covariates (age, gender, NIHSS, APACHE II, stroke location, stroke treatment, hemorrhagic transformation, Charlson comorbidity index, history of epilepsy), EA presence (OR 5.78 [1.36-24.56], p = 0.017), maximum daily burden > 10% (OR 23.69 [2.43-230.7], p = 0.006), and maximum daily burden > 50% (OR 9.34 [1.01-86.72], p = 0.049) were associated with worse outcomes. After adjusting for covariates, we also found a dose-dependent association between increasing EA burden and increasing probability of poor outcomes (OR 1.89 [1.18-3.03] p = 0.009). We did not find an independent association between EA frequency and outcomes (OR: 4.43 [.98-20.03] p = 0.053). However, the combined effect of increasing EA burden and frequency ≥ 1.5 Hz (EA burden * frequency) was significantly associated with worse outcomes (OR 1.64 [1.03-2.63] p = 0.039).Electrographic seizures and periodic and rhythmic patterns in patients with AIS are associated with worse outcomes in a dose-dependent manner. Future studies are needed to assess whether treatment of this EEG activity can improve outcomes.

  View details for DOI 10.1007/s12028-020-00944-0

  View details for PubMedID 32246435

  View details for PubMedCentralID PMC7416505

• Breakthrough spikes in rapid eye movement sleep from the epilepsy monitoring unit are associated with peak seizure frequency. Sleep McKenzie, M. B., Jones, M. L., O'Carroll, A., Serletis, D., Shafer, L. A., Ng, M. C. 2020; 43 (5)

  Abstract

  Rapid eye movement sleep (REM) usually suppresses interictal epileptiform discharges (IED) and seizures. However, breakthrough IEDs in REM sometimes continue. We aimed to determine if the amount of IED and seizures in REM, or REM duration, is associated with clinical trajectories.Continuous electroencephalogram (EEG) recordings from the epilepsy monitoring unit (EMU) were clipped to at least 3 h of concatenated salient findings per day including all identified REM. Concatenated EEG files were analyzed for nightly REM duration and the "REM spike burden" (RSB), defined as the proportion of REM occupied by IED or seizures. Patient charts were reviewed for clinical data, including patient-reported peak seizure frequency. Logistic and linear regressions were performed, as appropriate, to explore associations between two explanatory measures (duration of REM and RSB) and six indicators of seizure activity (clinical trajectory outcomes).The median duration of REM sleep was 43.3 (IQR 20.9-73.2) min per patient per night. 59/63 (93.7%) patients achieved REM during EMU admission. 39/59 (66.1%) patients had breakthrough IEDs or seizures in REM with the median RSB at 0.7% (IQR 0%-8.4%). Every 1% increase in RSB was associated with 1.69 (95% CI = 0.47-2.92) more seizures per month during the peak seizure period of one's epilepsy (p = 0.007).Increased epileptiform activity during REM is associated with increased peak seizure frequency, suggesting an overall poorer epilepsy trajectory. Our findings suggest that RSB in the EMU is a useful biomarker to help guide about what to expect over the course of one's epilepsy.

  View details for DOI 10.1093/sleep/zsz281

  View details for PubMedID 31768558

• Artificial intelligence in sleep medicine: an American Academy of Sleep Medicine position statement. Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine Goldstein, C. A., Berry, R. B., Kent, D. T., Kristo, D. A., Seixas, A. A., Redline, S., Westover, M. B., Abbasi-Feinberg, F., Aurora, R. N., Carden, K. A., Kirsch, D. B., Malhotra, R. K., Martin, J. L., Olson, E. J., Ramar, K., Rosen, C. L., Rowley, J. A., Shelgikar, A. V. 2020; 16 (4): 605-607

  Abstract

  Sleep medicine is well positioned to benefit from advances that use big data to create artificially intelligent computer programs. One obvious initial application in the sleep disorders center is the assisted (or enhanced) scoring of sleep and associated events during polysomnography (PSG). This position statement outlines the potential opportunities and limitations of integrating artificial intelligence (AI) into the practice of sleep medicine. Additionally, although the most apparent and immediate application of AI in our field is the assisted scoring of PSG, we propose potential clinical use cases that transcend the sleep laboratory and are expected to deepen our understanding of sleep disorders, improve patient-centered sleep care, augment day-to-day clinical operations, and increase our knowledge of the role of sleep in health at a population level.

  View details for DOI 10.5664/jcsm.8288

  View details for PubMedID 32022674

  View details for PubMedCentralID PMC7161449

• Artificial intelligence in sleep medicine: background and implications for clinicians. Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine Goldstein, C. A., Berry, R. B., Kent, D. T., Kristo, D. A., Seixas, A. A., Redline, S., Westover, M. B. 2020; 16 (4): 609-618

  Abstract

  Polysomnography remains the cornerstone of objective testing in sleep medicine and results in massive amounts of electrophysiological data, which is well-suited for analysis with artificial intelligence (AI)-based tools. Combined with other sources of health data, AI is expected to provide new insights to inform the clinical care of sleep disorders and advance our understanding of the integral role sleep plays in human health. Additionally, AI has the potential to streamline day-to-day operations and therefore optimize direct patient care by the sleep disorders team. However, clinicians, scientists, and other stakeholders must develop best practices to integrate this rapidly evolving technology into our daily work while maintaining the highest degree of quality and transparency in health care and research. Ultimately, when harnessed appropriately in conjunction with human expertise, AI will improve the practice of sleep medicine and further sleep science for the health and well-being of our patients.

  View details for DOI 10.5664/jcsm.8388

  View details for PubMedID 32065113

  View details for PubMedCentralID PMC7161463

• Protected Health Information filter (Philter): accurately and securely de-identifying free-text clinical notes NPJ DIGITAL MEDICINE Norgeot, B., Muenzen, K., Peterson, T. A., Fan, X., Glicksberg, B. S., Schenk, G., Rutenberg, E., Oskotsky, B., Sirota, M., Yazdany, J., Schmajuk, G., Ludwig, D., Goldstein, T., Butte, A. J. 2020; 3 (1)

  View details for DOI 10.1038/s41746-020-0258-y

  View details for Web of Science ID 000528990400001

• Excess brain age in the sleep electroencephalogram predicts reduced life expectancy NEUROBIOLOGY OF AGING Paixao, L., Sikka, P., Sun, H., Jain, A., Hogan, J., Thomas, R., Westover, M. 2020; 88: 150-155

  Abstract

  The brain age index (BAI) measures the difference between an individual's apparent "brain age" (BA; estimated by comparing EEG features during sleep from an individual with age norms), and their chronological age (CA); that is BAI = BA-CA. Here, we evaluate whether BAI predicts life expectancy. Brain age was quantified using a previously published machine learning algorithm for a cohort of participants ≥40 years old who underwent an overnight sleep electroencephalogram (EEG) as part of the Sleep Heart Health Study (n = 4877). Excess brain age (BAI >0) was associated with reduced life expectancy (adjusted hazard ratio: 1.12, [1.03, 1.21], p = 0.002). Life expectancy decreased by -0.81 [-1.44, -0.24] years per standard-deviation increase in BAI. Our findings show that BAI, a sleep EEG-based biomarker of the deviation of sleep microstructure from patterns normal for age, is an independent predictor of life expectancy.

  View details for DOI 10.1016/j.neurobiolaging.2019.12.015

  View details for Web of Science ID 000520054800015

  View details for PubMedID 31932049

  View details for PubMedCentralID PMC7085452

• Electrographic predictors of successful weaning from anaesthetics in refractory status epilepticus. Brain : a journal of neurology Rubin, D. B., Angelini, B., Shoukat, M., Chu, C. J., Zafar, S. F., Westover, M. B., Cash, S. S., Rosenthal, E. S. 2020; 143 (4): 1143-1157

  Abstract

  Intravenous third-line anaesthetic agents are typically titrated in refractory status epilepticus to achieve either seizure suppression or burst suppression on continuous EEG. However, the optimum treatment paradigm is unknown and little data exist to guide the withdrawal of anaesthetics in refractory status epilepticus. Premature withdrawal of anaesthetics risks the recurrence of seizures, whereas the prolonged use of anaesthetics increases the risk of treatment-associated adverse effects. This study sought to measure the accuracy of features of EEG activity during anaesthetic weaning in refractory status epilepticus as predictors of successful weaning from intravenous anaesthetics. We prespecified a successful anaesthetic wean as the discontinuation of intravenous anaesthesia without developing recurrent status epilepticus, and a wean failure as either recurrent status epilepticus or the resumption of anaesthesia for the purpose of treating an EEG pattern concerning for incipient status epilepticus. We evaluated two types of features as predictors of successful weaning: spectral components of the EEG signal, and spatial-correlation-based measures of functional connectivity. The results of these analyses were used to train a classifier to predict wean outcome. Forty-seven consecutive anaesthetic weans (23 successes, 24 failures) were identified from a single-centre cohort of patients admitted with refractory status epilepticus from 2016 to 2019. Spectral components of the EEG revealed no significant differences between successful and unsuccessful weans. Analysis of functional connectivity measures revealed that successful anaesthetic weans were characterized by the emergence of larger, more densely connected, and more highly clustered spatial functional networks, yielding 75.5% (95% confidence interval: 73.1-77.8%) testing accuracy in a bootstrap analysis using a hold-out sample of 20% of data for testing and 74.6% (95% confidence interval 73.2-75.9%) testing accuracy in a secondary external validation cohort, with an area under the curve of 83.3%. Distinct signatures in the spatial networks of functional connectivity emerge during successful anaesthetic liberation in status epilepticus; these findings are absent in patients with anaesthetic wean failure. Identifying features that emerge during successful anaesthetic weaning may allow faster and more successful anaesthetic liberation after refractory status epilepticus.

  View details for DOI 10.1093/brain/awaa069

  View details for PubMedID 32268366

  View details for PubMedCentralID PMC7174057

• Soluble ST2 Is Associated With New Epileptiform Abnormalities Following Nontraumatic Subarachnoid Hemorrhage. Stroke Lissak, I. A., Zafar, S. F., Westover, M. B., Schleicher, R. L., Kim, J. A., Leslie-Mazwi, T., Stapleton, C. J., Patel, A. B., Kimberly, W. T., Rosenthal, E. S. 2020; 51 (4): 1128-1134

  Abstract

  Background and Purpose- We evaluated the association between 2 types of predictors of delayed cerebral ischemia after nontraumatic subarachnoid hemorrhage, including biomarkers of the innate immune response and neurophysiologic changes on continuous electroencephalography. Methods- We studied subarachnoid hemorrhage patients that had at least 72 hours of continuous electroencephalography and blood samples collected within the first 5 days of symptom onset. We measured inflammatory biomarkers previously associated with delayed cerebral ischemia and functional outcome, including soluble ST2 (sST2), IL-6 (interleukin-6), and CRP (C-reactive protein). Serial plasma samples and cerebrospinal fluid sST2 levels were available in a subgroup of patients. Neurophysiologic changes were categorized into new or worsening epileptiform abnormalities (EAs) or new background deterioration. The association of biomarkers with neurophysiologic changes were evaluated using the Wilcoxon rank-sum test. Plasma and cerebrospinal fluid sST2 were further examined longitudinally using repeated measures mixed-effects models. Results- Forty-six patients met inclusion criteria. Seventeen (37%) patients developed new or worsening EAs, 21 (46%) developed new background deterioration, and 8 (17%) developed neither. Early (day, 0-5) plasma sST2 levels were higher among patients with new or worsening EAs (median 115 ng/mL [interquartile range, 73.8-197]) versus those without (74.7 ng/mL [interquartile range, 44.8-102]; P=0.024). Plasma sST2 levels were similar between patients with or without new background deterioration. Repeated measures mixed-effects modeling that adjusted for admission risk factors showed that the association with new or worsening EAs remained independent for both plasma sST2 (β=0.41 [95% CI, 0.09-0.73]; P=0.01) and cerebrospinal fluid sST2 (β=0.97 [95% CI, 0.14-1.8]; P=0.021). IL-6 and CRP were not associated with new background deterioration or with new or worsening EAs. Conclusions- In patients admitted with subarachnoid hemorrhage, sST2 level was associated with new or worsening EAs but not new background deterioration. This association may identify a link between a specific innate immune response pathway and continuous electroencephalography abnormalities in the pathogenesis of secondary brain injury after subarachnoid hemorrhage.

  View details for DOI 10.1161/STROKEAHA.119.028515

  View details for PubMedID 32156203

  View details for PubMedCentralID PMC7123848

• Covid-19 - Navigating the Uncharted. The New England journal of medicine Fauci, A. S., Lane, H. C., Redfield, R. R. 2020; 382 (13): 1268-1269

  View details for DOI 10.1056/NEJMe2002387

  View details for PubMedID 32109011

  View details for PubMedCentralID PMC7121221

• Early Prediction of Sepsis From Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019. Critical care medicine Reyna, M. A., Josef, C. S., Jeter, R., Shashikumar, S. P., Westover, M. B., Nemati, S., Clifford, G. D., Sharma, A. 2020; 48 (2): 210-217

  Abstract

  Sepsis is a major public health concern with significant morbidity, mortality, and healthcare expenses. Early detection and antibiotic treatment of sepsis improve outcomes. However, although professional critical care societies have proposed new clinical criteria that aid sepsis recognition, the fundamental need for early detection and treatment remains unmet. In response, researchers have proposed algorithms for early sepsis detection, but directly comparing such methods has not been possible because of different patient cohorts, clinical variables and sepsis criteria, prediction tasks, evaluation metrics, and other differences. To address these issues, the PhysioNet/Computing in Cardiology Challenge 2019 facilitated the development of automated, open-source algorithms for the early detection of sepsis from clinical data.Participants submitted containerized algorithms to a cloud-based testing environment, where we graded entries for their binary classification performance using a novel clinical utility-based evaluation metric. We designed this scoring function specifically for the Challenge to reward algorithms for early predictions and penalize them for late or missed predictions and for false alarms.ICUs in three separate hospital systems. We shared data from two systems publicly and sequestered data from all three systems for scoring.We sourced over 60,000 ICU patients with up to 40 clinical variables for each hour of a patient's ICU stay. We applied Sepsis-3 clinical criteria for sepsis onset.None.A total of 104 groups from academia and industry participated, contributing 853 submissions. Furthermore, 90 abstracts based on Challenge entries were accepted for presentation at Computing in Cardiology.Diverse computational approaches predict the onset of sepsis several hours before clinical recognition, but generalizability to different hospital systems remains a challenge.

  View details for DOI 10.1097/CCM.0000000000004145

  View details for PubMedID 31939789

  View details for PubMedCentralID PMC6964870

• Machine learning models reveal neurocognitive impairment type and prevalence are associated with distinct variables in HIV/AIDS. Journal of neurovirology Tu, W., Chen, P. A., Koenig, N., Gomez, D., Fujiwara, E., Gill, M. J., Kong, L., Power, C. 2020; 26 (1): 41-51

  Abstract

  Neurocognitive impairment (NCI) among HIV-infected patients is heterogeneous in its reported presentations and frequencies. To determine the prevalence of NCI and its associated subtypes as well as predictive variables, we investigated patients with HIV/AIDS receiving universal health care. Recruited adult HIV-infected subjects underwent a neuropsychological (NP) test battery with established normative (sex-, age-, and education-matched) values together with assessment of their demographic and clinical variables. Three patient groups were identified including neurocognitively normal (NN, n = 246), HIV-associated neurocognitive disorders (HAND, n = 78), and neurocognitively impaired-other disorders (NCI-OD, n = 46). Univariate, multiple logistic regression and machine learning analyses were applied. Univariate analyses showed variables differed significantly between groups including birth continent, quality of life, substance use, and PHQ-9. Multiple logistic regression models revealed groups again differed significantly for substance use, PHQ-9 score, VACS index, and head injury. Random forest (RF) models disclosed that classification algorithms distinguished HAND from NN and NCI-OD from NN with area under the curve (AUC) values of 0.87 and 0.77, respectively. Relative importance plots derived from the RF model exhibited distinct variable rankings that were predictive of NCI status for both NN versus HAND and NN versus NCI-OD comparisons. Thus, NCI was frequently detected (33.5%) although HAND prevalence (21%) was lower than in several earlier reports underscoring the potential contribution of other factors to NCI. Machine learning models uncovered variables related to individual NCI types that were not identified by univariate or multiple logistic regression analyses, highlighting the value of other approaches to understanding NCI in HIV/AIDS.

  View details for DOI 10.1007/s13365-019-00791-6

  View details for PubMedID 31520320

• Seizure tracking of epileptic EEGs using a model-driven approach. Journal of neural engineering Song, J. L., Li, Q., Pan, M., Zhang, B., Westover, M. B., Zhang, R. 2020; 17 (1): 016024

  Abstract

  As a chronic neurological disorder, epilepsy is characterized by recurrent and unprovoked epileptic seizures that can disrupt the normal neuro-biologic, cognitive, psychological conditions of patients. Therefore, it is worthwhile to give a detailed account of how the epileptic EEG evolves during a period of seizure so that an effective control can be guided for epileptic patients in clinics.Considering the successful application of the neural mass model (NMM) in exploring the insights into brain activities for epilepsy, in this paper, we aim to construct a model-driven approach to track the development of seizures using epileptic EEGs. We first propose a new time-delay Wendling model with sub-populations (TD-W-SP model) with respect to three aspects of improvements. Then we introduce a model-driven seizure tracking approach, where a model training method is designed based on extracted features from epileptic EEGs and a tracking index is defined as a function of the trained model parameters.Numerical results on eight patients on CHB-MIT database demonstrate that our proposed method performs well in simulating epileptic-like EEGs as well as tracking the evolution of three stages (that is, from pre-ictal to ictal and from ictal to post-ictal) during a period of epileptic seizure.A useful attempt to track epileptic seizures by combining the NMM with the data analysis.

  View details for DOI 10.1088/1741-2552/ab2409

  View details for PubMedID 31121573

  View details for PubMedCentralID PMC6874715

• Diagnostic Value of Electroencephalography with Ten Electrodes in Critically Ill Patients. Neurocritical care Westover, M. B., Gururangan, K. n., Markert, M. S., Blond, B. N., Lai, S. n., Benard, S. n., Bickel, S. n., Hirsch, L. J., Parvizi, J. n. 2020

  Abstract

  In critical care settings, electroencephalography (EEG) with reduced number of electrodes (reduced montage EEG, rm-EEG) might be a timely alternative to the conventional full montage EEG (fm-EEG). However, past studies have reported variable accuracies for detecting seizures using rm-EEG. We hypothesized that the past studies did not distinguish between differences in sensitivity from differences in classification of EEG patterns by different readers. The goal of the present study was to revisit the diagnostic value of rm-EEG when confounding issues are accounted for.We retrospectively collected 212 adult EEGs recorded at Massachusetts General Hospital and reviewed by two epileptologists with access to clinical, trending, and video information. In Phase I of the study, we re-configured the first 4 h of the EEGs in lateral circumferential montage with ten electrodes and asked new readers to interpret the EEGs without access to any other ancillary information. We compared their rating to the reading of hospital clinicians with access to ancillary information. In Phase II, we measured the accuracy of the same raters reading representative samples of the discordant EEGs in full and reduced configurations presented randomly by comparing their performance to majority consensus as the gold standard.Of the 95 EEGs without seizures in the selected fm-EEG, readers of rm-EEG identified 92 cases (97%) as having no seizure activity. Of 117 EEGs with "seizures" identified in the selected fm-EEG, none of the cases was labeled as normal on rm-EEG. Readers of rm-EEG reported pathological activity in 100% of cases, but labeled them as seizures (N = 77), rhythmic or periodic patterns (N = 24), epileptiform spikes (N = 7), or burst suppression (N = 6). When the same raters read representative epochs of the discordant EEG cases (N = 43) in both fm-EEG and rm-EEG configurations, we found high concordance (95%) and intra-rater agreement (93%) between fm-EEG and rm-EEG diagnoses.Reduced EEG with ten electrodes in circumferential configuration preserves key features of the traditional EEG system. Discrepancies between rm-EEG and fm-EEG as reported in some of the past studies can be in part due to methodological factors such as choice of gold standard diagnosis, asymmetric access to ancillary clinical information, and inter-rater variability rather than detection failure of rm-EEG as a result of electrode reduction per se.

  View details for DOI 10.1007/s12028-019-00911-4

  View details for PubMedID 32034656

• Interrater Reliability of Experts in Identifying Interictal Epileptiform Discharges in Electroencephalograms. JAMA neurology Jing, J., Herlopian, A., Karakis, I., Ng, M., Halford, J. J., Lam, A., Maus, D., Chan, F., Dolatshahi, M., Muniz, C. F., Chu, C., Sacca, V., Pathmanathan, J., Ge, W., Sun, H., Dauwels, J., Cole, A. J., Hoch, D. B., Cash, S. S., Westover, M. B. 2020; 77 (1): 49-57

  Abstract

  The validity of using electroencephalograms (EEGs) to diagnose epilepsy requires reliable detection of interictal epileptiform discharges (IEDs). Prior interrater reliability (IRR) studies are limited by small samples and selection bias.To assess the reliability of experts in detecting IEDs in routine EEGs.This prospective analysis conducted in 2 phases included as participants physicians with at least 1 year of subspecialty training in clinical neurophysiology. In phase 1, 9 experts independently identified candidate IEDs in 991 EEGs (1 expert per EEG) reported in the medical record to contain at least 1 IED, yielding 87 636 candidate IEDs. In phase 2, the candidate IEDs were clustered into groups with distinct morphological features, yielding 12 602 clusters, and a representative candidate IED was selected from each cluster. We added 660 waveforms (11 random samples each from 60 randomly selected EEGs reported as being free of IEDs) as negative controls. Eight experts independently scored all 13 262 candidates as IEDs or non-IEDs. The 1051 EEGs in the study were recorded at the Massachusetts General Hospital between 2012 and 2016.Primary outcome measures were percentage of agreement (PA) and beyond-chance agreement (Gwet κ) for individual IEDs (IED-wise IRR) and for whether an EEG contained any IEDs (EEG-wise IRR). Secondary outcomes were the correlations between numbers of IEDs marked by experts across cases, calibration of expert scoring to group consensus, and receiver operating characteristic analysis of how well multivariate logistic regression models may account for differences in the IED scoring behavior between experts.Among the 1051 EEGs assessed in the study, 540 (51.4%) were those of females and 511 (48.6%) were those of males. In phase 1, 9 experts each marked potential IEDs in a median of 65 (interquartile range [IQR], 28-332) EEGs. The total number of IED candidates marked was 87 636. Expert IRR for the 13 262 individually annotated IED candidates was fair, with the mean PA being 72.4% (95% CI, 67.0%-77.8%) and mean κ being 48.7% (95% CI, 37.3%-60.1%). The EEG-wise IRR was substantial, with the mean PA being 80.9% (95% CI, 76.2%-85.7%) and mean κ being 69.4% (95% CI, 60.3%-78.5%). A statistical model based on waveform morphological features, when provided with individualized thresholds, explained the median binary scores of all experts with a high degree of accuracy of 80% (range, 73%-88%).This study's findings suggest that experts can identify whether EEGs contain IEDs with substantial reliability. Lower reliability regarding individual IEDs may be largely explained by various experts applying different thresholds to a common underlying statistical model.

  View details for DOI 10.1001/jamaneurol.2019.3531

  View details for PubMedID 31633742

  View details for PubMedCentralID PMC6806666

• Detection of mesial temporal lobe epileptiform discharges on intracranial electrodes using deep learning. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Abou Jaoude, M., Jing, J., Sun, H., Jacobs, C. S., Pellerin, K. R., Westover, M. B., Cash, S. S., Lam, A. D. 2020; 131 (1): 133-141

  Abstract

  Develop a high-performing algorithm to detect mesial temporal lobe (mTL) epileptiform discharges on intracranial electrode recordings.An epileptologist annotated 13,959 epileptiform discharges from a dataset of intracranial EEG recordings from 46 epilepsy patients. Using this dataset, we trained a convolutional neural network (CNN) to recognize mTL epileptiform discharges from a single intracranial bipolar channel. The CNN outputs from multiple bipolar channel inputs were averaged to generate the final detector output. Algorithm performance was estimated using a nested 5-fold cross-validation.On the receiver-operating characteristic curve, our algorithm achieved an area under the curve (AUC) of 0.996 and a partial AUC (for specificity > 0.9) of 0.981. AUC on a precision-recall curve was 0.807. A sensitivity of 84% was attained at a false positive rate of 1 per minute. 35.9% of the false positive detections corresponded to epileptiform discharges that were missed during expert annotation.Using deep learning, we developed a high-performing, patient non-specific algorithm for detection of mTL epileptiform discharges on intracranial electrodes.Our algorithm has many potential applications for understanding the impact of mTL epileptiform discharges in epilepsy and on cognition, and for developing therapies to specifically reduce mTL epileptiform activity.

  View details for DOI 10.1016/j.clinph.2019.09.031

  View details for PubMedID 31760212

  View details for PubMedCentralID PMC6879011

• Evaluating the Clinical Impact of Rapid Response Electroencephalography: The DECIDE Multicenter Prospective Observational Clinical Study. Critical care medicine Vespa, P. M., Olson, D. M., John, S. n., Hobbs, K. S., Gururangan, K. n., Nie, K. n., Desai, M. J., Markert, M. n., Parvizi, J. n., Bleck, T. P., Hirsch, L. J., Westover, M. B. 2020

  Abstract

  To measure the diagnostic accuracy, timeliness, and ease of use of Ceribell rapid response electroencephalography. We assessed physicians' diagnostic assessments and treatment plans before and after rapid response electroencephalography assessment. Primary outcomes were changes in physicians' diagnostic and therapeutic decision making and their confidence in these decisions based on the use of the rapid response electroencephalography system. Secondary outcomes were time to electroencephalography, setup time, ease of use, and quality of electroencephalography data.Prospective multicenter nonrandomized observational study.ICUs in five academic hospitals in the United States.Patients with encephalopathy suspected of having nonconvulsive seizures and physicians evaluating these patients.Physician bedside assessment of sonified electroencephalography (30 s from each hemisphere) and visual electroencephalography (60 s) using rapid response electroencephalography.Physicians (29 fellows or residents, eight attending neurologists) evaluated 181 ICU patients; complete clinical and electroencephalography data were available in 164 patients (average 58.6 ± 18.7 yr old, 45% females). Relying on rapid response electroencephalography information at the bedside improved the sensitivity (95% CI) of physicians' seizure diagnosis from 77.8% (40.0%, 97.2%) to 100% (66.4%, 100%) and the specificity (95% CI) of their diagnosis from 63.9% (55.8%, 71.4%) to 89% (83.0%, 93.5%). Physicians' confidence in their own diagnosis and treatment plan were also improved. Time to electroencephalography (median [interquartile range]) was 5 minutes (4-10 min) with rapid response electroencephalography while the conventional electroencephalography was delayed by several hours (median [interquartile range] delay = 239 minutes [134-471 min] [p < 0.0001 using Wilcoxon signed rank test]). The device was rated as easy to use (mean ± SD: 4.7 ± 0.6 [1 = difficult, 5 = easy]) and was without serious adverse effects.Rapid response electroencephalography enabled timely and more accurate assessment of patients in the critical care setting. The use of rapid response electroencephalography may be clinically beneficial in the assessment of patients with high suspicion for nonconvulsive seizures and status epilepticus.

  View details for DOI 10.1097/CCM.0000000000004428

  View details for PubMedID 32618687

• The probability of seizures during continuous EEG monitoring in high-risk neonates. Epilepsia Worden, L. T., Chinappen, D. M., Stoyell, S. M., Gold, J., Paixao, L., Krishnamoorthy, K., Kramer, M. A., Westover, M. B., Chu, C. J. 2019; 60 (12): 2508-2518

  Abstract

  We evaluated the impact of monitoring indication, early electroencephalography (EEG), and clinical features on seizure risk in all neonates undergoing continuous EEG (cEEG) monitoring following a standardized monitoring protocol.All cEEGs from unique neonates 34-48 weeks postmenstrual age monitored from 1/2011-10/2017 (n = 291) were included. We evaluated the impact of cEEG monitoring indication (acute neonatal encephalopathy [ANE], suspicious clinical events [SCEs], or other high-risk conditions [OHRs]), age, medication status, and early EEG abnormalities (including the presence of epileptiform discharges and abnormal background continuity, amplitude, asymmetry, asynchrony, excessive sharp transients, and burst suppression) on time to first seizure and overall seizure risk using Kaplan-Meier survival curves and multivariable Cox proportional hazards models.Seizures occurred in 28% of high-risk neonates. Discontinuation of monitoring after 24 hours of seizure-freedom would have missed 8.5% of neonates with seizures. Overall seizure risk was lower in neonates monitored for ANE compared to OHR (P = .004) and trended lower compared to SCE (P = .097). The time course of seizure presentation varied by group, where the probability of future seizure was less than 1% after 17 hours of seizure-free monitoring in the SCE group, but required 42 hours in the OHR group, and 73 hours in the ANE group. The presence of early epileptiform discharges increased seizure risk in each group (ANE: adjusted hazard ratio [aHR] 4.32, 95% confidence interval [CI] 1.23-15.13, P = .022; SCE: aHR 10.95, 95% CI 4.77-25.14, P < 1e-07; OHR: aHR 56.90, 95% CI 10.32-313.72, P < 1e-05).Neonates who undergo cEEG are at high risk for seizures, and risk varies by monitoring indication and early EEG findings. Seizures are captured in nearly all neonates undergoing monitoring for SCE within 24 hours of cEEG monitoring. Neonates monitored for OHR and ANE can present with delayed seizures and require longer durations of monitoring. Early epileptiform discharges are the best early EEG feature to predict seizure risk.

  View details for DOI 10.1111/epi.16387

  View details for PubMedID 31745988

  View details for PubMedCentralID PMC7083278

• Comparing the efficacy, exposure, and cost of clinical trial analysis methods. Epilepsia Oliveira, A., Romero, J. M., Goldenholz, D. M. 2019; 60 (12): e128-e132

  Abstract

  This study aimed to compare three commonly used analysis methods for clinical trials in epilepsy in terms of statistical efficiency, nonefficacious exposure, and cost. A realistic seizure diary simulator was employed to produce 102 000 trials, which were analyzed by the 50%-responder rate method (RR50), median percentage change (MPC), and time to prerandomization (TTP). Half the trials compared a placebo to a drug that was 20% better, and the other half compared two placebos. The former were used to calculate statistical power; the latter were used for type 1 error rates. Based on the number of patients needed to achieve 90% power, expected number of patient-days of nonefficacious exposures and expected cost were calculated for each method. MPC demonstrated the highest efficacy, lowest exposure, and lowest cost. RR50 demonstrated the lowest efficacy, highest exposure, and highest cost. Costs were: MPC $1 295 000, TTP $1 315 720, and RR50 $2 331 000. Selecting an optimal analysis method for a primary outcome in an epilepsy trial can have consequences in terms of nonefficacious exposure and cost. This study provides evidence supporting the use of MPC (preferred) or TTP, and evidence suggesting that RR50 would incur high costs and excess exposures.

  View details for DOI 10.1111/epi.16384

  View details for PubMedID 31724165

• A novel neural computational model of generalized periodic discharges in acute hepatic encephalopathy. Journal of computational neuroscience Song, J. L., Paixao, L., Li, Q., Li, S. H., Zhang, R., Westover, M. B. 2019; 47 (2-3): 109-124

  Abstract

  Acute hepatic encephalopathy (AHE) due to acute liver failure is a common form of delirium, a state of confusion, impaired attention, and decreased arousal. The electroencephalogram (EEG) in AHE often exhibits a striking abnormal pattern of brain activity, which epileptiform discharges repeat in a regular repeating pattern. This pattern is known as generalized periodic discharges, or triphasic-waves (TPWs). While much is known about the neurophysiological mechanisms underlying AHE, how these mechanisms relate to TPWs is poorly understood. In order to develop hypotheses how TPWs arise, our work builds a computational model of AHE (AHE-CM), based on three modifications of the well-studied Liley model which emulate mechanisms believed central to brain dysfunction in AHE: increased neuronal excitability, impaired synaptic transmission, and enhanced postsynaptic inhibition. To relate our AHE-CM to clinical EEG data from patients with AHE, we design a model parameter optimization method based on particle filtering (PF-POM). Based on results from 7 AHE patients, we find that the proposed AHE-CM not only performs well in reproducing important aspects of the EEG, namely the periodicity of triphasic waves (TPWs), but is also helpful in suggesting mechanisms underlying variation in EEG patterns seen in AHE. In particular, our model helps explain what conditions lead to increased frequency of TPWs. In this way, our model represents a starting point for exploring the underlying mechanisms of brain dynamics in delirium by relating microscopic mechanisms to EEG patterns.

  View details for DOI 10.1007/s10827-019-00727-3

  View details for PubMedID 31506807

  View details for PubMedCentralID PMC6881550

• Quantitative Electroencephalogram Trends Predict Recovery in Hypoxic-Ischemic Encephalopathy. Critical care medicine Ghassemi, M. M., Amorim, E., Alhanai, T., Lee, J. W., Herman, S. T., Sivaraju, A., Gaspard, N., Hirsch, L. J., Scirica, B. M., Biswal, S., Moura Junior, V., Cash, S. S., Brown, E. N., Mark, R. G., Westover, M. B. 2019; 47 (10): 1416-1423

  Abstract

  Electroencephalogram features predict neurologic recovery following cardiac arrest. Recent work has shown that prognostic implications of some key electroencephalogram features change over time. We explore whether time dependence exists for an expanded selection of quantitative electroencephalogram features and whether accounting for this time dependence enables better prognostic predictions.Retrospective.ICUs at four academic medical centers in the United States.Comatose patients with acute hypoxic-ischemic encephalopathy.None.We analyzed 12,397 hours of electroencephalogram from 438 subjects. From the electroencephalogram, we extracted 52 features that quantify signal complexity, category, and connectivity. We modeled associations between dichotomized neurologic outcome (good vs poor) and quantitative electroencephalogram features in 12-hour intervals using sequential logistic regression with Elastic Net regularization. We compared a predictive model using time-varying features to a model using time-invariant features and to models based on two prior published approaches. Models were evaluated for their ability to predict binary outcomes using area under the receiver operator curve, model calibration (how closely the predicted probability of good outcomes matches the observed proportion of good outcomes), and sensitivity at several common specificity thresholds of interest. A model using time-dependent features outperformed (area under the receiver operator curve, 0.83 ± 0.08) one trained with time-invariant features (0.79 ± 0.07; p < 0.05) and a random forest approach (0.74 ± 0.13; p < 0.05). The time-sensitive model was also the best-calibrated.The statistical association between quantitative electroencephalogram features and neurologic outcome changed over time, and accounting for these changes improved prognostication performance.

  View details for DOI 10.1097/CCM.0000000000003840

  View details for PubMedID 31241498

  View details for PubMedCentralID PMC6746597

• Quantitative EEG reactivity and machine learning for prognostication in hypoxic-ischemic brain injury. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Amorim, E., van der Stoel, M., Nagaraj, S. B., Ghassemi, M. M., Jing, J., O'Reilly, U. M., Scirica, B. M., Lee, J. W., Cash, S. S., Westover, M. B. 2019; 130 (10): 1908-1916

  Abstract

  Electroencephalogram (EEG) reactivity is a robust predictor of neurological recovery after cardiac arrest, however interrater-agreement among electroencephalographers is limited. We sought to evaluate the performance of machine learning methods using EEG reactivity data to predict good long-term outcomes in hypoxic-ischemic brain injury.We retrospectively reviewed clinical and EEG data of comatose cardiac arrest subjects. Electroencephalogram reactivity was tested within 72 h from cardiac arrest using sound and pain stimuli. A Quantitative EEG (QEEG) reactivity method evaluated changes in QEEG features (EEG spectra, entropy, and frequency features) during the 10 s before and after each stimulation. Good outcome was defined as Cerebral Performance Category of 1-2 at six months. Performance of a random forest classifier was compared against a penalized general linear model (GLM) and expert electroencephalographer review.Fifty subjects were included and sixteen (32%) had good outcome. Both QEEG reactivity methods had comparable performance to expert EEG reactivity assessment for good outcome prediction (mean AUC 0.8 for random forest vs. 0.69 for GLM vs. 0.69 for expert review, respectively; p non-significant).Machine-learning models utilizing quantitative EEG reactivity data can predict long-term outcome after cardiac arrest.A quantitative approach to EEG reactivity assessment may support prognostication in cardiac arrest.

  View details for DOI 10.1016/j.clinph.2019.07.014

  View details for PubMedID 31419742

  View details for PubMedCentralID PMC6751020

• Clinical EEG slowing correlates with delirium severity and predicts poor clinical outcomes. Neurology Kimchi, E. Y., Neelagiri, A., Whitt, W., Sagi, A. R., Ryan, S. L., Gadbois, G., Groothuysen, D., Westover, M. B. 2019; 93 (13): e1260-e1271

  Abstract

  To determine which findings on routine clinical EEGs correlate with delirium severity across various presentations and to determine whether EEG findings independently predict important clinical outcomes.We prospectively studied a cohort of nonintubated inpatients undergoing EEG for evaluation of altered mental status. Patients were assessed for delirium within 1 hour of EEG with the 3-Minute Diagnostic Interview for Confusion Assessment Method (3D-CAM) and 3D-CAM severity score. EEGs were interpreted clinically by neurophysiologists, and reports were reviewed to identify features such as theta or delta slowing and triphasic waves. Generalized linear models were used to quantify associations among EEG findings, delirium, and clinical outcomes, including length of stay, Glasgow Outcome Scale scores, and mortality.We evaluated 200 patients (median age 60 years, IQR 48.5-72 years); 121 (60.5%) met delirium criteria. The EEG finding most strongly associated with delirium presence was a composite of generalized theta or delta slowing (odds ratio 10.3, 95% confidence interval 5.3-20.1). The prevalence of slowing correlated not only with overall delirium severity (R 2 = 0.907) but also with the severity of each feature assessed by CAM-based delirium algorithms. Slowing was common in delirium even with normal arousal. EEG slowing was associated with longer hospitalizations, worse functional outcomes, and increased mortality, even after adjustment for delirium presence or severity.Generalized slowing on routine clinical EEG strongly correlates with delirium and may be a valuable biomarker for delirium severity. In addition, generalized EEG slowing should trigger elevated concern for the prognosis of patients with altered mental status.

  View details for DOI 10.1212/WNL.0000000000008164

  View details for PubMedID 31467255

  View details for PubMedCentralID PMC7011865

• Automated tracking of level of consciousness and delirium in critical illness using deep learning NPJ DIGITAL MEDICINE Sun, H., Kimchi, E., Akeju, O., Nagaraj, S. B., McClain, L. M., Zhou, D. W., Boyle, E., Zheng, W., Ge, W., Westover, M. 2019; 2: 89

  Abstract

  Over- and under-sedation are common in the ICU, and contribute to poor ICU outcomes including delirium. Behavioral assessments, such as Richmond Agitation-Sedation Scale (RASS) for monitoring levels of sedation and Confusion Assessment Method for the ICU (CAM-ICU) for detecting signs of delirium, are often used. As an alternative, brain monitoring with electroencephalography (EEG) has been proposed in the operating room, but is challenging to implement in ICU due to the differences between critical illness and elective surgery, as well as the duration of sedation. Here we present a deep learning model based on a combination of convolutional and recurrent neural networks that automatically tracks both the level of consciousness and delirium using frontal EEG signals in the ICU. For level of consciousness, the system achieves a median accuracy of 70% when allowing prediction to be within one RASS level difference across all patients, which is comparable or higher than the median technician-nurse agreement at 59%. For delirium, the system achieves an AUC of 0.80 with 69% sensitivity and 83% specificity at the optimal operating point. The results show it is feasible to continuously track level of consciousness and delirium in the ICU.

  View details for DOI 10.1038/s41746-019-0167-0

  View details for Web of Science ID 000484610300001

  View details for PubMedID 31508499

  View details for PubMedCentralID PMC6733797

• Drug-Specific Models Improve the Performance of an EEG-based Automated Brain-State Prediction System. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Kashkooli, K., Polk, S. L., Chamadia, S., Hahm, E., Ethridge, B., Gitlin, J., Ibala, R., Mekonnen, J., Pedemonte, J., Murphy, J. M., Sun, H., Westover, M. B., Akeju, O. 2019; 2019: 5808-5811

  Abstract

  Maintaining anesthetic states using automated brain-state prediction systems is expected to reduce drug overdosage and associated side-effects. However, commercially available brain-state monitoring systems perform poorly on drug-class combinations. We assume that current automated brain-state prediction systems perform poorly because they do not account for brain-state dynamics that are unique to drug-class combinations. In this work, we develop a k-nearest neighbors model to test whether improvements to automated brain-state prediction of drug-class combinations are feasible. We utilize electroencephalogram data collected from human subjects who received general anesthesia with sevoflurane and general anesthesia with the drug-class combination of sevoflurane-plus-ketamine. We demonstrate improved performance predicting anesthesia-induced brain-states using drug-specific models.

  View details for DOI 10.1109/EMBC.2019.8856935

  View details for PubMedID 31947172

  View details for PubMedCentralID PMC7077760

• Pharmacologic Unmasking of Neurologic Deficits: A Stress Test for the Brain. Anesthesiology Vlisides, P. E., Mashour, G. A. 2019; 131 (1): 5-6

  View details for DOI 10.1097/ALN.0000000000002775

  View details for PubMedID 31166237

  View details for PubMedCentralID PMC6586480

• Automatic Detection of General Anesthetic-States using ECG-Derived Autonomic Nervous System Features. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Polk, S. L., Kashkooli, K., Nagaraj, S. B., Chamadia, S., Murphy, J. M., Sun, H., Westover, M. B., Barbieri, R., Akeju, O. 2019; 2019: 2019-2022

  Abstract

  Electroencephalogram (EEG)-based prediction systems are used to target anesthetic-states in patients undergoing procedures with general anesthesia (GA). These systems are not widely employed in resource-limited settings because they are cost-prohibitive. Although anesthetic-drugs induce highly-structured, oscillatory neural dynamics that make EEG-based systems a principled approach for anesthetic-state monitoring, anesthetic-drugs also significantly modulate the autonomic nervous system (ANS). Because ANS dynamics can be inferred from electrocardiogram (ECG) features such as heart rate variability, it may be possible to develop an ECG-based system to infer anesthetic-states as a low-cost and practical alternative to EEG-based anesthetic-state prediction systems. In this work, we demonstrate that an ECG-based system using ANS features can be used to discriminate between non-GA and GA states in sevoflurane, with a GA F1 score of 0.834, [95% CI, 0.776, 0.892], and in sevoflurane-plus-ketamine, with a GA F1 score of 0.880 [0.815, 0.954]. With further refinement, ECG-based anesthetic-state systems could be developed as a fully automated system for anesthetic-state monitoring in resource-limited settings.

  View details for DOI 10.1109/EMBC.2019.8857704

  View details for PubMedID 31946297

  View details for PubMedCentralID PMC7077759

• Electroencephalographic reactivity as predictor of neurological outcome in postanoxic coma: A multicenter prospective cohort study. Annals of neurology Admiraal, M. M., van Rootselaar, A. F., Hofmeijer, J., Hoedemaekers, C. W., van Kaam, C. R., Keijzer, H. M., van Putten, M. J., Schultz, M. J., Horn, J. 2019; 86 (1): 17-27

  Abstract

  Outcome prediction in patients after cardiac arrest (CA) is challenging. Electroencephalographic reactivity (EEG-R) might be a reliable predictor. We aimed to determine the prognostic value of EEG-R using a standardized assessment.In a prospective cohort study, a strictly defined EEG-R assessment protocol was executed twice per day in adult patients after CA. EEG-R was classified as present or absent by 3 EEG readers, blinded to patient characteristics. Uncertain reactivity was classified as present. Primary outcome was best Cerebral Performance Category score (CPC) in 6 months after CA, dichotomized as good (CPC = 1-2) or poor (CPC = 3-5). EEG-R was considered reliable for predicting poor outcome if specificity was ≥95%. For good outcome prediction, a specificity of ≥80% was used. Added value of EEG-R was the increase in specificity when combined with EEG background, neurological examination, and somatosensory evoked potentials (SSEPs).Of 160 patients enrolled, 149 were available for analyses. Absence of EEG-R for poor outcome prediction had a specificity of 82% and a sensitivity of 73%. For good outcome prediction, specificity was 73% and sensitivity 82%. Specificity for poor outcome prediction increased from 98% to 99% when EEG-R was added to a multimodal model. For good outcome prediction, specificity increased from 70% to 89%.EEG-R testing in itself is not sufficiently reliable for outcome prediction in patients after CA. For poor outcome prediction, it has no substantial added value to EEG background, neurological examination, and SSEPs. For prediction of good outcome, EEG-R seems to have added value. ANN NEUROL 2019.

  View details for DOI 10.1002/ana.25507

  View details for PubMedID 31124174

  View details for PubMedCentralID PMC6618107

• Comparison of machine learning models for seizure prediction in hospitalized patients. Annals of clinical and translational neurology Struck, A. F., Rodriguez-Ruiz, A. A., Osman, G., Gilmore, E. J., Haider, H. A., Dhakar, M. B., Schrettner, M., Lee, J. W., Gaspard, N., Hirsch, L. J., Westover, M. B. 2019; 6 (7): 1239-1247

  Abstract

  To compare machine learning methods for predicting inpatient seizures risk and determine the feasibility of 1-h screening EEG to identify low-risk patients (<5% seizures risk in 48 h).The Critical Care EEG Monitoring Research Consortium (CCEMRC) multicenter database contains 7716 continuous EEGs (cEEG). Neural networks (NN), elastic net logistic regression (EN), and sparse linear integer model (RiskSLIM) were trained to predict seizures. RiskSLIM was used previously to generate 2HELPS2B model of seizure predictions. Data were divided into training (60% for model fitting) and evaluation (40% for model evaluation) cohorts. Performance was measured using area under the receiver operating curve (AUC), mean risk calibration (CAL), and negative predictive value (NPV). A secondary analysis was performed using Monte Carlo simulation (MCS) to normalize all EEG recordings to 48 h and use only the first hour of EEG as a "screening EEG" to generate predictions.RiskSLIM recreated the 2HELPS2B model. All models had comparable AUC: evaluation cohort (NN: 0.85, EN: 0.84, 2HELPS2B: 0.83) and MCS (NN: 0.82, EN; 0.82, 2HELPS2B: 0.81) and NPV (absence of seizures in the group that the models predicted to be low risk): evaluation cohort (NN: 97%, EN: 97%, 2HELPS2B: 97%) and MCS (NN: 97%, EN: 99%, 2HELPS2B: 97%). 2HELPS2B model was able to identify the largest proportion of low-risk patients.For seizure risk stratification of hospitalized patients, the RiskSLIM generated 2HELPS2B model compares favorably to the complex NN and EN generated models. 2HELPS2B is able to accurately and quickly identify low-risk patients with only a 1-h screening EEG.

  View details for DOI 10.1002/acn3.50817

  View details for PubMedID 31353866

  View details for PubMedCentralID PMC6649418

• Polypharmacy, Gait Performance, and Falls in Community-Dwelling Older Adults. Results from the Gait and Brain Study. Journal of the American Geriatrics Society Montero-Odasso, M., Sarquis-Adamson, Y., Song, H. Y., Bray, N. W., Pieruccini-Faria, F., Speechley, M. 2019; 67 (6): 1182-1188

  Abstract

  Polypharmacy, defined as the use of five or more medications, has been repeatedly linked to fall incidence, and recently it was cross-sectionally associated with gait disturbances. Our objectives were to evaluate cross-sectional and longitudinal associations between polypharmacy and gait performance in a well-established clinic-based cohort study. We also assessed whether gait impairments could mediate associations between number of medications and fall incidence.Prospective cohort of community-dwelling older adults, with 5 years of follow-up.Geriatric clinics in an academic hospital in London, ON, Canada.Community-dwelling older adults aged 65 and older (n = 249; 76.6 ± 8.6 y; 63% women).Number of medications, quantitative spatiotemporal gait parameters, and fall incidence during follow-up.The number of medications was cross-sectionally associated with poor gait performance (slow gait, speed p < .001; higher variability, p < .001; and higher stride, p < .001; step, p = .013, and double support times, p < .001). Prospectively, the number of medications was associated with overall gait decline (odds ratio = 1.23; 95% confidence interval [CI] = 1.13-1.33; p < .001), faster gait decline (hazard ratio = 4.62; 95%CI = 1.82-11.73; p < .001), and higher falls incidence (p = .006). These associations remained true after adjusting for age, sex, and accounting for "confounding by indication bias" by using a comorbidity propensity score adjustment. Each additional medication taken, significantly increased gait decline risk by 12% to 16% and fall incidence risk by 5% to 7%. Mediation analyses revealed that gait impairments in stride length, step length, and step width mediated the strength of the association between medications and fall incidence.Polypharmacy was cross-sectionally associated with poor gait performance and longitudinally associated with gait decline and fall incidence. Despite our use of propensity matching, confounding by indication could have influenced the results. Quantitative spatial gait parameters performance mediated the strength of the association between medications and falls, suggesting a role of gait disturbances in the medication-related falls pathway.

  View details for DOI 10.1111/jgs.15774

  View details for PubMedID 30698285

• Predictive Accuracy of Alpha-Delta Ratio on Quantitative Electroencephalography for Delayed Cerebral Ischemia in Patients with Aneurysmal Subarachnoid Hemorrhage: Meta-Analysis. World neurosurgery Yu, Z., Wen, D., Zheng, J., Guo, R., Li, H., You, C., Ma, L. 2019; 126: e510-e516

  Abstract

  Delayed cerebral ischemia (DCI) is significantly related to death and unfavorable functional outcome in patients with aneurysmal subarachnoid hemorrhage (SAH). The association between alpha-delta ratio (ADR) on quantitative electroencephalography (EEG) and DCI has been reported in several previous studies, but their results are conflicting. This meta-analysis was conducted to assess the accuracy of ADR for DCI prediction in patients with aneurysmal SAH.PubMed and Embase were systematically searched for related records. Study selection and data collection were completed by 2 investigators. Sensitivity, specificity, and their 95% confidence intervals (CIs) were pooled. A summary receiver operating characteristic curve was plotted to show the pooled accuracy. Deeks funnel plot was used to evaluate publication bias.Five studies were included in this meta-analysis. The pooled sensitivity and specificity of worsening ADR for DCI prediction in patients with aneurysmal SAH were 0.83 (95% CI 0.44-0.97) and 0.74 (95% CI 0.50-0.89), respectively. In addition, the area under the summary receiver operating characteristic curve was 0.84 (95% CI 0.81-0.87). No obvious publication bias was found using Deeks funnel plot (P = 0.29).Worsening ADR on quantitative EEG is a reliable predictor of DCI in patients with aneurysmal SAH. Further studies are still needed to confirm the role of quantitative EEG in DCI prediction.

  View details for DOI 10.1016/j.wneu.2019.02.082

  View details for PubMedID 30825635

• Variability in functional outcome and treatment practices by treatment center after out-of-hospital cardiac arrest: analysis of International Cardiac Arrest Registry INTENSIVE CARE MEDICINE May, T. L., Lary, C. W., Riker, R. R., Friberg, H., Patel, N., Soreide, E., McPherson, J. A., Unden, J., Hand, R., Sunde, K., Stammet, P., Rubertsson, S., Belohlvaek, J., Dupont, A., Hirsch, K. G., Valsson, F., Kern, K., Sadaka, F., Israelsson, J., Dankiewicz, J., Nielsen, N., Seder, D. B., Agarwal, S. 2019; 45 (5): 637–46

  View details for DOI 10.1007/s00134-019-05580-7

  View details for Web of Science ID 000465981200008

• Medical assertion classification in Chinese EMRs using attention enhanced neural network. Mathematical biosciences and engineering : MBE Zhang, Z. C., Zhang, Y., Zhou, T., Pang, Y. L. 2019; 16 (4): 1966-1977

  Abstract

  Electronic medical records (EMRs), such as hospital discharge summaries, contain a wealth of information only expressed in natural language. Automated methods for extracting information from these records must be able to recognize medical concepts in text and their semantic context. A contextual property critical to reason on information from EMRs is the doctor's belief status or assertion of the patient's medical problem. Research on the medical assertion classification (MAC) can establish the foundation for various health data analyses and clinical applications. However, previous MAC studies are mainly based on traditional machine learning methods which mostly require manually constructed features and the original unlabeled data cannot be easily and effectively applied to classification or classification tasks. Furthermore, external medical knowledge such as various medical dictionary bases, which provides rich explain and definition information about medical entity, is rarely utilized in existing neural network models of medical information extraction. In this study, we propose a deep neural network architecture enhanced by medical knowledge attention layer through combining GRU neural network with CNN model to classify the assertion type of medical problem such as disease and symptom in Chinese EMRs. The attention layer in the model is applied to integrate entity representations learned from medical dictionary bases as query for encoding. Experimental results on own manually annotated corpus indicate our approach achieves better performance compared to existing methods.

  View details for DOI 10.3934/mbe.2019096

  View details for PubMedID 31137195

• Lateralized periodic discharges frequency correlates with glucose metabolism. Neurology Subramaniam, T., Jain, A., Hall, L. T., Cole, A. J., Westover, M. B., Rosenthal, E. S., Struck, A. F. 2019; 92 (7): e670-e674

  Abstract

  To investigate the correlation between characteristics of lateralized periodic discharges (LPDs) and glucose metabolism measured by 18F-fluorodeoxyglucose (FDG)-PET.We retrospectively reviewed medical records to identify patients who underwent FDG-PET during EEG monitoring with LPDs present during the FDG uptake period. Two blinded board-certified neurophysiologists independently interpreted EEGs. FDG uptake was measured using standardized uptake value (SUV). Structural images were fused with PET images to aid with localization of SUV. Two PET readers independently measured maximum SUV. Relative SUV values were obtained by normalization of the maximum SUV to the SUV of pons (SUVRpons). LPD frequency was analyzed both as a categorical variable and as a continuous measure. Other secondary variables included duration, amplitude, presence of structural lesion, and "plus" EEG features such as rhythmic or fast sharp activity.Nine patients were identified and 7 had a structural etiology for LPDs. Analysis using frequency as a categorical variable and continuous variable showed an association between increased LPD frequency and increased ipsilateral SUVRpons (p = 0.02). Metabolism associated with LPDs (0.5 Hz as a baseline) increased by a median of 100% at 1 Hz and for frequencies >1 Hz increased by a median of 309%. There were no statistically significant differences in SUVRpons for other factors including duration (p = 0.10), amplitude (p = 0.80), structural etiology (p = 0.55), or "plus" features such as rhythmic or fast sharp activity (p = 0.84).Metabolic activity increases monotonically with LPD frequency. LPD frequency should be a measure of interest when developing neuroprotection strategies in critical neurologic illness.

  View details for DOI 10.1212/WNL.0000000000006903

  View details for PubMedID 30635488

  View details for PubMedCentralID PMC6382363

• Brain age from the electroencephalogram of sleep. Neurobiology of aging Sun, H., Paixao, L., Oliva, J. T., Goparaju, B., Carvalho, D. Z., van Leeuwen, K. G., Akeju, O., Thomas, R. J., Cash, S. S., Bianchi, M. T., Westover, M. B. 2019; 74: 112-120

  Abstract

  The human electroencephalogram (EEG) of sleep undergoes profound changes with age. These changes can be conceptualized as "brain age (BA)," which can be compared to chronological age to reflect the degree of deviation from normal aging. Here, we develop an interpretable machine learning model to predict BA based on 2 large sleep EEG data sets: the Massachusetts General Hospital (MGH) sleep lab data set (N = 2532; ages 18-80); and the Sleep Heart Health Study (SHHS, N = 1974; ages 40-80). The model obtains a mean absolute deviation of 7.6 years between BA and chronological age (CA) in healthy participants in the MGH data set. As validation, a subset of SHHS containing longitudinal EEGs 5.2 years apart shows an average of 5.4 years increase in BA. Participants with significant neurological or psychiatric disease exhibit a mean excess BA, or "brain age index" (BAI = BA-CA) of 4 years relative to healthy controls. Participants with hypertension and diabetes have a mean excess BA of 3.5 years. The findings raise the prospect of using the sleep EEG as a potential biomarker for healthy brain aging.

  View details for DOI 10.1016/j.neurobiolaging.2018.10.016

  View details for PubMedID 30448611

  View details for PubMedCentralID PMC6478501

• Detecting abnormal electroencephalograms using deep convolutional networks. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology van Leeuwen, K. G., Sun, H., Tabaeizadeh, M., Struck, A. F., van Putten, M. J., Westover, M. B. 2019; 130 (1): 77-84

  Abstract

  Electroencephalography (EEG) is a central part of the medical evaluation for patients with neurological disorders. Training an algorithm to label the EEG normal vs abnormal seems challenging, because of EEG heterogeneity and dependence of contextual factors, including age and sleep stage. Our objectives were to validate prior work on an independent data set suggesting that deep learning methods can discriminate between normal vs abnormal EEGs, to understand whether age and sleep stage information can improve discrimination, and to understand what factors lead to errors.We train a deep convolutional neural network on a heterogeneous set of 8522 routine EEGs from the Massachusetts General Hospital. We explore several strategies for optimizing model performance, including accounting for age and sleep stage.The area under the receiver operating characteristic curve (AUC) on an independent test set (n = 851) is 0.917 marginally improved by including age (AUC = 0.924), and both age and sleep stages (AUC = 0.925), though not statistically significant.The model architecture generalizes well to an independent dataset. Adding age and sleep stage to the model does not significantly improve performance.Insights learned from misclassified examples, and minimal improvement by adding sleep stage and age suggest fruitful directions for further research.

  View details for DOI 10.1016/j.clinph.2018.10.012

  View details for PubMedID 30481649

  View details for PubMedCentralID PMC6309707

• Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network NATURE MEDICINE Hannun, A. Y., Rajpurkar, P., Haghpanahi, M., Tison, G. H., Bourn, C., Turakhia, M. P., Ng, A. Y. 2019; 25 (1): 65-+

  View details for DOI 10.1038/s41591-018-0268-3

  View details for Web of Science ID 000455027700022

• A Systematic Review and Meta-Analysis Examining the Impact of Sleep Disturbance on Postoperative Delirium. Critical care medicine Fadayomi, A. B., Ibala, R., Bilotta, F., Westover, M. B., Akeju, O. 2018; 46 (12): e1204-e1212

  Abstract

  Basic science and clinical studies suggest that sleep disturbance may be a modifiable risk factor for postoperative delirium. We aimed to assess the association between preoperative sleep disturbance and postoperative delirium.We searched PubMed, Embase, CINAHL, Web of Science, and Cochrane from inception until May 31, 2017.We performed a systematic search of the literature for all studies that reported on sleep disruption and postoperative delirium excluding cross-sectional studies, case reports, and studies not reported in English language.Two authors independently performed study selection and data extraction. We calculated pooled effects estimates with a random-effects model constructed in Stata and evaluated the risk of bias by formal testing (Stata Corp V.14, College Station, TX), DATA SYNTHESIS:: We included 12 studies, from 1,238 citations that met our inclusion criteria. The pooled odds ratio for the association between sleep disturbance and postoperative delirium was 5.24 (95% CI, 3.61-7.60; p < 0.001 and I = 0.0%; p = 0.76). The pooled risk ratio for the association between sleep disturbance and postoperative delirium in prospective studies (n = 6) was 2.90 (95% CI, 2.28-3.69; p < 0.001 and I = 0.0%; p = 0.89). The odds ratio associated with obstructive sleep apnea and unspecified types of sleep disorder were 4.75 (95% CI, 2.65-8.54; p < 0.001 and I = 0.0%; p = 0.85) and 5.60 (95% CI, 3.46-9.07; p < 0.001 and I = 0.0%; p = 0.41), respectively. We performed Begg's and Egger's tests for publication bias and confirmed a null result for publication bias (p = 0.371 and 0.103, respectively).Preexisting sleep disturbances are likely associated with postoperative delirium. Whether system-level initiatives targeting patients with preoperative sleep disturbance may help reduce the prevalence, morbidity, and healthcare costs associated with postoperative delirium remains to be determined.

  View details for DOI 10.1097/CCM.0000000000003400

  View details for PubMedID 30222634

  View details for PubMedCentralID PMC6274586

• Predicting drug-resistant epilepsy - A machine learning approach based on administrative claims data. Epilepsy & behavior : E&B An, S., Malhotra, K., Dilley, C., Han-Burgess, E., Valdez, J. N., Robertson, J., Clark, C., Westover, M. B., Sun, J. 2018; 89: 118-125

  Abstract

  Patients with drug-resistant epilepsy (DRE) are at high risk of morbidity and mortality, yet their referral to specialist care is frequently delayed. The ability to identify patients at high risk of DRE at the time of treatment initiation, and to subsequently steer their treatment pathway toward more personalized interventions, has high clinical utility. Here, we aim to demonstrate the feasibility of developing algorithms for predicting DRE using machine learning methods. Longitudinal, intersected data sourced from US pharmacy, medical, and adjudicated hospital claims from 1,376,756 patients from 2006 to 2015 were analyzed; 292,892 met inclusion criteria for epilepsy, and 38,382 were classified as having DRE using a proxy measure for drug resistance. Patients were characterized using 1270 features reflecting demographics, comorbidities, medications, procedures, epilepsy status, and payer status. Data from 175,735 randomly selected patients were used to train three algorithms and from the remainder to assess the trained models' predictive power. A model with only age and sex was used as a benchmark. The best model, random forest, achieved an area under the receiver operating characteristic curve (95% confidence interval [CI]) of 0.764 (0.759, 0.770), compared with 0.657 (0.651, 0.663) for the benchmark model. Moreover, predicted probabilities for DRE were well-calibrated with the observed frequencies in the data. The model predicted drug resistance approximately 2 years before patients in the test dataset had failed two antiepileptic drugs (AEDs). Machine learning models constructed using claims data predicted which patients are likely to fail ≥3 AEDs and are at risk of developing DRE at the time of the first AED prescription. The use of such models can ensure that patients with predicted DRE receive specialist care with potentially more aggressive therapeutic interventions from diagnosis, to help reduce the serious sequelae of DRE.

  View details for DOI 10.1016/j.yebeh.2018.10.013

  View details for PubMedID 30412924

  View details for PubMedCentralID PMC6461470

• On the analysis of discrete time competing risks data. Biometrics Lee, M., Feuer, E. J., Fine, J. P. 2018; 74 (4): 1468-1481

  Abstract

  Regression methodology has been well developed for competing risks data with continuous event times, both for the cause-specific hazard and cumulative incidence functions. However, in many applications, including those from the Surveillance, Epidemiology, and End Results (SEER) program of the National Cancer Institute, the event times may be observed discretely. Naive application of continuous time regression methods to such data is not appropriate. We propose maximum likelihood inferences for estimation of model parameters for the discrete time cause-specific hazard functions, develop predictions for the associated cumulative incidence functions, and derive consistent variance estimators for the predicted cumulative incidence functions. The methods are readily implemented using standard software for generalized estimating equations, where models for different causes may be fitted separately. For the SEER data, it may be desirable to model different event types on different time scales and the methods are generalized to accommodate such scenarios, extending earlier work on continuous time data. Simulation studies demonstrate that the methods perform well in realistic set-ups. The methodology is illustrated with stage III colon cancer data from SEER.

  View details for DOI 10.1111/biom.12881

  View details for PubMedID 29665621

• Electroencephalogram Based Detection of Deep Sedation in ICU Patients Using Atomic Decomposition. IEEE transactions on bio-medical engineering Nagaraj, S. B., McClain, L. M., Boyle, E. J., Zhou, D. W., Ramaswamy, S. M., Biswal, S., Akeju, O., Purdon, P. L., Westover, M. B. 2018; 65 (12): 2684-2691

  Abstract

  This study was performed to evaluate how well states of deep sedation in ICU patients can be detected from the frontal electroencephalogram (EEG) using features based on the method of atomic decomposition (AD).We analyzed a clinical dataset of 20 min of EEG recordings per patient from 44 mechanically ventilated adult patients receiving sedatives in an intensive care unit (ICU) setting. Several features derived from AD of the EEG signal were used to discriminate between awake and sedated states. We trained support vector machine (SVM) classifiers using AD features and compared the classification performance with SVM classifiers trained using standard spectral and entropy features using leave-one-subject-out validation. The potential of each feature to discriminate between awake and sedated states was quantified using area under the receiver operating characteristic curve (AUC).The sedation level classification system using AD was able to reliably discriminate between sedated and awake states achieving an average AUC of 0.90, which was significantly better () than performance achieved using spectral (AUC = 0.86) and entropy (AUC = 0.81) domain features. A combined feature set consisting of AD, entropy, and spectral features provided better discrimination (AUC = 0.91, ) than any individual feature set.Features derived from the atomic decomposition of EEG signals provide useful discriminative information about the depth of sedation in ICU patients.With further refinement and external validation, the proposed system may be able to assist clinical staff with continuous surveillance of sedation levels in mechanically ventilated critically ill ICU patients.

  View details for DOI 10.1109/TBME.2018.2813265

  View details for PubMedID 29993386

  View details for PubMedCentralID PMC6424570

• Estimating the False Positive Rate of Absent Somatosensory Evoked Potentials in Cardiac Arrest Prognostication. Critical care medicine Amorim, E., Ghassemi, M. M., Lee, J. W., Greer, D. M., Kaplan, P. W., Cole, A. J., Cash, S. S., Bianchi, M. T., Westover, M. B. 2018; 46 (12): e1213-e1221

  Abstract

  Absence of somatosensory evoked potentials is considered a nearly perfect predictor of poor outcome after cardiac arrest. However, reports of good outcomes despite absent somatosensory evoked potentials and high rates of withdrawal of life-sustaining therapies have raised concerns that estimates of the prognostic value of absent somatosensory evoked potentials may be biased by self-fulfilling prophecies. We aimed to develop an unbiased estimate of the false positive rate of absent somatosensory evoked potentials as a predictor of poor outcome after cardiac arrest.PubMed.We selected 35 studies in cardiac arrest prognostication that reported somatosensory evoked potentials.In each study, we identified rates of withdrawal of life-sustaining therapies and good outcomes despite absent somatosensory evoked potentials. We appraised studies for potential biases using the Quality in Prognosis Studies tool. Using these data, we developed a statistical model to estimate the false positive rate of absent somatosensory evoked potentials adjusted for withdrawal of life-sustaining therapies rate.Two-thousand one-hundred thirty-three subjects underwent somatosensory evoked potential testing. Five-hundred ninety-four had absent somatosensory evoked potentials; of these, 14 had good functional outcomes. The rate of withdrawal of life-sustaining therapies for subjects with absent somatosensory evoked potential could be estimated in 14 of the 35 studies (mean 80%, median 100%). The false positive rate for absent somatosensory evoked potential in predicting poor neurologic outcome, adjusted for a withdrawal of life-sustaining therapies rate of 80%, is 7.7% (95% CI, 4-13%).Absent cortical somatosensory evoked potentials do not infallibly predict poor outcome in patients with coma following cardiac arrest. The chances of survival in subjects with absent somatosensory evoked potentials, though low, may be substantially higher than generally believed.

  View details for DOI 10.1097/CCM.0000000000003436

  View details for PubMedID 30247243

  View details for PubMedCentralID PMC6424571

• Effect of epileptiform abnormality burden on neurologic outcome and antiepileptic drug management after subarachnoid hemorrhage. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Zafar, S. F., Postma, E. N., Biswal, S., Boyle, E. J., Bechek, S., O'Connor, K., Shenoy, A., Kim, J., Shafi, M. S., Patel, A. B., Rosenthal, E. S., Westover, M. B. 2018; 129 (11): 2219-2227

  Abstract

  To quantify the burden of epileptiform abnormalities (EAs) including seizures, periodic and rhythmic activity, and sporadic discharges in patients with aneurysmal subarachnoid hemorrhage (aSAH), and assess the effect of EA burden and treatment on outcomes.Retrospective analysis of 136 high-grade aSAH patients. EAs were defined using the American Clinical Neurophysiology Society nomenclature. Burden was defined as prevalence of <1%, 1-9%, 10-49%, 50-89%, and >90% for each 18-24 hour epoch. Our outcome measure was 3-month Glasgow Outcome Score.47.8% patients had EAs. After adjusting for clinical covariates EA burden on first day of recording and maximum daily burden were associated with worse outcomes. Patients with higher EA burden were more likely to be treated with anti-epileptic drugs (AEDs) beyond the standard prophylactic protocol. There was no difference in outcomes between patients continued on AEDs beyond standard prophylaxis compared to those who were not.Higher burden of EAs in aSAH independently predicts worse outcome. Although nearly half of these patients received treatment, our data suggest current AED management practices may not influence outcome.EA burden predicts worse outcomes and may serve as a target for prospective interventional controlled studies to directly assess the impact of AEDs, and create evidence-based treatment protocols.

  View details for DOI 10.1016/j.clinph.2018.08.015

  View details for PubMedID 30212805

  View details for PubMedCentralID PMC6478499

• EEG Reactivity Evaluation Practices for Adult and Pediatric Hypoxic-Ischemic Coma Prognostication in North America. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Amorim, E., Gilmore, E. J., Abend, N. S., Hahn, C. D., Gaspard, N., Herman, S. T., Hirsch, L. J., Lee, J. W., Cash, S. S., Westover, M. B. 2018; 35 (6): 510-514

  Abstract

  The aim of this study was to assess the variability in EEG reactivity evaluation practices during cardiac arrest prognostication.A survey of institutional representatives from North American academic hospitals participating in the Critical Care EEG Monitoring Research Consortium was conducted to assess practice patterns involving EEG reactivity evaluation. This 10-question multiple-choice survey evaluated metrics related to technical, interpretation, personnel, and procedural aspects of bedside EEG reactivity testing and interpretation specific to cardiac arrest prognostication. One response per hospital was obtained.Responses were received from 25 hospitals, including 7 pediatric hospitals. A standardized EEG reactivity protocol was available in 44% of centers. Sixty percent of respondents believed that reactivity interpretation was subjective. Reactivity bedside testing always (100%) started during hypothermia and was performed daily during monitoring in the majority (71%) of hospitals. Stimulation was performed primarily by neurodiagnostic technologists (76%). The mean number of activation procedures modalities tested was 4.5 (SD 2.1). The most commonly used activation procedures were auditory (83.3%), nail bed pressure (63%), and light tactile stimuli (63%). Changes in EEG amplitude alone were not considered consistent with EEG reactivity in 21% of centers.There is substantial variability in EEG reactivity evaluation practices during cardiac arrest prognostication among North American academic hospitals. Efforts are needed to standardize protocols and nomenclature according with national guidelines and promote best practices in EEG reactivity evaluation.

  View details for DOI 10.1097/WNP.0000000000000517

  View details for PubMedID 30216207

  View details for PubMedCentralID PMC6424574

• Bilateral independent periodic discharges are associated with electrographic seizures and poor outcome: A case-control study. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Osman, G., Rahangdale, R., Britton, J. W., Gilmore, E. J., Haider, H. A., Hantus, S., Herlopian, A., Hocker, S. E., Woo Lee, J., Legros, B., Mendoza, M., Punia, V., Rampal, N., Szaflarski, J. P., Wallace, A. D., Westover, M. B., Hirsch, L. J., Gaspard, N. 2018; 129 (11): 2284-2289

  Abstract

  To determine the clinical correlates bilateral independent periodic discharges (BIPDs) and their association with electrographic seizures and outcome.Retrospective case-control study of patients with BIPDs compared to patients without periodic discharges ("No PDs") and patients with lateralized periodic discharges ("LPDs"), matched for age, etiology and level of alertness.We included 85 cases and 85 controls in each group. The most frequent etiologies of BIPDs were stroke, CNS infections, and anoxic brain injury. Acute bilateral cerebral injury was more common in the BIPDs group than in the No PDs and LPDs groups (70% vs. 37% vs. 35%). Electrographic seizures were more common with BIPDs than in the absence of PDs (45% vs. 8%), but not than with LPDs (52%). Mortality was higher in the BIPDs group (36%) than in the No PDs group (18%), with fewer patients with BIPDs achieving good outcome (moderate disability or better; 18% vs. 36%), but not than in the LPDs group (24% mortality, 26% good outcome). In multivariate analyses, BIPDs remained associated with mortality (OR: 3.0 [1.4-6.4]) and poor outcome (OR: 2.9 [1.4-6.2]).BIPDs are caused by bilateral acute brain injury and are associated with a high risk of electrographic seizures and of poor outcome.BIPDs are uncommon but their identification in critically ill patients has potential important implications, both in terms of clinical management and prognostication.

  View details for DOI 10.1016/j.clinph.2018.07.025

  View details for PubMedID 30227348

  View details for PubMedCentralID PMC6785981

• Antiepileptic drug treatment after an unprovoked first seizure: A decision analysis. Neurology Bao, E. L., Chao, L. Y., Ni, P., Moura, L. M., Cole, A. J., Cash, S. S., Hoch, D. B., Bianchi, M. T., Westover, M. B. 2018; 91 (15): e1429-e1439

  Abstract

  To compare the expected quality-adjusted life-years (QALYs) in adult patients undergoing immediate vs deferred antiepileptic drug (AED) treatment after a first unprovoked seizure.We constructed a simulated clinical trial (Markov decision model) to compare immediate vs deferred AED treatment after a first unprovoked seizure in adults. Three base cases were considered, representing patients with varying degrees of seizure recurrence risk and effect of seizures on quality of life (QOL). Cohort simulation was performed to determine which treatment strategy would maximize the patient's expected QALYs. Sensitivity analyses were guided by clinical data to define decision thresholds across plausible measurement ranges, including seizure recurrence rate, effect of seizure recurrence on QOL, and efficacy of AEDs.For patients with a moderate risk of recurrent seizures (52.0% over 10 years after first seizure), immediate AED treatment maximized QALYs compared to deferred treatment. Sensitivity analyses showed that for the preferred choice to change to deferred AED treatment, key clinical measures needed to reach implausible values were 10-year seizure recurrence rate ≤38.0%, QOL reduction with recurrent seizures ≤0.06, and efficacy of AEDs on lowering seizure recurrence rate ≤16.3%.Our model determined that immediate AED treatment is preferable to deferred treatment in adult first-seizure patients over a wide and clinically relevant range of variables. Furthermore, our analysis suggests that the 10-year seizure recurrence rate that justifies AED treatment (38.0%) is substantially lower than the 60% threshold used in the current definition of epilepsy.

  View details for DOI 10.1212/WNL.0000000000006319

  View details for PubMedID 30209239

  View details for PubMedCentralID PMC6177278

• Electrophysiological mechanisms of human memory consolidation. Nature communications Zhang, H., Fell, J., Axmacher, N. 2018; 9 (1): 4103

  Abstract

  Consolidation stabilizes memory traces after initial encoding. Rodent studies suggest that memory consolidation depends on replay of stimulus-specific activity patterns during fast hippocampal "ripple" oscillations. Here, we measured replay in intracranial electroencephalography recordings in human epilepsy patients, and related replay to ripples. Stimulus-specific activity was identified using representational similarity analysis and then tracked during waking rest and sleep after encoding. Stimulus-specific gamma (30-90 Hz) activity during early (100-500 ms) and late (500-1200 ms) encoding is spontaneously reactivated during waking state and sleep, independent of later memory. Ripples during nREM sleep, but not during waking state, trigger replay of activity from the late time window specifically for remembered items. Ripple-triggered replay of activity from the early time window during nREM sleep is enhanced for forgotten items. These results provide the first electrophysiological evidence for replay related to memory consolidation in humans, and point to a prominent role of nREM ripple-triggered replay in consolidation processes.

  View details for DOI 10.1038/s41467-018-06553-y

  View details for PubMedID 30291240

  View details for PubMedCentralID PMC6173724

• Interictal Epileptiform Discharge Detection in EEG in Different Practice Settings. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Halford, J. J., Westover, M. B., LaRoche, S. M., Macken, M. P., Kutluay, E., Edwards, J. C., Bonilha, L., Kalamangalam, G. P., Ding, K., Hopp, J. L., Arain, A., Dawson, R. A., Martz, G. U., Wolf, B. J., Waters, C. G., Dean, B. C. 2018; 35 (5): 375-380

  Abstract

  The goal of the study was to measure the performance of academic and private practice (PP) neurologists in detecting interictal epileptiform discharges in routine scalp EEG recordings.Thirty-five EEG scorers (EEGers) participated (19 academic and 16 PP) and marked the location of ETs in 200 30-second EEG segments using a web-based EEG annotation system. All participants provided board certification status, years of Epilepsy Fellowship Training (EFT), and years in practice. The Persyst P13 automated IED detection algorithm was also run on the EEG segments for comparison.Academic EEGers had an average of 1.66 years of EFT versus 0.50 years of EFT for PP EEGers (P < 0.0001) and had higher rates of board certification. Inter-rater agreement for the 35 EEGers was fair. There was higher performance for EEGers in academics, with at least 1.5 years of EFT, and with American Board of Clinical Neurophysiology and American Board of Psychiatry and Neurology-E specialty board certification. The Persyst P13 algorithm at its default setting (perception value = 0.4) did not perform as well at the EEGers, but at substantially higher perception value settings, the algorithm performed almost as well human experts.Inter-rater agreement among EEGers in both academic and PP settings varies considerably. Practice location, years of EFT, and board certification are associated with significantly higher performance for IED detection in routine scalp EEG. Continued medical education of PP neurologists and neurologists without EFT is needed to improve routine scalp EEG interpretation skills. The performance of automated detection algorithms is approaching that of human experts.

  View details for DOI 10.1097/WNP.0000000000000492

  View details for PubMedID 30028830

  View details for PubMedCentralID PMC6126936

• Timing matters: Impact of anticonvulsant drug treatment and spikes on seizure risk in benign epilepsy with centrotemporal spikes. Epilepsia open Xie, W., Ross, E. E., Kramer, M. A., Eden, U. T., Chu, C. J. 2018; 3 (3): 409-417

  Abstract

  Benign epilepsy with centrotemporal spikes (BECTS) is a common, self-limited epilepsy syndrome affecting school-age children. Classic interictal epileptiform discharges (IEDs) confirm diagnosis, and BECTS is presumed to be pharmacoresponsive. As seizure risk decreases in time with this disease, we hypothesize that the impact of IEDs and anticonvulsive drug (ACD) treatment on the risk of subsequent seizure will differ based on disease duration.We calculate subsequent seizure risk following diagnosis in a large retrospective cohort of children with BECTS (n = 130), evaluating the impact of IEDs and ACD treatment in the first, second, third, and fourth years of disease. We use a Kaplan-Meier survival analysis and logistic regression models. Patients were censored if they were lost to follow-up or if they changed group status.Two-thirds of children had a subsequent seizure within 2 years of diagnosis. The majority of children had a subsequent seizure within 3 years despite treatment. The presence of IEDs on electroencephalography (EEG) did not impact subsequent seizure risk early in the disease. By the fourth year of disease, all children without IEDs remained seizure free, whereas one-third of children with IEDs at this stage had a subsequent seizure. Conversely, ACD treatment corresponded with lower risk of seizure early in the disease but did not impact seizure risk in later years.In this cohort, the majority of children with BECTS had a subsequent seizure despite treatment. In addition, ACD treatment and IEDs predicted seizure risk at specific points of disease duration. Future prospective studies are needed to validate these exploratory findings.

  View details for DOI 10.1002/epi4.12248

  View details for PubMedID 30187012

  View details for PubMedCentralID PMC6119752

• You Snooze, You Win: the PhysioNet/Computing in Cardiology Challenge 2018. Computing in cardiology Ghassemi, M. M., Moody, B. E., Lehman, L. H., Song, C., Li, Q., Sun, H., Mark, R. G., Westover, M. B., Clifford, G. D. 2018; 45

  Abstract

  The PhysioNet/Computing in Cardiology Challenge 2018 focused on the use of various physiological signals (EEG, EOG, EMG, ECG, SaO2) collected during polysomnographic sleep studies to detect sources of arousal (non-apnea) during sleep. A total of 1,983 polysomnographic recordings were made available to the entrants. The arousal labels for 994 of the recordings were made available in a public training set while 989 labels were retained in a hidden test set. Challengers were asked to develop an algorithm that could label the presence of arousals within the hidden test set. The performance metric used to assess entrants was the area under the precision-recall curve. A total of twenty-two independent teams entered the Challenge, deploying a variety of methods from generalized linear models to deep neural networks.

  View details for DOI 10.22489/cinc.2018.049

  View details for PubMedID 34796237

  View details for PubMedCentralID PMC8596964

• EEG findings in CAR T-cell therapy-related encephalopathy. Neurology Herlopian, A., Dietrich, J., Abramson, J. S., Cole, A. J., Westover, M. B. 2018; 91 (5): 227-229

  View details for DOI 10.1212/WNL.0000000000005910

  View details for PubMedID 29959264

  View details for PubMedCentralID PMC6093761

• Rapid Annotation of Seizures and Interictal-ictal Continuum EEG Patterns. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Jing, J., d’Angremont, E., Zafar, S., Rosenthal, E. S., Tabaeizadeh, M., Ebrahim, S., Dauwels, J., Westover, M. B. 2018; 2018: 3394-3397

  Abstract

  Seizures, status epilepticus, and seizure-like rhythmic or periodic activities are common, pathological, harmful states of brain electrical activity seen in the electroencephalogram (EEG) of patients during critical medical illnesses or acute brain injury. Accumulating evidence shows that these states, when prolonged, cause neurological injury. In this study we developed a valid method to automatically discover a small number of homogeneous pattern clusters, to facilitate efficient interactive labelling by EEG experts. 592 time domain and spectral features were extracted from continuous EEG (cEEG) data of 369 ICU (intensive care unit) patients. For each patient, feature dimensionality was reduced using principal component analysis (PCA), retaining 95% of the variance. K-medoids clustering was applied to learn a local dictionary from each patient, consisting of k=100 exemplars/words. Changepoint detection (CPD) was utilized to break each EEG into segments. A bag-of-words (BoW) representation was computed for each segment, specifically, a normalized histogram of the words found within each segment. Segments were further clustered using the BoW histograms by Affinity Propagation (AP) using a χ2 distance to measure similarities between histograms. The resulting 30 50 clusters for each patient were scored by EEG experts through labeling only the cluster medoids. Embedding methods t-SNE (t-distributed stochastic neighbor embedding) and PCA were used to provide a 2D representation for visualization and exploration of the data. Our results illustrate that it takes approximately 3 minutes to annotate 24 hours of cEEG by experts, which is at least 60 times faster than unaided manual review.

  View details for DOI 10.1109/EMBC.2018.8513059

  View details for PubMedID 30441116

  View details for PubMedCentralID PMC6776236

• Real-Time, Automated Detection of Ventilator-Associated Events: Avoiding Missed Detections, Misclassifications, and False Detections Due to Human Error. Infection control and hospital epidemiology Shenoy, E. S., Rosenthal, E. S., Shao, Y. P., Biswal, S., Ghanta, M., Ryan, E. E., Suslak, D., Swanson, N., Junior, V. M., Hooper, D. C., Westover, M. B. 2018; 39 (7): 826-833

  Abstract

  OBJECTIVETo validate a system to detect ventilator associated events (VAEs) autonomously and in real time.DESIGNRetrospective review of ventilated patients using a secure informatics platform to identify VAEs (ie, automated surveillance) compared to surveillance by infection control (IC) staff (ie, manual surveillance), including development and validation cohorts.SETTINGThe Massachusetts General Hospital, a tertiary-care academic health center, during January-March 2015 (development cohort) and January-March 2016 (validation cohort).PATIENTSVentilated patients in 4 intensive care units.METHODSThe automated process included (1) analysis of physiologic data to detect increases in positive end-expiratory pressure (PEEP) and fraction of inspired oxygen (FiO2); (2) querying the electronic health record (EHR) for leukopenia or leukocytosis and antibiotic initiation data; and (3) retrieval and interpretation of microbiology reports. The cohorts were evaluated as follows: (1) manual surveillance by IC staff with independent chart review; (2) automated surveillance detection of ventilator-associated condition (VAC), infection-related ventilator-associated complication (IVAC), and possible VAP (PVAP); (3) senior IC staff adjudicated manual surveillance-automated surveillance discordance. Outcomes included sensitivity, specificity, positive predictive value (PPV), and manual surveillance detection errors. Errors detected during the development cohort resulted in algorithm updates applied to the validation cohort.RESULTSIn the development cohort, there were 1,325 admissions, 479 ventilated patients, 2,539 ventilator days, and 47 VAEs. In the validation cohort, there were 1,234 admissions, 431 ventilated patients, 2,604 ventilator days, and 56 VAEs. With manual surveillance, in the development cohort, sensitivity was 40%, specificity was 98%, and PPV was 70%. In the validation cohort, sensitivity was 71%, specificity was 98%, and PPV was 87%. With automated surveillance, in the development cohort, sensitivity was 100%, specificity was 100%, and PPV was 100%. In the validation cohort, sensitivity was 85%, specificity was 99%, and PPV was 100%. Manual surveillance detection errors included missed detections, misclassifications, and false detections.CONCLUSIONSManual surveillance is vulnerable to human error. Automated surveillance is more accurate and more efficient for VAE surveillance.Infect Control Hosp Epidemiol 2018;826-833.

  View details for DOI 10.1017/ice.2018.97

  View details for PubMedID 29769151

  View details for PubMedCentralID PMC6776240

• Sleep devices: wearables and nearables, informational and interventional, consumer and clinical. Metabolism: clinical and experimental Bianchi, M. T. 2018; 84: 99-108

  Abstract

  The field of sleep is in many ways ideally positioned to take full advantage of advancements in technology and analytics that is fueling the mobile health movement. Combining hardware and software advances with increasingly available big datasets that contain scored data obtained under gold standard sleep laboratory conditions completes the trifecta of this perfect storm. This review highlights recent developments in consumer and clinical devices for sleep, emphasizing the need for validation at multiple levels, with the ultimate goal of using personalized data and advanced algorithms to provide actionable information that will improve sleep health.

  View details for DOI 10.1016/j.metabol.2017.10.008

  View details for PubMedID 29080814

• A Mean Field Model of Acute Hepatic Encephalopathy. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Song, J., Sun, H., Jing, J., Carlos, L., Chao, L., Cash, S. S., Zhang, R., Westover, M. B. 2018; 2018: 2366-2369

  Abstract

  Acute hepatic encephalopathy (AHE) is a common form of delirium, a state of confusion, impaired attention, and decreased arousal due to acute liver failure. However, the neurophysiological mechanisms underlying AHE are poorly understood. In order to develop hypotheses for mechanisms of AHE, our work builds on an existing neural mean field model for similar EEG patterns in cerebral anoxia, the bursting Liley model. The model proposes that generalized periodic discharges, similar to the triphasic waves (TPWs) seen in severe AHE, arise through three types of processes a) increased neuronal excitability; b) defective brain energy metabolism leading to impaired synaptic transmission; c) and enhanced postsynaptic inhibition mediated by increased GABA-ergic and glycinergic transmission. We relate the model parameters to human EEG data using a particle-filter based optimization method that matches the TPW inter-event-interval distribution of the model with that observed in patients EEGs. In this way our model relates microscopic mechanisms to EEG patterns. Our model represents a starting point for exploring the underlying mechanisms of brain dynamics in delirium.

  View details for DOI 10.1109/EMBC.2018.8512786

  View details for PubMedID 30440882

  View details for PubMedCentralID PMC7088433

• Rule of 100: a litmus test for informationless diagnostic tests. Postgraduate medical journal Westover, A. M., Shapiro, D., Westover, M. B., Bianchi, M. T. 2018; 94 (1112): 364-366

  View details for DOI 10.1136/postgradmedj-2018-135555

  View details for PubMedID 29514996

  View details for PubMedCentralID PMC6771257

• Randomized trial of lacosamide versus fosphenytoin for nonconvulsive seizures. Annals of neurology Husain, A. M., Lee, J. W., Kolls, B. J., Hirsch, L. J., Halford, J. J., Gupta, P. K., Minazad, Y., Jones, J. M., LaRoche, S. M., Herman, S. T., Swisher, C. B., Sinha, S. R., Palade, A., Dombrowski, K. E., Gallentine, W. B., Hahn, C. D., Gerard, E. E., Bhapkar, M., Lokhnygina, Y., Westover, M. B. 2018; 83 (6): 1174-1185

  Abstract

  The optimal treatment of nonconvulsive seizures in critically ill patients is uncertain. We evaluated the comparative effectiveness of the antiseizure drugs lacosamide (LCM) and fosphenytoin (fPHT) in this population.The TRENdS (Treatment of Recurrent Electrographic Nonconvulsive Seizures) study was a noninferiority, prospective, multicenter, randomized treatment trial of patients diagnosed with nonconvulsive seizures (NCSs) by continuous electroencephalography (cEEG). Treatment was randomized to intravenous (IV) LCM 400mg or IV fPHT 20mg phenytoin equivalents/kg. The primary endpoint was absence of electrographic seizures for 24 hours as determined by 1 blinded EEG reviewer. The frequency with which NCS control was achieved in each arm was compared, and the 90% confidence interval (CI) was determined. Noninferiority of LCM to fPHT was to be concluded if the lower bound of the CI for relative risk was >0.8.Seventy-four subjects were enrolled (37 LCM, 37 fPHT) between August 21, 2012 and December 20, 2013. The mean age was 63.6 years; 38 were women. Seizures were controlled in 19 of 30 (63.3%) subjects in the LCM arm and 16 of 32 (50%) subjects in the fPHT arm. LCM was noninferior to fPHT (p = 0.02), with a risk ratio of 1.27 (90% CI = 0.88-1.83). Treatment emergent adverse events (TEAEs) were similar in both arms, occurring in 9 of 35 (25.7%) LCM and 9 of 37 (24.3%) fPHT subjects (p = 1.0).LCM was noninferior to fPHT in controlling NCS, and TEAEs were comparable. LCM can be considered an alternative to fPHT in the treatment of NCSs detected on cEEG. Ann Neurol 2018;83:1174-1185.

  View details for DOI 10.1002/ana.25249

  View details for PubMedID 29733464

• Preferential degradation of cognitive networks differentiates Alzheimer's disease from ageing. Brain : a journal of neurology Chhatwal, J. P., Schultz, A. P., Johnson, K. A., Hedden, T., Jaimes, S., Benzinger, T. L., Jack, C., Ances, B. M., Ringman, J. M., Marcus, D. S., Ghetti, B., Farlow, M. R., Danek, A., Levin, J., Yakushev, I., Laske, C., Koeppe, R. A., Galasko, D. R., Xiong, C., Masters, C. L., Schofield, P. R., Kinnunen, K. M., Salloway, S., Martins, R. N., McDade, E., Cairns, N. J., Buckles, V. D., Morris, J. C., Bateman, R., Sperling, R. A. 2018; 141 (5): 1486-1500

  Abstract

  Converging evidence from structural, metabolic and functional connectivity MRI suggests that neurodegenerative diseases, such as Alzheimer's disease, target specific neural networks. However, age-related network changes commonly co-occur with neuropathological cascades, limiting efforts to disentangle disease-specific alterations in network function from those associated with normal ageing. Here we elucidate the differential effects of ageing and Alzheimer's disease pathology through simultaneous analyses of two functional connectivity MRI datasets: (i) young participants harbouring highly-penetrant mutations leading to autosomal-dominant Alzheimer's disease from the Dominantly Inherited Alzheimer's Network (DIAN), an Alzheimer's disease cohort in which age-related comorbidities are minimal and likelihood of progression along an Alzheimer's disease trajectory is extremely high; and (ii) young and elderly participants from the Harvard Aging Brain Study, a cohort in which imaging biomarkers of amyloid burden and neurodegeneration can be used to disambiguate ageing alone from preclinical Alzheimer's disease. Consonant with prior reports, we observed the preferential degradation of cognitive (especially the default and dorsal attention networks) over motor and sensory networks in early autosomal-dominant Alzheimer's disease, and found that this distinctive degradation pattern was magnified in more advanced stages of disease. Importantly, a nascent form of the pattern observed across the autosomal-dominant Alzheimer's disease spectrum was also detectable in clinically normal elderly with clear biomarker evidence of Alzheimer's disease pathology (preclinical Alzheimer's disease). At the more granular level of individual connections between node pairs, we observed that connections within cognitive networks were preferentially targeted in Alzheimer's disease (with between network connections relatively spared), and that connections between positively coupled nodes (correlations) were preferentially degraded as compared to connections between negatively coupled nodes (anti-correlations). In contrast, ageing in the absence of Alzheimer's disease biomarkers was characterized by a far less network-specific degradation across cognitive and sensory networks, of between- and within-network connections, and of connections between positively and negatively coupled nodes. We go on to demonstrate that formalizing the differential patterns of network degradation in ageing and Alzheimer's disease may have the practical benefit of yielding connectivity measurements that highlight early Alzheimer's disease-related connectivity changes over those due to age-related processes. Together, the contrasting patterns of connectivity in Alzheimer's disease and ageing add to prior work arguing against Alzheimer's disease as a form of accelerated ageing, and suggest multi-network composite functional connectivity MRI metrics may be useful in the detection of early Alzheimer's disease-specific alterations co-occurring with age-related connectivity changes. More broadly, our findings are consistent with a specific pattern of network degradation associated with the spreading of Alzheimer's disease pathology within targeted neural networks.

  View details for DOI 10.1093/brain/awy053

  View details for PubMedID 29522171

  View details for PubMedCentralID PMC5917745

• Continuous electroencephalography predicts delayed cerebral ischemia after subarachnoid hemorrhage: A prospective study of diagnostic accuracy. Annals of neurology Rosenthal, E. S., Biswal, S., Zafar, S. F., O'Connor, K. L., Bechek, S., Shenoy, A. V., Boyle, E. J., Shafi, M. M., Gilmore, E. J., Foreman, B. P., Gaspard, N., Leslie-Mazwi, T. M., Rosand, J., Hoch, D. B., Ayata, C., Cash, S. S., Cole, A. J., Patel, A. B., Westover, M. B. 2018; 83 (5): 958-969

  Abstract

  Delayed cerebral ischemia (DCI) is a common, disabling complication of subarachnoid hemorrhage (SAH). Preventing DCI is a key focus of neurocritical care, but interventions carry risk and cannot be applied indiscriminately. Although retrospective studies have identified continuous electroencephalographic (cEEG) measures associated with DCI, no study has characterized the accuracy of cEEG with sufficient rigor to justify using it to triage patients to interventions or clinical trials. We therefore prospectively assessed the accuracy of cEEG for predicting DCI, following the Standards for Reporting Diagnostic Accuracy Studies.We prospectively performed cEEG in nontraumatic, high-grade SAH patients at a single institution. The index test consisted of clinical neurophysiologists prospectively reporting prespecified EEG alarms: (1) decreasing relative alpha variability, (2) decreasing alpha-delta ratio, (3) worsening focal slowing, or (4) late appearing epileptiform abnormalities. The diagnostic reference standard was DCI determined by blinded, adjudicated review. Primary outcome measures were sensitivity and specificity of cEEG for subsequent DCI, determined by multistate survival analysis, adjusted for baseline risk.One hundred three of 227 consecutive patients were eligible and underwent cEEG monitoring (7.7-day mean duration). EEG alarms occurred in 96.2% of patients with and 19.6% without subsequent DCI (1.9-day median latency, interquartile range = 0.9-4.1). Among alarm subtypes, late onset epileptiform abnormalities had the highest predictive value. Prespecified EEG findings predicted DCI among patients with low (91% sensitivity, 83% specificity) and high (95% sensitivity, 77% specificity) baseline risk.cEEG accurately predicts DCI following SAH and may help target therapies to patients at highest risk of secondary brain injury. Ann Neurol 2018;83:958-969.

  View details for DOI 10.1002/ana.25232

  View details for PubMedID 29659050

  View details for PubMedCentralID PMC6021198

• CLASSIFIER CASCADE TO AID IN DETECTION OF EPILEPTIFORM TRANSIENTS IN INTERICTAL EEG. Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference) Bagheri, E., Jin, J., Dauwels, J., Cash, S., Westover, M. B. 2018; 2018: 970-974

  Abstract

  The presence of Epileptiform Transients (ET) in the electroencephalogram (EEG) is a key finding in the medical workup of a patient with suspected epilepsy. Automated ET detection can increase the uniformity and speed of ET detection. Current ET detection methods suffer from insufficient precision and high false positive rates. Since ETs occur infrequently in the EEG of most patients, the majority of recordings comprise background EEG waveforms. In this work we establish a method to exclude as much background data as possible from EEG recordings by applying a classifier cascade. The remaining data can then be classified using other ET detection methods. We compare a single Support Vector Machine (SVM) to a cascade of SVMs for detecting ETs. Our results show that the precision and false positive rate improve significantly by incorporating a classifier cascade before ET detection. Our method can help improve the precision and false positive rate of an ET detection system. At a fixed sensitivity, we were able to improve precision by 6.78%; and at a fixed false positive rate, the sensitivity improved by 2.83%.

  View details for DOI 10.1109/ICASSP.2018.8461992

  View details for PubMedID 31582912

  View details for PubMedCentralID PMC6775762

• Epileptiform activity in traumatic brain injury predicts post-traumatic epilepsy. Annals of neurology Kim, J. A., Boyle, E. J., Wu, A. C., Cole, A. J., Staley, K. J., Zafar, S., Cash, S. S., Westover, M. B. 2018; 83 (4): 858-862

  Abstract

  We hypothesize that epileptiform abnormalities (EAs) in the electroencephalogram (EEG) during the acute period following traumatic brain injury (TBI) independently predict first-year post-traumatic epilepsy (PTE1 ). We analyze PTE1 risk factors in two cohorts matched for TBI severity and age (n = 50). EAs independently predict risk for PTE1 (odds ratio [OR], 3.16 [0.99, 11.68]); subdural hematoma is another independent risk factor (OR, 4.13 [1.18, 39.33]). Differences in EA rates are apparent within 5 days following TBI. Our results suggest that increased EA prevalence identifies patients at increased risk for PTE1 , and that EAs acutely post-TBI can identify patients most likely to benefit from antiepileptogenesis drug trials. Ann Neurol 2018;83:858-862.

  View details for DOI 10.1002/ana.25211

  View details for PubMedID 29537656

  View details for PubMedCentralID PMC5912971

• Blood Glucose Variability: A Strong Independent Predictor of Neurological Outcomes in Aneurysmal Subarachnoid Hemorrhage. Journal of intensive care medicine Okazaki, T., Hifumi, T., Kawakita, K., Shishido, H., Ogawa, D., Okauchi, M., Shindo, A., Kawanishi, M., Tamiya, T., Kuroda, Y. 2018; 33 (3): 189-195

  Abstract

  In patients with aneurysmal subarachnoid hemorrhage (SAH), increased glucose variability (GV) is associated with increased mortality and cerebral infarction; however, there are no reports demonstrating an association between GV and neurological outcome. This study investigated whether GV had an independent effect on neurological outcomes in patients with SAH in the intensive care unit.Consecutive adult patients hospitalized with SAH between January 1, 2009, and May 31, 2015 (N = 122) were retrospectively reviewed. Univariate/multivariate analyses were performed to identify independent predictors of poor neurological outcome. Patients were divided according to the mean glucose level (80-139 vs 140-200 mg/dL) and further subdivided using quartiles (Q) of the standard deviation (SD, representing variability) of the glucose level (Q1, Q2 + 3, and Q4).Unfavorable neurological outcomes occurred in 44.2% of the patients. On multiple regression analysis, age, Hunt and Kosnik grade, SD of glucose (odds ratio [OR], 1.09; 95% confidence interval [CI], 1.02-1.17; P < .01), and minimum blood glucose level (OR, 0.95; 95% CI, 0.91-0.99; P < .01) were significantly associated with unfavorable neurological outcomes. Both groups (mean glucose levels: 80-139 and 140-200 mg/dL groups) had increasing unfavorable neurological outcomes with increasing SD of glucose (Q1, 15.0%; Q2 + 3, 40.0%; Q4, 52.4% and Q1, 44.4%; Q2 + 3, 50%; Q4, 88.9% in the 80-139 and 140-200 mg/dL groups, respectively). Patients with minimum glucose of <90 mg/dL comprised >50% of unfavorable neurological outcome.Increased GV was an independent predictor of unfavorable neurological outcomes in patients with SAH.

  View details for DOI 10.1177/0885066616669328

  View details for PubMedID 27630011

• ADARRI: a novel method to detect spurious R-peaks in the electrocardiogram for heart rate variability analysis in the intensive care unit. Journal of clinical monitoring and computing Rebergen, D. J., Nagaraj, S. B., Rosenthal, E. S., Bianchi, M. T., van Putten, M. J., Westover, M. B. 2018; 32 (1): 53-61

  Abstract

  We developed a simple and fully automated method for detecting artifacts in the R-R interval (RRI) time series of the ECG that is tailored to the intensive care unit (ICU) setting. From ECG recordings of 50 adult ICU-subjects we selected 60 epochs with valid R-peak detections and 60 epochs containing artifacts leading to missed or false positive R-peak detections. Next, we calculated the absolute value of the difference between two adjacent RRIs (adRRI), and obtained the empirical probability distributions of adRRI values for valid R-peaks and artifacts. From these, we calculated an optimal threshold for separating adRRI values arising from artifact versus non-artefactual data. We compared the performance of our method with the methods of Berntson and Clifford on the same data. We identified 257,458 R-peak detections, of which 235,644 (91.5%) were true detections and 21,814 (8.5%) arose from artifacts. Our method showed superior performance for detecting artifacts with sensitivity 100%, specificity 99%, precision 99%, positive likelihood ratio of 100 and negative likelihood ratio <0.001 compared to Berntson's and Clifford's method with a sensitivity, specificity, precision and positive and negative likelihood ratio of 99%, 78%, 82%, 4.5, 0.013 for Berntson's method and 55%, 98%, 96%, 27.5, 0.460 for Clifford's method, respectively. A novel algorithm using a patient-independent threshold derived from the distribution of adRRI values in ICU ECG data identifies artifacts accurately, and outperforms two other methods in common use. Furthermore, the threshold was calculated based on real data from critically ill patients and the algorithm is easy to implement.

  View details for DOI 10.1007/s10877-017-9999-9

  View details for PubMedID 28210934

  View details for PubMedCentralID PMC5559344

• Reliability of the American Academy of Sleep Medicine Rules for Assessing Sleep Depth in Clinical Practice JOURNAL OF CLINICAL SLEEP MEDICINE Younes, M., Kuna, S. T., Pack, A. I., Walsh, J. K., Kushida, C. A., Staley, B., Pien, G. W. 2018; 14 (2): 205–13

  Abstract

  The American Academy of Sleep Medicine has published manuals for scoring polysomnograms that recommend time spent in non-rapid eye movement sleep stages (stage N1, N2, and N3 sleep) be reported. Given the well-established large interrater variability in scoring stage N1 and N3 sleep, we determined the range of time in stage N1 and N3 sleep scored by a large number of technologists when compared to reasonably estimated true values.Polysomnograms of 70 females were scored by 10 highly trained sleep technologists, two each from five different academic sleep laboratories. Range and confidence interval (CI = difference between the 5th and 95th percentiles) of the 10 times spent in stage N1 and N3 sleep assigned in each polysomnogram were determined. Average values of times spent in stage N1 and N3 sleep generated by the 10 technologists in each polysomnogram were considered representative of the true values for the individual polysomnogram. Accuracy of different technologists in estimating delta wave duration was determined by comparing their scores to digitally determined durations.The CI range of the ten N1 scores was 4 to 39 percent of total sleep time (% TST) in different polysomnograms (mean CI ± standard deviation = 11.1 ± 7.1 % TST). Corresponding range for N3 was 1 to 28 % TST (14.4 ± 6.1 % TST). For stage N1 and N3 sleep, very low or very high values were reported for virtually all polysomnograms by different technologists. Technologists varied widely in their assignment of stage N3 sleep, scoring that stage when the digitally determined time of delta waves ranged from 3 to 17 seconds.Manual scoring of non-rapid eye movement sleep stages is highly unreliable among highly trained, experienced technologists. Measures of sleep continuity and depth that are reliable and clinically relevant should be a focus of clinical research.

  View details for PubMedID 29351821

  View details for PubMedCentralID PMC5786839

• The Maximal Oxygen Uptake Verification Phase: a Light at the End of the Tunnel? Sports medicine - open Schaun, G. Z. 2017; 3 (1): 44

  Abstract

  Commonly performed during an incremental test to exhaustion, maximal oxygen uptake (V̇O2max) assessment has become a recurring practice in clinical and experimental settings. To validate the test, several criteria were proposed. In this context, the plateau in oxygen uptake (V̇O2) is inconsistent in its frequency, reducing its usefulness as a robust method to determine "true" V̇O2max. Moreover, secondary criteria previously suggested, such as expiratory exchange ratios or percentages of maximal heart rate, are highly dependent on protocol design and often are achieved at V̇O2 percentages well below V̇O2max. Thus, an alternative method termed verification phase was proposed. Currently, it is clear that the verification phase can be a practical and sensitive method to confirm V̇O2max; however, procedures to conduct it are not standardized across the literature and no previous research tried to summarize how it has been employed. Therefore, in this review the knowledge on the verification phase was updated, while suggestions on how it can be performed (e.g. intensity, duration, recovery) were provided according to population and protocol design. Future studies should focus to identify a verification protocol feasible for different populations and to compare square-wave and multistage verification phases. Additionally, studies assessing verification phases in different patient populations are still warranted.

  View details for DOI 10.1186/s40798-017-0112-1

  View details for PubMedID 29218470

  View details for PubMedCentralID PMC5721097

• Association of an Electroencephalography-Based Risk Score With Seizure Probability in Hospitalized Patients. JAMA neurology Struck, A. F., Ustun, B., Ruiz, A. R., Lee, J. W., LaRoche, S. M., Hirsch, L. J., Gilmore, E. J., Vlachy, J., Haider, H. A., Rudin, C., Westover, M. B. 2017; 74 (12): 1419-1424

  Abstract

  Continuous electroencephalography (EEG) use in critically ill patients is expanding. There is no validated method to combine risk factors and guide clinicians in assessing seizure risk.To use seizure risk factors from EEG and clinical history to create a simple scoring system associated with the probability of seizures in patients with acute illness.We used a prospective multicenter (Emory University Hospital, Brigham and Women's Hospital, and Yale University Hospital) database containing clinical and electrographic variables on 5427 continuous EEG sessions from eligible patients if they had continuous EEG for clinical indications, excluding epilepsy monitoring unit admissions. We created a scoring system model to estimate seizure risk in acutely ill patients undergoing continuous EEG. The model was built using a new machine learning method (RiskSLIM) that is designed to produce accurate, risk-calibrated scoring systems with a limited number of variables and small integer weights. We validated the accuracy and risk calibration of our model using cross-validation and compared its performance with models built with state-of-the-art logistic regression methods. The database was developed by the Critical Care EEG Research Consortium and used data collected over 3 years. The EEG variables were interpreted using standardized terminology by certified reviewers.All patients had more than 6 hours of uninterrupted EEG recordings.The main outcome was the average risk calibration error.There were 5427 continuous EEGs performed on 4772 participants (2868 men, 49.9%; median age, 61 years) performed at 3 institutions, without further demographic stratification. Our final model, 2HELPS2B, had an area under the curve of 0.819 and average calibration error of 2.7% (95% CI, 2.0%-3.6%). It included 6 variables with the following point assignments: (1) brief (ictal) rhythmic discharges (B[I]RDs) (2 points); (2) presence of lateralized periodic discharges, lateralized rhythmic delta activity, or bilateral independent periodic discharges (1 point); (3) prior seizure (1 point); (4) sporadic epileptiform discharges (1 point); (5) frequency greater than 2.0 Hz for any periodic or rhythmic pattern (1 point); and (6) presence of "plus" features (superimposed, rhythmic, sharp, or fast activity) (1 point). The probable seizure risk of each score was 5% for a score of 0, 12% for a score of 1, 27% for a score of 2, 50% for a score of 3, 73% for a score of 4, 88% for a score of 5, and greater than 95% for a score of 6 or 7.The 2HELPS2B model is a quick accurate tool to aid clinical judgment of the risk of seizures in critically ill patients.

  View details for DOI 10.1001/jamaneurol.2017.2459

  View details for PubMedID 29052706

  View details for PubMedCentralID PMC5822188

• Accuracy of Limited-Montage Electroencephalography in Monitoring Postanoxic Comatose Patients. Clinical EEG and neuroscience Pati, S., McClain, L., Moura, L., Fan, Y., Westover, M. B. 2017; 48 (6): 422-427

  Abstract

  Continuous EEG (cEEG) monitoring may help to identify the small percentage of adults with hypoxic-ischemic encephalopathy (HIE) who will regain consciousness if allowed sufficient time. However, the limited yield in this population has led some to question the cost-effectiveness cEEG monitoring in this population. We hypothesized that limited-montage cEEG could provide essentially the same neurophysiologic information at lower cost. In this proof of concept study, we aim to demonstrate the potentials of limited channel EEG in prognostication in postanoxic patients.We retrospectively reviewed cEEG data from cases monitored at our institution with conventional 21-channel EEG over a 6-month period. Twenty-eight cases were identified in which patients with HIE underwent cEEG for at least 24 hours. Gold-standard findings were determined by conventional visual analysis of the full cEEG, and 2 independent electroencephalographers scored the same data using only limited-montage (4-channel) views. The sensitivity and specificity of limited-montage cEEG review were compared with conventional analysis. We also compared the relative costs of conventional and limited-montage EEG.Using 4-channel limited montage cEEG, reviewers were able to classify accurately background continuity (in 88%), background amplitude (in 81%), maximum background frequency (in 70%), periodic epileptiform discharges, including a seizure (in 92%) and sporadic discharges (in 91%). All epileptiform features were detected with greater than 90% sensitivity and specificity. Eye movement artifact seen over bifrontal electrodes gave false positive detections of periodic epileptiform discharges in 31% of cases.Limited-channel continuous EEG monitoring can provide meaningful electrophysiological data that can be used for prognostication in postanoxic comatose patients. Limited channel EEG can be a cost-effective alternative to conventional EEG monitoring in post-anoxic comatose patients.

  View details for DOI 10.1177/1550059417715389

  View details for PubMedID 28641453

  View details for PubMedCentralID PMC5835011

• Large-Scale Automated Sleep Staging. Sleep Sun, H., Jia, J., Goparaju, B., Huang, G. B., Sourina, O., Bianchi, M. T., Westover, M. B. 2017; 40 (10)

  Abstract

  Automated sleep staging has been previously limited by a combination of clinical and physiological heterogeneity. Both factors are in principle addressable with large data sets that enable robust calibration. However, the impact of sample size remains uncertain. The objectives are to investigate the extent to which machine learning methods can approximate the performance of human scorers when supplied with sufficient training cases and to investigate how staging performance depends on the number of training patients, contextual information, model complexity, and imbalance between sleep stage proportions.A total of 102 features were extracted from six electroencephalography (EEG) channels in routine polysomnography. Two thousand nights were partitioned into equal (n = 1000) training and testing sets for validation. We used epoch-by-epoch Cohen's kappa statistics to measure the agreement between classifier output and human scorer according to American Academy of Sleep Medicine scoring criteria.Epoch-by-epoch Cohen's kappa improved with increasing training EEG recordings until saturation occurred (n = ~300). The kappa value was further improved by accounting for contextual (temporal) information, increasing model complexity, and adjusting the model training procedure to account for the imbalance of stage proportions. The final kappa on the testing set was 0.68. Testing on more EEG recordings leads to kappa estimates with lower variance.Training with a large data set enables automated sleep staging that compares favorably with human scorers. Because testing was performed on a large and heterogeneous data set, the performance estimate has low variance and is likely to generalize broadly.

  View details for DOI 10.1093/sleep/zsx139

  View details for PubMedID 29029305

  View details for PubMedCentralID PMC6251659

• Interictal epileptiform discharge characteristics underlying expert interrater agreement. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Bagheri, E., Dauwels, J., Dean, B. C., Waters, C. G., Westover, M. B., Halford, J. J. 2017; 128 (10): 1994-2005

  Abstract

  The presence of interictal epileptiform discharges (IED) in the electroencephalogram (EEG) is a key finding in the medical workup of a patient with suspected epilepsy. However, inter-rater agreement (IRA) regarding the presence of IED is imperfect, leading to incorrect and delayed diagnoses. An improved understanding of which IED attributes mediate expert IRA might help in developing automatic methods for IED detection able to emulate the abilities of experts. Therefore, using a set of IED scored by a large number of experts, we set out to determine which attributes of IED predict expert agreement regarding the presence of IED.IED were annotated on a 5-point scale by 18 clinical neurophysiologists within 200 30-s EEG segments from recordings of 200 patients. 5538 signal analysis features were extracted from the waveforms, including wavelet coefficients, morphological features, signal energy, nonlinear energy operator response, electrode location, and spectrogram features. Feature selection was performed by applying elastic net regression and support vector regression (SVR) was applied to predict expert opinion, with and without the feature selection procedure and with and without several types of signal normalization.Multiple types of features were useful for predicting expert annotations, but particular types of wavelet features performed best. Local EEG normalization also enhanced best model performance. As the size of the group of EEGers used to train the models was increased, the performance of the models leveled off at a group size of around 11.The features that best predict inter-rater agreement among experts regarding the presence of IED are wavelet features, using locally standardized EEG. Our models for predicting expert opinion based on EEGer's scores perform best with a large group of EEGers (more than 10).By examining a large group of EEG signal analysis features we found that wavelet features with certain wavelet basis functions performed best to identify IEDs. Local normalization also improves predictability, suggesting the importance of IED morphology over amplitude-based features. Although most IED detection studies in the past have used opinion from three or fewer experts, our study suggests a "wisdom of the crowd" effect, such that pooling over a larger number of expert opinions produces a better correlation between expert opinion and objectively quantifiable features of the EEG.

  View details for DOI 10.1016/j.clinph.2017.06.252

  View details for PubMedID 28837905

  View details for PubMedCentralID PMC5842710

• Response. Sleep medicine Bianchi, M. T., Thomas, R. J., Westover, M. B. 2017; 38: 160-161

  View details for DOI 10.1016/j.sleep.2017.07.017

  View details for PubMedID 28843388

  View details for PubMedCentralID PMC9847345

• Computer-Interpreted Electrocardiograms: Benefits and Limitations. Journal of the American College of Cardiology Schläpfer, J., Wellens, H. J. 2017; 70 (9): 1183-1192

  Abstract

  Computerized interpretation of the electrocardiogram (CIE) was introduced to improve the correct interpretation of the electrocardiogram (ECG), facilitating health care decision making and reducing costs. Worldwide, millions of ECGs are recorded annually, with the majority automatically analyzed, followed by an immediate interpretation. Limitations in the diagnostic accuracy of CIE were soon recognized and still persist, despite ongoing improvement in ECG algorithms. Unfortunately, inexperienced physicians ordering the ECG may fail to recognize interpretation mistakes and accept the automated diagnosis without criticism. Clinical mismanagement may result, with the risk of exposing patients to useless investigations or potentially dangerous treatment. Consequently, CIE over-reading and confirmation by an experienced ECG reader are essential and are repeatedly recommended in published reports. Implementation of new ECG knowledge is also important. The current status of automated ECG interpretation is reviewed, with suggestions for improvement.

  View details for DOI 10.1016/j.jacc.2017.07.723

  View details for PubMedID 28838369

• 26th Annual Computational Neuroscience Meeting (CNS*2017): Part 3 Antwerp, Belgium. 15-20 July 2017 Abstracts BMC NEUROSCIENCE [Anonymous] 2017; 18: 95–176

  View details for DOI 10.1186/s12868-017-0372-1

  View details for Web of Science ID 000468460900001

• Time-dependent risk of seizures in critically ill patients on continuous electroencephalogram. Annals of neurology Struck, A. F., Osman, G., Rampal, N., Biswal, S., Legros, B., Hirsch, L. J., Westover, M. B., Gaspard, N. 2017; 82 (2): 177-185

  Abstract

  Find the optimal continuous electroencephalographic (CEEG) monitoring duration for seizure detection in critically ill patients.We analyzed prospective data from 665 consecutive CEEGs, including clinical factors and time-to-event emergence of electroencephalographic (EEG) findings over 72 hours. Clinical factors were selected using logistic regression. EEG risk factors were selected a priori. Clinical factors were used for baseline (pre-EEG) risk. EEG findings were used for the creation of a multistate survival model with 3 states (entry, EEG risk, and seizure). EEG risk state is defined by emergence of epileptiform patterns.The clinical variables of greatest predictive value were coma (31% had seizures; odds ratio [OR] = 1.8, p < 0.01) and history of seizures, either remotely or related to acute illness (34% had seizures; OR = 3.0, p < 0.001). If there were no epileptiform findings on EEG, the risk of seizures within 72 hours was between 9% (no clinical risk factors) and 36% (coma and history of seizures). If epileptiform findings developed, the seizure incidence was between 18% (no clinical risk factors) and 64% (coma and history of seizures). In the absence of epileptiform EEG abnormalities, the duration of monitoring needed for seizure risk of <5% was between 0.4 hours (for patients who are not comatose and had no prior seizure) and 16.4 hours (comatose and prior seizure).The initial risk of seizures on CEEG is dependent on history of prior seizures and presence of coma. The risk of developing seizures on CEEG decays to <5% by 24 hours if no epileptiform EEG abnormalities emerge, independent of initial clinical risk factors. Ann Neurol 2017;82:177-185.

  View details for DOI 10.1002/ana.24985

  View details for PubMedID 28681492

  View details for PubMedCentralID PMC5842678

• Performance of Spectrogram-Based Seizure Identification of Adult EEGs by Critical Care Nurses and Neurophysiologists. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Amorim, E., Williamson, C. A., Moura, L. M., Shafi, M. M., Gaspard, N., Rosenthal, E. S., Guanci, M. M., Rajajee, V., Westover, M. B. 2017; 34 (4): 359-364

  Abstract

  Continuous EEG screening using spectrograms or compressed spectral arrays (CSAs) by neurophysiologists has shorter review times with minimal loss of sensitivity for seizure detection when compared with visual analysis of raw EEG. Limited data are available on the performance characteristics of CSA-based seizure detection by neurocritical care nurses.This is a prospective cross-sectional study that was conducted in two academic neurocritical care units and involved 33 neurointensive care unit nurses and four neurophysiologists.All nurses underwent a brief training session before testing. Forty two-hour CSA segments of continuous EEG were reviewed and rated for the presence of seizures. Two experienced clinical neurophysiologists masked to the CSA data performed conventional visual analysis of the raw EEG and served as the gold standard. The overall accuracy was 55.7% among nurses and 67.5% among neurophysiologists. Nurse seizure detection sensitivity was 73.8%, and the false-positive rate was 1-per-3.2 hours. Sensitivity and false-alarm rate for the neurophysiologists was 66.3% and 1-per-6.4 hours, respectively. Interrater agreement for seizure screening was fair for nurses (Gwet AC1 statistic: 43.4%) and neurophysiologists (AC1: 46.3%).Training nurses to perform seizure screening utilizing continuous EEG CSA displays is feasible and associated with moderate sensitivity. Nurses and neurophysiologists had comparable sensitivities, but nurses had a higher false-positive rate. Further work is needed to improve sensitivity and reduce false-alarm rates.

  View details for DOI 10.1097/WNP.0000000000000368

  View details for PubMedID 27930420

  View details for PubMedCentralID PMC5482787

• Design, implementation, and evaluation of a physiological closed-loop control device for medically-induced coma. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference , Purdon, P. L., Solt, K., Sims, N. M., Brown, E. N., Westover, M. B. 2017; 2017: 4313-4316

  Abstract

  Concerns regarding reliability and safety, as well as uncertainties about what constitutes adequate performance evaluation, have impeded the clinical translation of PCLC devices. We describe an attempt to address these challenges through design, implementation, and evaluation of a PCLC device for delivering medically-induced coma, with the intention to eventually conduct a clinical trial. This device works by automatically adjusting the infusion rate of propofol - a general anesthetic - in response to an electroencephalogram (EEG) pattern called burst suppression. We also designed and implemented a computational patient model which interfaces with hardware and produces realistic EEG signals in response to propofol infusion. The computational patient model is used in hardware-in-the-loop studies to evaluate the behavior of our PCLC device under realistic perturbations. Finally, we have tested the performance of our PCLC device in rodents. Results from these studies suggest that closed-loop control of medically-induced coma in humans is feasible and robust. Consequently, our work produced a PCLC device and relevant pre-clinical evidence in support of a pilot clinical trial.

  View details for DOI 10.1109/EMBC.2017.8037810

  View details for PubMedID 29060851

  View details for PubMedCentralID PMC5835010

• An open request to epidemiologists: please stop querying self-reported sleep duration. Sleep medicine Bianchi, M. T., Thomas, R. J., Westover, M. B. 2017; 35: 92-93

  View details for DOI 10.1016/j.sleep.2017.02.001

  View details for PubMedID 28284821

  View details for PubMedCentralID PMC9371612

• Automated epileptiform spike detection via affinity propagation-based template matching. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Thomas, J., , Dauwels, J., Cash, S. S., Westover, M. B. 2017; 2017: 3057-3060

  Abstract

  Interictal epileptiform spikes are the key diagnostic biomarkers for epilepsy. The clinical gold standard of spike detection is visual inspection performed by neurologists. This is a tedious, time-consuming, and expert-centered process. The development of automated spike detection systems is necessary in order to provide a faster and more reliable diagnosis of epilepsy. In this paper, we propose an efficient template matching spike detector based on a combination of spike and background waveform templates. We generate a template library by clustering a collection of spikes and background waveforms extracted from a database of 50 patients with epilepsy. We benchmark the performance of five clustering techniques based on the receiver operating characteristic (ROC) curves. In addition, background templates are integrated with existing spike templates to improve the overall performance. The affinity propagation-based template matching system with a combination of spike and background templates is shown to outperform the other four conventional methods with the highest area-under-curve (AUC) of 0.953.

  View details for DOI 10.1109/EMBC.2017.8037502

  View details for PubMedID 29060543

  View details for PubMedCentralID PMC5835014

• The continuum of spreading depolarizations in acute cortical lesion development: Examining Leão's legacy. Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism Hartings, J. A., Shuttleworth, C. W., Kirov, S. A., Ayata, C., Hinzman, J. M., Foreman, B., Andrew, R. D., Boutelle, M. G., Brennan, K. C., Carlson, A. P., Dahlem, M. A., Drenckhahn, C., Dohmen, C., Fabricius, M., Farkas, E., Feuerstein, D., Graf, R., Helbok, R., Lauritzen, M., Major, S., Oliveira-Ferreira, A. I., Richter, F., Rosenthal, E. S., Sakowitz, O. W., Sánchez-Porras, R., Santos, E., Schöll, M., Strong, A. J., Urbach, A., Westover, M. B., Winkler, M. K., Witte, O. W., Woitzik, J., Dreier, J. P. 2017; 37 (5): 1571-1594

  Abstract

  A modern understanding of how cerebral cortical lesions develop after acute brain injury is based on Aristides Leão's historic discoveries of spreading depression and asphyxial/anoxic depolarization. Treated as separate entities for decades, we now appreciate that these events define a continuum of spreading mass depolarizations, a concept that is central to understanding their pathologic effects. Within minutes of acute severe ischemia, the onset of persistent depolarization triggers the breakdown of ion homeostasis and development of cytotoxic edema. These persistent changes are diagnosed as diffusion restriction in magnetic resonance imaging and define the ischemic core. In delayed lesion growth, transient spreading depolarizations arise spontaneously in the ischemic penumbra and induce further persistent depolarization and excitotoxic damage, progressively expanding the ischemic core. The causal role of these waves in lesion development has been proven by real-time monitoring of electrophysiology, blood flow, and cytotoxic edema. The spreading depolarization continuum further applies to other models of acute cortical lesions, suggesting that it is a universal principle of cortical lesion development. These pathophysiologic concepts establish a working hypothesis for translation to human disease, where complex patterns of depolarizations are observed in acute brain injury and appear to mediate and signal ongoing secondary damage.

  View details for DOI 10.1177/0271678X16654495

  View details for PubMedID 27328690

  View details for PubMedCentralID PMC5435288

• Recording, analysis, and interpretation of spreading depolarizations in neurointensive care: Review and recommendations of the COSBID research group. Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism Dreier, J. P., Fabricius, M., Ayata, C., Sakowitz, O. W., Shuttleworth, C. W., Dohmen, C., Graf, R., Vajkoczy, P., Helbok, R., Suzuki, M., Schiefecker, A. J., Major, S., Winkler, M. K., Kang, E. J., Milakara, D., Oliveira-Ferreira, A. I., Reiffurth, C., Revankar, G. S., Sugimoto, K., Dengler, N. F., Hecht, N., Foreman, B., Feyen, B., Kondziella, D., Friberg, C. K., Piilgaard, H., Rosenthal, E. S., Westover, M. B., Maslarova, A., Santos, E., Hertle, D., Sánchez-Porras, R., Jewell, S. L., Balança, B., Platz, J., Hinzman, J. M., Lückl, J., Schoknecht, K., Schöll, M., Drenckhahn, C., Feuerstein, D., Eriksen, N., Horst, V., Bretz, J. S., Jahnke, P., Scheel, M., Bohner, G., Rostrup, E., Pakkenberg, B., Heinemann, U., Claassen, J., Carlson, A. P., Kowoll, C. M., Lublinsky, S., Chassidim, Y., Shelef, I., Friedman, A., Brinker, G., Reiner, M., Kirov, S. A., Andrew, R. D., Farkas, E., Güresir, E., Vatter, H., Chung, L. S., Brennan, K. C., Lieutaud, T., Marinesco, S., Maas, A. I., Sahuquillo, J., Dahlem, M. A., Richter, F., Herreras, O., Boutelle, M. G., Okonkwo, D. O., Bullock, M. R., Witte, O. W., Martus, P., van den Maagdenberg, A. M., Ferrari, M. D., Dijkhuizen, R. M., Shutter, L. A., Andaluz, N., Schulte, A. P., MacVicar, B., Watanabe, T., Woitzik, J., Lauritzen, M., Strong, A. J., Hartings, J. A. 2017; 37 (5): 1595-1625

  Abstract

  Spreading depolarizations (SD) are waves of abrupt, near-complete breakdown of neuronal transmembrane ion gradients, are the largest possible pathophysiologic disruption of viable cerebral gray matter, and are a crucial mechanism of lesion development. Spreading depolarizations are increasingly recorded during multimodal neuromonitoring in neurocritical care as a causal biomarker providing a diagnostic summary measure of metabolic failure and excitotoxic injury. Focal ischemia causes spreading depolarization within minutes. Further spreading depolarizations arise for hours to days due to energy supply-demand mismatch in viable tissue. Spreading depolarizations exacerbate neuronal injury through prolonged ionic breakdown and spreading depolarization-related hypoperfusion (spreading ischemia). Local duration of the depolarization indicates local tissue energy status and risk of injury. Regional electrocorticographic monitoring affords even remote detection of injury because spreading depolarizations propagate widely from ischemic or metabolically stressed zones; characteristic patterns, including temporal clusters of spreading depolarizations and persistent depression of spontaneous cortical activity, can be recognized and quantified. Here, we describe the experimental basis for interpreting these patterns and illustrate their translation to human disease. We further provide consensus recommendations for electrocorticographic methods to record, classify, and score spreading depolarizations and associated spreading depressions. These methods offer distinct advantages over other neuromonitoring modalities and allow for future refinement through less invasive and more automated approaches.

  View details for DOI 10.1177/0271678X16654496

  View details for PubMedID 27317657

  View details for PubMedCentralID PMC5435289

• Reply: Computer models to inform epilepsy surgery strategies: prediction of postoperative outcome. Brain : a journal of neurology Sinha, N., Dauwels, J., Kaiser, M., Cash, S. S., Westover, M. B., Wang, Y., Taylor, P. N. 2017; 140 (5): e31

  View details for DOI 10.1093/brain/awx068

  View details for PubMedID 28334902

  View details for PubMedCentralID PMC10448005

• A cost-effectiveness analysis of nasal surgery to increase continuous positive airway pressure adherence in sleep apnea patients with nasal obstruction. The Laryngoscope Kempfle, J. S., BuSaba, N. Y., Dobrowski, J. M., Westover, M. B., Bianchi, M. T. 2017; 127 (4): 977-983

  Abstract

  Nasal surgery has been implicated to improve continuous positive airway pressure (CPAP) compliance in patients with obstructive sleep apnea (OSA) and nasal obstruction. However, the cost-effectiveness of nasal surgery to improve CPAP compliance is not known. We modeled the cost-effectiveness of two types of nasal surgery versus no surgery in patients with OSA and nasal obstruction undergoing CPAP therapy.Cost-effectiveness decision tree model.We built a decision tree model to identify conditions under which nasal surgery would be cost-effective to improve CPAP adherence over the standard of care. We compared turbinate reduction and septoplasty to nonsurgical treatment over varied time horizons from a third-party payer perspective. We included variables for cost of untreated OSA, surgical cost and complications, improved compliance postoperatively, and quality of life.Our study identified nasal surgery as a cost-effective strategy to improve compliance of OSA patients using CPAP across a range of plausible model assumptions regarding the cost of untreated OSA, the probability of adherence improvement, and a chronic time horizon. The relatively lower surgical cost of turbinate reduction made it more cost-effective at earlier time horizons, whereas septoplasty became cost-effective after a longer timespan.Across a range of plausible values in a clinically relevant decision model, nasal surgery is a cost-effective strategy to improve CPAP compliance in OSA patients with nasal obstruction. Our results suggest that OSA patients with nasal obstruction who struggle with CPAP therapy compliance should undergo evaluation for nasal surgery.2c Laryngoscope, 127:977-983, 2017.

  View details for DOI 10.1002/lary.26257

  View details for PubMedID 27653626

  View details for PubMedCentralID PMC5483184

• Alternative remedies for insomnia: a proposed method for personalized therapeutic trials. Nature and science of sleep Romero, K., Goparaju, B., Russo, K., Westover, M. B., Bianchi, M. T. 2017; 9: 97-108

  Abstract

  Insomnia is a common symptom, with chronic insomnia being diagnosed in 5-10% of adults. Although many insomnia patients use prescription therapy for insomnia, the health benefits remain uncertain and adverse risks remain a concern. While similar effectiveness and risk concerns exist for herbal remedies, many individuals turn to such alternatives to prescriptions for insomnia. Like prescription hypnotics, herbal remedies that have undergone clinical testing often show subjective sleep improvements that exceed objective measures, which may relate to interindividual heterogeneity and/or placebo effects. Response heterogeneity can undermine traditional randomized trial approaches, which in some fields has prompted a shift toward stratified trials based on genotype or phenotype, or the so-called n-of-1 method of testing placebo versus active drug in within-person alternating blocks. We reviewed six independent compendiums of herbal agents to assemble a group of over 70 reported to benefit sleep. To bridge the gap between the unfeasible expectation of formal evidence in this space and the reality of common self-medication by those with insomnia, we propose a method for guided self-testing that overcomes certain operational barriers related to inter- and intraindividual sources of phenotypic variability. Patient-chosen outcomes drive a general statistical model that allows personalized self-assessment that can augment the open-label nature of routine practice. The potential advantages of this method include flexibility to implement for other (nonherbal) insomnia interventions.

  View details for DOI 10.2147/NSS.S128095

  View details for PubMedID 28360539

  View details for PubMedCentralID PMC5364017

• Electroencephalographic Periodic Discharges and Frequency-Dependent Brain Tissue Hypoxia in Acute Brain Injury. JAMA neurology Witsch, J., Frey, H. P., Schmidt, J. M., Velazquez, A., Falo, C. M., Reznik, M., Roh, D., Agarwal, S., Park, S., Connolly, E. S., Claassen, J. 2017; 74 (3): 301-309

  Abstract

  Periodic discharges (PDs) that do not meet seizure criteria, also termed the ictal interictal continuum, are pervasive on electroencephalographic (EEG) recordings after acute brain injury. However, their association with brain homeostasis and the need for clinical intervention remain unknown.To determine whether distinct PD patterns can be identified that, similar to electrographic seizures, cause brain tissue hypoxia, a measure of ongoing brain injury.This prospective cohort study included 90 comatose patients with high-grade spontaneous subarachnoid hemorrhage who underwent continuous surface (scalp) EEG (sEEG) recording and multimodality monitoring, including invasive measurements of intracortical (depth) EEG (dEEG), partial pressure of oxygen in interstitial brain tissue (Pbto2), and regional cerebral blood flow (CBF). Patient data were collected from June 1, 2006, to September 1, 2014, at a single tertiary care center. The retrospective analysis was performed from September 1, 2014, to May 1, 2016, with a hypothesis that the effect on brain tissue oxygenation was primarily dependent on the discharge frequency.Electroencephalographic recordings were visually classified based on PD frequency and spatial distribution of discharges. Correlations between mean multimodality monitoring data and change-point analyses were performed to characterize electrophysiological changes by applying bootstrapping.Of the 90 patients included in the study (26 men and 64 women; mean [SD] age, 55 [15] years), 32 (36%) had PDs on sEEG and dEEG recordings and 21 (23%) on dEEG recordings only. Frequencies of PDs ranged from 0.5 to 2.5 Hz. Median Pbto2 was 23 mm Hg without PDs compared with 16 mm Hg at 2.0 Hz and 14 mm Hg at 2.5 Hz (differences were significant for 0 vs 2.5 Hz based on bootstrapping). Change-point analysis confirmed a temporal association of high-frequency PD onset (≥2.0 Hz) and Pbto2 reduction (median normalized Pbto2 decreased by 25% 5-10 minutes after onset). Increased regional CBF of 21.0 mL/100 g/min for 0 Hz, 25.9 mL/100 g/min for 1.0 Hz, 27.5 mL/100 g/min for 1.5 Hz, and 34.7 mL/100 g/min for 2.0 Hz and increased global cerebral perfusion pressure of 91 mm Hg for 0 Hz, 100.5 mm Hg for 0.5 Hz, 95.5 mm Hg for 1.0 Hz, 97.0 mm Hg for 2.0 Hz, 98.0 mm Hg for 2.5 Hz, 95.0 mm Hg for 2.5 Hz, and 67.8 mm Hg for 3.0 Hz were seen for higher PD frequencies.These data give some support to consider redefining the continuum between seizures and PDs, suggesting that additional damage after acute brain injury may be reflected by frequency changes in electrocerebral recordings. Similar to seizures, cerebral blood flow increases in patients with PDs to compensate for the increased metabolic demand but higher-frequency PDs (>2 per second) may be inadequately compensated without an additional rise in CBF and associated with brain tissue hypoxia, or higher-frequency PDs may reflect inadequacies in brain compensatory mechanisms.

  View details for DOI 10.1001/jamaneurol.2016.5325

  View details for PubMedID 28097330

  View details for PubMedCentralID PMC5548418

• Interrater agreement in the interpretation of neonatal electroencephalography in hypoxic-ischemic encephalopathy. Epilepsia Wusthoff, C. J., Sullivan, J., Glass, H. C., Shellhaas, R. A., Abend, N. S., Chang, T., Tsuchida, T. N. 2017; 58 (3): 429-435

  Abstract

  Research using neonatal electroencephalography (EEG) has been limited by a lack of a standardized classification system and interpretation terminology. In 2013, the American Clinical Neurophysiology Society (ACNS) published a guideline for standardized terminology and categorization in the description of continuous EEG in neonates. We sought to assess interrater agreement for this neonatal EEG categorization system as applied by a group of pediatric neurophysiologists.A total of 60 neonatal EEG studies were collected from three institutions. All EEG segments were from term neonates with hypoxic-ischemic encephalopathy. Three pediatric neurophysiologists independently reviewed each record using the ACNS standardized scoring system. Unweighted kappa values were calculated for interrater agreement of categorical data across multiple observers.Interrater agreement was very good for identification of seizures (κ = 0.93, p < 0.001), with perfect agreement in 95% of records (57 of 60). Interrater agreement was moderate for classifying records as normal or having any abnormality (κ = 0.49, p < 0.001), with perfect agreement in 78% of records (47 of 60). Interrater agreement was good in classifying EEG backgrounds on a 5-category scale (normal, excessively discontinuous, burst suppression, status epilepticus, or electrocerebral inactivity) (κ = 0.70, p < 0.001), with perfect agreement in 72% of records (43 of 60). Other specific background features had lower agreement, including voltage (κ = 0.41, p < 0.001), variability (κ = 0.35, p < 0.001), symmetry (κ = 0.18, p = 0.01), presence of abnormal sharp waves (κ < 0.20, p < 0.05), and presence of brief rhythmic discharges (κ < 0.20, p < 0.05).We found good or very good interrater agreement applying the ACNS system for identification of seizures and classification of EEG background. Other specific EEG features showed limited interrater agreement. Of importance to both clinicians and researchers, our findings support using the ACNS system in identifying seizures and classifying backgrounds of neonatal EEG recordings, but also suggest limited reproducibility for certain other EEG features.

  View details for DOI 10.1111/epi.13661

  View details for PubMedID 28166364

  View details for PubMedCentralID PMC5339031

• Big data in sleep medicine: prospects and pitfalls in phenotyping. Nature and science of sleep Bianchi, M. T., Russo, K., Gabbidon, H., Smith, T., Goparaju, B., Westover, M. B. 2017; 9: 11-29

  Abstract

  Clinical polysomnography (PSG) databases are a rich resource in the era of "big data" analytics. We explore the uses and potential pitfalls of clinical data mining of PSG using statistical principles and analysis of clinical data from our sleep center. We performed retrospective analysis of self-reported and objective PSG data from adults who underwent overnight PSG (diagnostic tests, n=1835). Self-reported symptoms overlapped markedly between the two most common categories, insomnia and sleep apnea, with the majority reporting symptoms of both disorders. Standard clinical metrics routinely reported on objective data were analyzed for basic properties (missing values, distributions), pairwise correlations, and descriptive phenotyping. Of 41 continuous variables, including clinical and PSG derived, none passed testing for normality. Objective findings of sleep apnea and periodic limb movements were common, with 51% having an apnea-hypopnea index (AHI) >5 per hour and 25% having a leg movement index >15 per hour. Different visualization methods are shown for common variables to explore population distributions. Phenotyping methods based on clinical databases are discussed for sleep architecture, sleep apnea, and insomnia. Inferential pitfalls are discussed using the current dataset and case examples from the literature. The increasing availability of clinical databases for large-scale analytics holds important promise in sleep medicine, especially as it becomes increasingly important to demonstrate the utility of clinical testing methods in management of sleep disorders. Awareness of the strengths, as well as caution regarding the limitations, will maximize the productive use of big data analytics in sleep medicine.

  View details for DOI 10.2147/NSS.S130141

  View details for PubMedID 28243157

  View details for PubMedCentralID PMC5317347

• Selection of first-line therapy in multiple sclerosis using risk-benefit decision analysis. Neurology Bargiela, D., Bianchi, M. T., Westover, M. B., Chibnik, L. B., Healy, B. C., De Jager, P. L., Xia, Z. 2017; 88 (7): 677-684

  Abstract

  To integrate long-term measures of disease-modifying drug efficacy and risk to guide selection of first-line treatment of multiple sclerosis.We created a Markov decision model to evaluate disability worsening and progressive multifocal leukoencephalopathy (PML) risk in patients receiving natalizumab (NTZ), fingolimod (FGL), or glatiramer acetate (GA) over 30 years. Leveraging publicly available data, we integrated treatment utility, disability worsening, and risk of PML into quality-adjusted life-years (QALYs). We performed sensitivity analyses varying PML risk, mortality and morbidity, and relative risk of disease worsening across clinically relevant ranges.Over the entire reported range of NTZ-associated PML risk, NTZ as first-line therapy is predicted to provide a greater net benefit (15.06 QALYs) than FGL (13.99 QALYs) or GA (12.71 QALYs) treatment over 30 years, after accounting for loss of QALYs due to PML or death (resulting from all causes). NTZ treatment is associated with delayed worsening to an Expanded Disability Status Scale score ≥6.0 vs FGL or GA (22.7, 17.0, and 12.4 years, respectively). Compared to untreated patients, NTZ-treated patients have a greater relative risk of death in the early years of treatment that varies according to PML risk profile.NTZ as a first-line treatment is associated with the highest net benefit across full ranges of PML risk, mortality, and morbidity compared to FGL or GA. Integrated modeling of long-term treatment risks and benefits informs stratified clinical decision-making and can support patient counseling on selection of first-line treatment options.

  View details for DOI 10.1212/WNL.0000000000003612

  View details for PubMedID 28087821

  View details for PubMedCentralID PMC5317380

• cEEG electrode-related pressure ulcers in acutely hospitalized patients. Neurology. Clinical practice Moura, L. M., Carneiro, T. S., Kwasnik, D., Moura, V. F., Blodgett, C. S., Cohen, J., McKenna Guanci, M., Hoch, D. B., Hsu, J., Cole, A. J., Westover, M. B. 2017; 7 (1): 15-25

  Abstract

  Pressure ulcers resulting from continuous EEG (cEEG) monitoring in hospitalized patients have gained attention as a preventable medical complication. We measured their incidence and risk factors.We performed an observational investigation of cEEG-electrode-related pressure ulcers (EERPU) among acutely ill patients over a 22-month period. Variables analyzed included age, sex, monitoring duration, hospital location, application methods, vasopressor usage, nutritional status, skin allergies, fever, and presence/severity of EERPU. We examined risk for pressure ulcers vs monitoring duration using Kaplan-Meyer survival analysis, and performed multivariate risk assessment using Cox proportional hazard model.Among 1,519 patients, EERPU occurred in 118 (7.8%). Most (n = 109, 92.3%) consisted of hyperemia only without skin breakdown. A major predictor was monitoring duration, with 3-, 5-, and 10-day risks of 16%, 32%, and 60%, respectively. Risk factors included older age (mean age 60.65 vs 50.3, p < 0.01), care in an intensive care unit (9.37% vs 5.32%, p < 0.01), lack of a head wrap (8.31% vs 27.3%, p = 0.02), use of vasopressors (16.7% vs 9.64%, p < 0.01), enteral feeding (11.7% vs 5.45%, p = 0.04), and fever (18.4% vs 9.3%, p < 0.01). Elderly patients (71-80 years) were at higher risk (hazard ratio 6.84 [1.95-24], p < 0.01), even after accounting for monitoring time and other pertinent variables in multivariate analysis.EERPU are uncommon and generally mild. Elderly patients and those with more severe illness have higher risk of developing EERPU, and the risk increases as a function of monitoring duration.

  View details for DOI 10.1212/CPJ.0000000000000312

  View details for PubMedID 28243502

  View details for PubMedCentralID PMC5310208

• Epileptiform abnormalities predict delayed cerebral ischemia in subarachnoid hemorrhage. Clinical neurophysiology Kim, J. A., Rosenthal, E. S., Biswal, S., Zafar, S., SHENOY, A. V., O'Connor, K. L., Bechek, S. C., Valdery Moura, J., SHAFI, M. M., Patel, A. B., Cash, S. S., Westover, M. B. 2017

  Abstract

  To identify whether abnormal neural activity, in the form of epileptiform discharges and rhythmic or periodic activity, which we term here ictal-interictal continuum abnormalities (IICAs), are associated with delayed cerebral ischemia (DCI).Retrospective analysis of continuous electroencephalography (cEEG) reports and medical records from 124 patients with moderate to severe grade subarachnoid hemorrhage (SAH). We identified daily occurrence of seizures and IICAs. Using survival analysis methods, we estimated the cumulative probability of IICA onset time for patients with and without delayed cerebral ischemia (DCI).Our data suggest the presence of IICAs indeed increases the risk of developing DCI, especially when they begin several days after the onset of SAH. We found that all IICA types except generalized rhythmic delta activity occur more commonly in patients who develop DCI. In particular, IICAs that begin later in hospitalization correlate with increased risk of DCI.IICAs represent a new marker for identifying early patients at increased risk for DCI. Moreover, IICAs might contribute mechanistically to DCI and therefore represent a new potential target for intervention to prevent secondary cerebral injury following SAH.These findings imply that IICAs may be a novel marker for predicting those at higher risk for DCI development.

  View details for DOI 10.1016/j.clinph.2017.01.016

  View details for PubMedID 28258936

• Automated spike detection in EEG. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Webber, W. R., Lesser, R. P. 2017; 128 (1): 241-242

  View details for DOI 10.1016/j.clinph.2016.11.018

  View details for PubMedID 27940048

• Continuous EEG monitoring enhances multimodal outcome prediction in hypoxic-ischemic brain injury. Resuscitation Amorim, E., Rittenberger, J. C., Zheng, J. J., Westover, M. B., Baldwin, M. E., Callaway, C. W., Popescu, A. 2016; 109: 121-126

  Abstract

  Hypoxic brain injury is the largest contributor to disability and mortality after cardiac arrest. We aim to identify electroencephalogram (EEG) characteristics that can predict outcome on cardiac arrest patients treated with targeted temperature management (TTM).We retrospectively examined clinical, EEG, functional outcome at discharge, and in-hospital mortality for 373 adult subjects with return of spontaneous circulation after cardiac arrest. Poor outcome was defined as a Cerebral Performance Category score of 3-5. Pure suppression-burst (SB) was defined as SB not associated with status epilepticus (SE), seizures, or generalized periodic discharges.In-hospital mortality was 68.6% (N=256). Presence of both unreactive EEG background and SE was associated with a positive predictive value (PPV) of 100% (95% confidence interval: 0.96-1) and a false-positive rate (FPR) of 0% (95% CI: 0-0.11) for poor functional outcome. A prediction model including demographics data, admission exam, presence of status epilepticus, pure SB, and lack of EEG reactivity had an area under the curve of 0.92 (95% CI: 0.87-0.95) for poor functional outcome prediction, and 0.96 (95% CI: 0.94-0.98) for in-hospital mortality. Presence of pure SB (N=87) was confounded by anesthetics use in 83.9% of the cases, and was not an independent predictor of poor functional outcome, having a FPR of 23% (95% CI: 0.19-0.28).An unreactive EEG background and SE predicted poor functional outcome and in-hospital mortality in cardiac arrest patients undergoing TTM. Prognostic value of pure SB is confounded by use of sedative agents, and its use on prognostication decisions should be made with caution.

  View details for DOI 10.1016/j.resuscitation.2016.08.012

  View details for PubMedID 27554945

  View details for PubMedCentralID PMC5124407

• Rapid annotation of interictal epileptiform discharges via template matching under Dynamic Time Warping. Journal of neuroscience methods Jing, J., Dauwels, J., Rakthanmanon, T., Keogh, E., Cash, S. S., Westover, M. B. 2016; 274: 179-190

  Abstract

  EEG interpretation relies on experts who are in short supply. There is a great need for automated pattern recognition systems to assist with interpretation. However, attempts to develop such systems have been limited by insufficient expert-annotated data. To address these issues, we developed a system named NeuroBrowser for EEG review and rapid waveform annotation.At the core of NeuroBrowser lies on ultrafast template matching under Dynamic Time Warping, which substantially accelerates the task of annotation.Our results demonstrate that NeuroBrowser can reduce the time required for annotation of interictal epileptiform discharges by EEG experts by 20-90%, with an average of approximately 70%.In comparison with conventional manual EEG annotation, NeuroBrowser is able to save EEG experts approximately 70% on average of the time spent in annotating interictal epileptiform discharges. We have already extracted 19,000+ interictal epileptiform discharges from 100 patient EEG recordings. To our knowledge this represents the largest annotated database of interictal epileptiform discharges in existence.NeuroBrowser is an integrated system for rapid waveform annotation. While the algorithm is currently tailored to annotation of interictal epileptiform discharges in scalp EEG recordings, the concepts can be easily generalized to other waveforms and signal types.

  View details for DOI 10.1016/j.jneumeth.2016.02.025

  View details for PubMedID 26944098

  View details for PubMedCentralID PMC5519352

• Therapeutic coma for status epilepticus: Differing practices in a prospective multicenter study. Neurology Alvarez, V., Lee, J. W., Westover, M. B., Drislane, F. W., Novy, J., Faouzi, M., Marchi, N. A., Dworetzky, B. A., Rossetti, A. O. 2016; 87 (16): 1650-1659

  Abstract

  Our aim was to analyze and compare the use of therapeutic coma (TC) for refractory status epilepticus (SE) across different centers and its effect on outcome.Clinical data for all consecutive adults (>16 years) with SE of all etiologies (except postanoxic) admitted to 4 tertiary care centers belonging to Harvard Affiliated Hospitals (HAH) and the Centre Hospitalier Universitaire Vaudois (CHUV) were prospectively collected and analyzed for TC details, mortality, and duration of hospitalization.Two hundred thirty-six SE episodes in the CHUV and 126 in the HAH were identified. Both groups were homogeneous in demographics, comorbidities, SE characteristics, and Status Epilepticus Severity Score (STESS); TC was used in 25.4% of cases in HAH vs 9.75% in CHUV. After adjustment, TC use was associated with younger age, lower Charlson Comorbidity Index, increasing SE severity, refractory SE, and center (odds ratio 11.3 for HAH vs CHUV, 95% confidence interval 2.47-51.7). Mortality was associated with increasing Charlson Comorbidity Index and STESS, etiology, and refractory SE. Length of stay correlated with STESS, etiology, refractory SE, and use of TC (incidence rate ratio 1.6, 95% confidence interval 1.22-2.11).Use of TC for SE treatment seems markedly different between centers from the United States and Europe, and did not affect mortality considering the whole cohort. However, TC may increase length of hospital stay and related costs.This study provides Class III evidence that for patients with SE, TC does not significantly affect mortality. The study lacked the precision to exclude an important effect of TC on mortality.

  View details for DOI 10.1212/WNL.0000000000003224

  View details for PubMedID 27664985

  View details for PubMedCentralID PMC5085074

• Automatic Classification of Sedation Levels in ICU Patients Using Heart Rate Variability. Critical care medicine Nagaraj, S. B., McClain, L. M., Zhou, D. W., Biswal, S., Rosenthal, E. S., Purdon, P. L., Westover, M. B. 2016; 44 (9): e782-9

  Abstract

  To explore the potential value of heart rate variability features for automated monitoring of sedation levels in mechanically ventilated ICU patients.Multicenter, pilot study.Several ICUs at Massachusetts General Hospital, Boston, MA.Electrocardiogram recordings from 40 mechanically ventilated adult patients receiving sedatives in an ICU setting were used to develop and test the proposed automated system.Richmond Agitation-Sedation Scale scores were acquired prospectively to assess patient sedation levels and were used as ground truth. Richmond Agitation-Sedation Scale scores were grouped into four levels, denoted "unarousable" (Richmond Agitation- Sedation Scale = -5, -4), "sedated" (-3, -2, -1), "awake" (0), "agitated" (+1, +2, +3, +4). A multiclass support vector machine algorithm was used for classification. Classifier training and performance evaluations were carried out using leave-oneout cross validation. An overall accuracy of 69% was achieved for discriminating between the four levels of sedation. The proposed system was able to reliably discriminate (accuracy = 79%) between sedated (Richmond Agitation-Sedation Scale < 0) and nonsedated states (Richmond Agitation-Sedation Scale > 0).With further refinement, the methodology reported herein could lead to a fully automated system for depth of sedation monitoring. By enabling monitoring to be continuous, such technology may help clinical staff to monitor sedation levels more effectively and to reduce complications related to over- and undersedation.

  View details for DOI 10.1097/CCM.0000000000001708

  View details for PubMedID 27035240

  View details for PubMedCentralID PMC4987179

• Sensitivity of quantitative EEG for seizure identification in the intensive care unit NEUROLOGY Haider, H. A., Esteller, R., Hahn, C. D., Westover, M., Halford, J. J., Lee, J. W., Shafi, M. M., Gaspard, N., Herman, S. T., Gerard, E. E., Hirsch, L. J., Ehrenberg, J. A., LaRoche, S. M., Critical Care EEG Monitoring Res 2016; 87 (9): 935-944

  Abstract

  To evaluate the sensitivity of quantitative EEG (QEEG) for electrographic seizure identification in the intensive care unit (ICU).Six-hour EEG epochs chosen from 15 patients underwent transformation into QEEG displays. Each epoch was reviewed in 3 formats: raw EEG, QEEG + raw, and QEEG-only. Epochs were also analyzed by a proprietary seizure detection algorithm. Nine neurophysiologists reviewed raw EEGs to identify seizures to serve as the gold standard. Nine other neurophysiologists with experience in QEEG evaluated the epochs in QEEG formats, with and without concomitant raw EEG. Sensitivity and false-positive rates (FPRs) for seizure identification were calculated and median review time assessed.Mean sensitivity for seizure identification ranged from 51% to 67% for QEEG-only and 63%-68% for QEEG + raw. FPRs averaged 1/h for QEEG-only and 0.5/h for QEEG + raw. Mean sensitivity of seizure probability software was 26.2%-26.7%, with FPR of 0.07/h. Epochs with the highest sensitivities contained frequent, intermittent seizures. Lower sensitivities were seen with slow-frequency, low-amplitude seizures and epochs with rhythmic or periodic patterns. Median review times were shorter for QEEG (6 minutes) and QEEG + raw analysis (14.5 minutes) vs raw EEG (19 minutes; p = 0.00003).A panel of QEEG trends can be used by experts to shorten EEG review time for seizure identification with reasonable sensitivity and low FPRs. The prevalence of false detections confirms that raw EEG review must be used in conjunction with QEEG. Studies are needed to identify optimal QEEG trend configurations and the utility of QEEG as a screening tool for non-EEG personnel.This study provides Class II evidence that QEEG + raw interpreted by experts identifies seizures in patients in the ICU with a sensitivity of 63%-68% and FPR of 0.5 seizures per hour.

  View details for DOI 10.1212/WNL.0000000000003034

  View details for Web of Science ID 000383980600020

  View details for PubMedID 27466474

  View details for PubMedCentralID PMC5035158

• Decision analysis of intracranial monitoring in non-lesional epilepsy. Seizure Hotan, G. C., Struck, A. F., Bianchi, M. T., Eskandar, E. N., Cole, A. J., Westover, M. B. 2016; 40: 59-70

  Abstract

  Up to one third of epilepsy patients develop pharmacoresistant seizures and many benefit from resective surgery. However, patients with non-lesional focal epilepsy often require intracranial monitoring to localize the seizure focus. Intracranial monitoring carries operative morbidity risk and does not always succeed in localizing the seizures, making the benefit of this approach less certain. We performed a decision analysis comparing three strategies for patients with non-lesional focal epilepsy: (1) intracranial monitoring, (2) vagal nerve stimulator (VNS) implantation and (3) medical management to determine which strategy maximizes the expected quality-adjusted life years (QALYs) for our base cases.We constructed two base cases using parameters reported in the medical literature: (1) a young, otherwise healthy patient and (2) an elderly, otherwise healthy patient. We constructed a decision tree comprising strategies for the treatment of non-lesional epilepsy and two clinical outcomes: seizure freedom and no seizure freedom. Sensitivity analyses of probabilities at each branch were guided by data from the medical literature to define decision thresholds across plausible parameter ranges.Intracranial monitoring maximizes the expected QALYs for both base cases. The sensitivity analyses provide estimates of the values of key variables, such as the surgical risk or the chance of localizing the focus, at which intracranial monitoring is no longer favored.Intracranial monitoring is favored over VNS and medical management in young and elderly patients over a wide, clinically-relevant range of pertinent model variables such as the chance of localizing the seizure focus and the surgical morbidity rate.

  View details for DOI 10.1016/j.seizure.2016.06.010

  View details for PubMedID 27348062

  View details for PubMedCentralID PMC4967015

• Heart rate variability as a biomarker for sedation depth estimation in ICU patients. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Nagaraj, S. B., Ramaswamy, S. M., Biswal, S., Boyle, E. J., Zhou, D. W., Mcclain, L. M., Rosenthal, E. S., Purdon, P. L., Westover, M. B. 2016; 2016: 6397-6400

  Abstract

  An automated patient-specific system to classify the level of sedation in ICU patients using heart rate variability signal is presented in this paper. ECG from 70 mechanically ventilated adult patients with administered sedatives in an ICU setting were used to develop a support vector machine based system for sedation depth monitoring using several heart rate variability measures. A leave-one-subject-out cross validation was used for classifier training and performance evaluations. The proposed patient-specific system provided a sensitivity, specificity and an AUC of 64%, 84.8% and 0.72, respectively. It is hoped that with the help of additional physiological signals the proposed patient-specific sedation level prediction system could lead to a fully automated multimodal system to assist clinical staff in ICUs to interpret the sedation level of the patient.

  View details for DOI 10.1109/EMBC.2016.7592192

  View details for PubMedID 28269712

  View details for PubMedCentralID PMC5478422

• Clinical Development and Implementation of an Institutional Guideline for Prospective EEG Monitoring and Reporting of Delayed Cerebral Ischemia JOURNAL OF CLINICAL NEUROPHYSIOLOGY Muniz, C. F., Shenoy, A. V., O'Connor, K. L., Bechek, S. C., Boyle, E. J., Guanci, M. M., Tehan, T. M., Zafar, S. F., Cole, A. J., Patel, A. B., Westover, M. B., Rosenthal, E. S. 2016; 33 (3): 217-226

  Abstract

  Delayed cerebral ischemia (DCI) is the most common and disabling complication among patients admitted to the hospital for subarachnoid hemorrhage (SAH). Clinical and radiographic methods often fail to detect DCI early enough to avert irreversible injury. We assessed the clinical feasibility of implementing a continuous EEG (cEEG) ischemia monitoring service for early DCI detection as part of an institutional guideline. An institutional neuromonitoring guideline was designed by an interdisciplinary team of neurocritical care, clinical neurophysiology, and neurosurgery physicians and nursing staff and cEEG technologists. The interdisciplinary team focused on (1) selection criteria of high-risk patients, (2) minimization of safety concerns related to prolonged monitoring, (3) technical selection of quantitative and qualitative neurophysiologic parameters based on expert consensus and review of the literature, (4) a structured interpretation and reporting methodology, prompting direct patient evaluation and iterative neurocritical care, and (5) a two-layered quality assurance process including structured clinician interviews assessing events of neurologic worsening and an adjudicated consensus review of neuroimaging and medical records. The resulting guideline's clinical feasibility was then prospectively evaluated. The institutional SAH monitoring guideline used transcranial Doppler ultrasound and cEEG monitoring for vasospasm and ischemia monitoring in patients with either Fisher group 3 or Hunt-Hess grade IV or V SAH. Safety criteria focused on prevention of skin breakdown and agitation. Technical components included monitoring of transcranial Doppler ultrasound velocities and cEEG features, including quantitative alpha:delta ratio and percent alpha variability, qualitative evidence of new focal slowing, late-onset epileptiform activity, or overall worsening of background. Structured cEEG reports were introduced including verbal communication for findings concerning neurologic decline. The guideline was successfully implemented over 27 months, during which neurocritical care physicians referred 71 SAH patients for combined transcranial Doppler ultrasound and cEEG monitoring. The quality assurance process determined a DCI rate of 48% among the monitored population, more than 90% of which occurred during the duration of cEEG monitoring (mean 6.9 days) beginning 2.7 days after symptom onset. An institutional guideline implementing cEEG for SAH ischemia monitoring and reporting is feasible to implement and efficiently identify patients at high baseline risk of DCI during the period of monitoring.

  View details for DOI 10.1097/WNP.0000000000000281

  View details for Web of Science ID 000377825000008

  View details for PubMedID 27258445

  View details for PubMedCentralID PMC4907266

• Not a Simple Plumbing Problem: Updating Our Understanding of Delayed Cerebral Ischemia in Aneurysmal Subarachnoid Hemorrhage. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Westover, M. B., Gaspard, N. 2016; 33 (3): 171-3

  View details for DOI 10.1097/WNP.0000000000000269

  View details for PubMedID 27258439

  View details for PubMedCentralID PMC4894327

• Metabolic Correlates of the Ictal-Interictal Continuum: FDG-PET During Continuous EEG. Neurocritical care Struck, A. F., Westover, M. B., Hall, L. T., Deck, G. M., Cole, A. J., Rosenthal, E. S. 2016; 24 (3): 324-31

  Abstract

  Ictal-interictal continuum (IIC) continuous EEG (cEEG) patterns including periodic discharges and rhythmic delta activity are associated with poor outcome and in the appropriate clinical context, IIC patterns may represent "electroclinical" status epilepticus (SE). To clarify the significance of IIC patterns and their relationship to "electrographic" SE, we investigated FDG-PET imaging as a complementary metabolic biomarker of SE among patients with IIC patterns.A single-center prospective clinical database was ascertained for patients undergoing FDG-PET during cEEG. Following MRI-PET co-registration, the maximum standardized uptake value in cortical and subcortical regions was compared to contralateral homologous and cerebellar regions. Consensus cEEG review and clinical rating of etiology and treatment response were performed retrospectively with blinding. Electrographic SE was classified as discrete seizures without interictal recovery or >3-Hz rhythmic IIC patterns. Electroclinical SE was classified as IIC patterns with electrographic and clinical response to anticonvulsants; clonic activity; or persistent post-ictal encephalopathy.Eighteen hospitalized subjects underwent FDG-PET during contemporaneous IIC patterns attributed to structural lesions (44 %), neuroinflammatory/neuroinfectious disease (39 %), or epilepsy (11 %). FDG-PET hypermetabolism was common (61 %) and predicted electrographic or electroclinical SE (sensitivity 79 % [95 % CI 53-93 %] and specificity 100 % [95 % CI 51-100 %]; p = 0.01). Excluding electrographic SE, hypermetabolism also predicted electroclinical SE (sensitivity 80 % [95 % CI 44-94 %] and specificity 100 % [95 % CI 51-100 %]; p = 0.01).In hospitalized patients with IIC EEG patterns, FDG-PET hypermetabolism is common and is a candidate metabolic biomarker of electrographic SE or electroclinical SE.

  View details for DOI 10.1007/s12028-016-0245-y

  View details for PubMedID 27169855

  View details for PubMedCentralID PMC5478419

• Interrater Agreement for Consensus Definitions of Delayed Ischemic Events After Aneurysmal Subarachnoid Hemorrhage. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Zafar, S. F., Westover, M. B., Gaspard, N., Gilmore, E. J., Foreman, B. P., OʼConnor, K. L., Rosenthal, E. S. 2016; 33 (3): 235-40

  Abstract

  Thirty percent of patients with subarachnoid hemorrhage experience delayed cerebral ischemia or delayed ischemic neurologic decline (DIND). Variability in the definitions of delayed ischemia makes outcome studies difficult to compare. A recent consensus statement advocates standardized definitions for delayed ischemia in clinical trials of subarachnoid hemorrhage. We sought to evaluate the interrater agreement of these definitions.Based on consensus definitions, we assessed for: (1) delayed cerebral infarction, defined as radiographic cerebral infarction; (2) DIND type 1 (DIND1), defined as focal neurologic decline; and (3) DIND2, defined as a global decline in arousal. Five neurologists retrospectively reviewed electronic records of 58 patients with subarachnoid hemorrhage. Three reviewers had access to and reviewed neuroradiology imaging. We assessed interrater agreement using the Gwet kappa statistic.Interrater agreement statistics were excellent (95.83%) for overall agreement on the presence or absence of any delayed ischemic event (DIND1, DIND2, or delayed cerebral infarction). Agreement was "moderate" for specifically identifying DIND1 (56.58%) and DIND2 (48.66%) events. We observed greater agreement for DIND1 when there was a significant focal motor decline of at least 1 point in the motor score. There was fair agreement (39.20%) for identifying delayed cerebral infarction; CT imaging was the predominant modality.Consensus definitions for delayed cerebral ischemia yielded near-perfect overall agreement and can thus be applied in future large-scale studies. However, a strict process of adjudication, explicit thresholds for determining focal neurologic decline, and MRI techniques that better discriminate edema from infarction seem critical for reproducibility of determination of specific outcome phenotypes, and will be important for successful clinical trials.

  View details for DOI 10.1097/WNP.0000000000000276

  View details for PubMedID 27258447

  View details for PubMedCentralID PMC4894325

• Development and Feasibility Testing of a Critical Care EEG Monitoring Database for Standardized Clinical Reporting and Multicenter Collaborative Research JOURNAL OF CLINICAL NEUROPHYSIOLOGY Lee, J. W., LaRoche, S., Choi, H., Ruiz, A. A., Fertig, E., Politsky, J. M., Herman, S. T., Loddenkemper, T., Sansevere, A. J., Korb, P. J., Abend, N. S., Goldstein, J. L., Sinha, S. R., Dombrowski, K. E., Ritzl, E. K., Westover, M. B., Gavvala, J. R., Gerard, E. E., Schmitt, S. E., Szaflarski, J. P., Ding, K., Haas, K. F., Buchsbaum, R., Hirsch, L. J., Wusthoff, C. J., Hopp, J. L., Hahn, C. D. 2016; 33 (2): 133-140

  Abstract

  The rapid expansion of the use of continuous critical care electroencephalogram (cEEG) monitoring and resulting multicenter research studies through the Critical Care EEG Monitoring Research Consortium has created the need for a collaborative data sharing mechanism and repository. The authors describe the development of a research database incorporating the American Clinical Neurophysiology Society standardized terminology for critical care EEG monitoring. The database includes flexible report generation tools that allow for daily clinical use.Key clinical and research variables were incorporated into a Microsoft Access database. To assess its utility for multicenter research data collection, the authors performed a 21-center feasibility study in which each center entered data from 12 consecutive intensive care unit monitoring patients. To assess its utility as a clinical report generating tool, three large volume centers used it to generate daily clinical critical care EEG reports.A total of 280 subjects were enrolled in the multicenter feasibility study. The duration of recording (median, 25.5 hours) varied significantly between the centers. The incidence of seizure (17.6%), periodic/rhythmic discharges (35.7%), and interictal epileptiform discharges (11.8%) was similar to previous studies. The database was used as a clinical reporting tool by 3 centers that entered a total of 3,144 unique patients covering 6,665 recording days.The Critical Care EEG Monitoring Research Consortium database has been successfully developed and implemented with a dual role as a collaborative research platform and a clinical reporting tool. It is now available for public download to be used as a clinical data repository and report generating tool.

  View details for DOI 10.1097/WNP.0000000000000230

  View details for Web of Science ID 000373223500009

  View details for PubMedCentralID PMC4878836

• Monitoring burst suppression in critically ill patients: Multi-centric evaluation of a novel method. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Fürbass, F., Herta, J., Koren, J., Westover, M. B., Hartmann, M. M., Gruber, A., Baumgartner, C., Kluge, T. 2016; 127 (4): 2038-46

  Abstract

  To develop a computational method to detect and quantify burst suppression patterns (BSP) in the EEGs of critical care patients. A multi-center validation study was performed to assess the detection performance of the method.The fully automatic method scans the EEG for discontinuous patterns and shows detected BSP and quantitative information on a trending display in real-time. The method is designed to work without setting any patient specific parameters and to be insensitive to EEG artifacts and periodic patterns. For validation a total of 3982 h of EEG from 88 patients were analyzed from three centers. Each EEG was annotated by two reviewers to assess the detection performance and the inter-rater agreement.Average inter-rater agreement between pairs of reviewers was κ=0.69. On average 22% of the review segments included BSP. An average sensitivity of 90% and a specificity of 84% were measured on the consensus annotations of two reviewers. More than 95% of the periodic patterns in the EEGs were correctly suppressed.A fully automatic method to detect burst suppression patterns was assessed in a multi-center study. The method showed high sensitivity and specificity.Clinically applicable burst suppression detection method validated in a large multi-center study.

  View details for DOI 10.1016/j.clinph.2016.02.001

  View details for PubMedID 26971487

  View details for PubMedCentralID PMC4879619

• Response Rates to Anticonvulsant Trials in Patients with Triphasic-Wave EEG Patterns of Uncertain Significance. Neurocritical care O'Rourke, D., Chen, P. M., Gaspard, N., Foreman, B., McClain, L., Karakis, I., Mahulikar, A., Westover, M. B. 2016; 24 (2): 233-9

  Abstract

  Generalized triphasic waves (TPWs) occur in both metabolic encephalopathies and non-convulsive status epilepticus (NCSE). Empiric trials of benzodiazepines (BZDs) or non-sedating AED (NSAEDs) are commonly used to differentiate the two, but the utility of such trials is debated. The goal of this study was to assess response rates of such trials and investigate whether metabolic profile differences affect the likelihood of a response.Three institutions within the Critical Care EEG Monitoring Research Consortium retrospectively identified patients with unexplained encephalopathy and TPWs who had undergone a trial of BZD and/or NSAEDs to differentiate between ictal and non-ictal patterns. We assessed responder rates and compared metabolic profiles of responders and non-responders. Response was defined as resolution of the EEG pattern and either unequivocal improvement in encephalopathy or appearance of previously absent normal EEG patterns, and further categorized as immediate (within <2 h of trial initiation) or delayed (>2 h from trial initiation).We identified 64 patients with TPWs who had an empiric trial of BZD and/or NSAED. Most patients (71.9%) were admitted with metabolic derangements and/or infection. Positive clinical responses occurred in 10/53 (18.9%) treated with BZDs. Responses to NSAEDs occurred in 19/45 (42.2%), being immediate in 6.7%, delayed but definite in 20.0%, and delayed but equivocal in 15.6%. Overall, 22/64 (34.4%) showed a definite response to either BZDs or NSAEDs, and 7/64 (10.9%) showed a possible response. Metabolic differences of responders versus non-responders were statistically insignificant, except that the 48-h low value of albumin in the BZD responder group was lower than in the non-responder group.Similar metabolic profiles in patients with encephalopathy and TPWs between responders and non-responders to anticonvulsants suggest that predicting responders a priori is difficult. The high responder rate suggests that empiric trials of anticonvulsants indeed provide useful clinical information. The more than twofold higher response rate to NSAEDs suggests that this strategy may be preferable to BZDs. Further prospective investigation is warranted.

  View details for DOI 10.1007/s12028-015-0151-8

  View details for PubMedID 26013921

  View details for PubMedCentralID PMC4870012

• Ictal-interictal continuum: A proposed treatment algorithm. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Rodríguez, V., Rodden, M. F., LaRoche, S. M. 2016; 127 (4): 2056-64

  Abstract

  The ictal-interictal continuum (IIC) is characterized by periodic and/or rhythmic EEG patterns that occur with relative high frequency in critically ill patients. Several studies have reported that some patterns seen within the continuum are independently associated with poor outcome. However there is no consensus regarding when to treat them or how aggressive treatment should be. In this review we examine peer-reviewed original scientific articles, guidelines and reviews indexed in PubMed and summarize current knowledge related to the ictal-interictal continuum. A treatment algorithm to guide management of critically ill patients with EEG patterns that fall along the IIC is proposed. The algorithm-based on best current practice in adults-takes into account associated clinical events, risk factors for developing seizures, response to medication trials and biomarkers of neuronal injury.

  View details for DOI 10.1016/j.clinph.2016.02.003

  View details for PubMedID 26971489

• Development and Feasibility Testing of a Critical Care EEG Monitoring Database for Standardized Clinical Reporting and Multicenter Collaborative Research. Journal of clinical neurophysiology Lee, J. W., LaRoche, S., Choi, H., Rodriguez Ruiz, A. A., Fertig, E., Politsky, J. M., Herman, S. T., Loddenkemper, T., Sansevere, A. J., Korb, P. J., Abend, N. S., Goldstein, J. L., Sinha, S. R., Dombrowski, K. E., Ritzl, E. K., Westover, M. B., Gavvala, J. R., Gerard, E. E., Schmitt, S. E., Szaflarski, J. P., Ding, K., Haas, K. F., Buchsbaum, R., Hirsch, L. J., Wusthoff, C. J., Hopp, J. L., Hahn, C. D. 2016; 33 (2): 133-140

  Abstract

  The rapid expansion of the use of continuous critical care electroencephalogram (cEEG) monitoring and resulting multicenter research studies through the Critical Care EEG Monitoring Research Consortium has created the need for a collaborative data sharing mechanism and repository. The authors describe the development of a research database incorporating the American Clinical Neurophysiology Society standardized terminology for critical care EEG monitoring. The database includes flexible report generation tools that allow for daily clinical use.Key clinical and research variables were incorporated into a Microsoft Access database. To assess its utility for multicenter research data collection, the authors performed a 21-center feasibility study in which each center entered data from 12 consecutive intensive care unit monitoring patients. To assess its utility as a clinical report generating tool, three large volume centers used it to generate daily clinical critical care EEG reports.A total of 280 subjects were enrolled in the multicenter feasibility study. The duration of recording (median, 25.5 hours) varied significantly between the centers. The incidence of seizure (17.6%), periodic/rhythmic discharges (35.7%), and interictal epileptiform discharges (11.8%) was similar to previous studies. The database was used as a clinical reporting tool by 3 centers that entered a total of 3,144 unique patients covering 6,665 recording days.The Critical Care EEG Monitoring Research Consortium database has been successfully developed and implemented with a dual role as a collaborative research platform and a clinical reporting tool. It is now available for public download to be used as a clinical data repository and report generating tool.

  View details for DOI 10.1097/WNP.0000000000000230

  View details for PubMedID 26943901

• CLUSTERING OF INTERICTAL SPIKES BY DYNAMIC TIME WARPING AND AFFINITY PROPAGATION. Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference) Thomas, J., Jin, J., Dauwels, J., Cash, S. S., Westover, M. B. 2016; 2016: 749-753

  Abstract

  Epilepsy is often associated with the presence of spikes in electroencephalograms (EEGs). The spike waveforms vary vastly among epilepsy patients, and also for the same patient across time. In order to develop semi-automated and automated methods for detecting spikes, it is crucial to obtain a better understanding of the various spike shapes. In this paper, we develop several approaches to extract exemplars of spikes. We generate spike exemplars by applying clustering algorithms to a database of spikes from 12 patients. As similarity measures for clustering, we consider the Euclidean distance and Dynamic Time Warping (DTW). We assess two clustering algorithms, namely, K-means clustering and affinity propagation. The clustering methods are compared based on the mean squared error, and the similarity measures are assessed based on the number of generated spike clusters. Affinity propagation with DTW is shown to be the best combination for clustering epileptic spikes, since it generates fewer spike templates and does not require to pre-specify the number of spike templates.

  View details for DOI 10.1109/ICASSP.2016.7471775

  View details for PubMedID 29527130

  View details for PubMedCentralID PMC5842698

• FAST AND EFFICIENT REJECTION OF BACKGROUND WAVEFORMS IN INTERICTAL EEG. Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference) Bagheri, E., Jin, J., Dauwels, J., Cash, S., Westover, M. B. 2016; 2016: 744-748

  Abstract

  Automated annotation of electroencephalograms (EEG) of epileptic patients is important in diagnosis and management of epilepsy. Epilepsy is often associated with the presence of epileptiform transients (ET) in the EEG. To develop an efficient ET detector, a vast amount of data is required to train and evaluate the performance of the detector. Interictal EEG data contains mostly background waveforms, since ETs only occur occasionally in most patients. In order to detect ETs in an automated fashion, it is meaningful to first try to eliminate most background waveforms by means of simple, fast classifiers. The remaining waveforms can in a following step be processed by more sophisticated and computationally demanding classification algorithms, such as deep learning systems. In this study, we design a cascade of simple thresholding steps to reject most background waveforms in interictal EEG, while maintaining most ETs. Several simple and quick-to-compute EEG features are chosen. By thresholding these features in consecutive steps, background waveforms are rejected sequentially. In our numerical experiments, a cascade of 10 steps is able to reject 98.65% of all background segments in the dataset, while preserving 90.6% of the ETs.

  View details for DOI 10.1109/ICASSP.2016.7471774

  View details for PubMedID 29507536

  View details for PubMedCentralID PMC5835012

• Decision Modeling in Sleep Apnea: The Critical Roles of Pretest Probability, Cost of Untreated Obstructive Sleep Apnea, and Time Horizon. Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine Moro, M., Westover, M. B., Kelly, J., Bianchi, M. T. 2016; 12 (3): 409-18

  Abstract

  Obstructive sleep apnea (OSA) is associated with increased morbidity and mortality, and treatment with positive airway pressure (PAP) is cost-effective. However, the optimal diagnostic strategy remains a subject of debate. Prior modeling studies have not consistently supported the widely held assumption that home sleep testing (HST) is cost-effective.We modeled four strategies: (1) treat no one; (2) treat everyone empirically; (3) treat those testing positive during in-laboratory polysomnography (PSG) via in-laboratory titration; and (4) treat those testing positive during HST with auto-PAP. The population was assumed to lack independent reasons for in-laboratory PSG (such as insomnia, periodic limb movements in sleep, complex apnea). We considered the third-party payer perspective, via both standard (quality-adjusted) and pure cost methods.The preferred strategy depended on three key factors: pretest probability of OSA, cost of untreated OSA, and time horizon. At low prevalence and low cost of untreated OSA, the treat no one strategy was favored, whereas empiric treatment was favored for high prevalence and high cost of untreated OSA. In-laboratory backup for failures in the at-home strategy increased the preference for the at-home strategy. Without laboratory backup in the at-home arm, the in-laboratory strategy was increasingly preferred at longer time horizons.Using a model framework that captures a broad range of clinical possibilities, the optimal diagnostic approach to uncomplicated OSA depends on pretest probability, cost of untreated OSA, and time horizon. Estimating each of these critical factors remains a challenge warranting further investigation.

  View details for DOI 10.5664/jcsm.5596

  View details for PubMedID 26518699

  View details for PubMedCentralID PMC4773629

• FAST AND EFFICIENT REJECTION OF BACKGROUND WAVEFORMS IN INTERICTAL EEG. Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference) Bagheri, E., Jin, J., Dauwels, J., Cash, S., Westover, M. B. 2016; 2016: 744-748

  Abstract

  Automated annotation of electroencephalograms (EEG) of epileptic patients is important in diagnosis and management of epilepsy. Epilepsy is often associated with the presence of epileptiform transients (ET) in the EEG. To develop an efficient ET detector, a vast amount of data is required to train and evaluate the performance of the detector. Interictal EEG data contains mostly background waveforms, since ETs only occur occasionally in most patients. In order to detect ETs in an automated fashion, it is meaningful to first try to eliminate most background waveforms by means of simple, fast classifiers. The remaining waveforms can in a following step be processed by more sophisticated and computationally demanding classification algorithms, such as deep learning systems. In this study, we design a cascade of simple thresholding steps to reject most background waveforms in interictal EEG, while maintaining most ETs. Several simple and quick-to-compute EEG features are chosen. By thresholding these features in consecutive steps, background waveforms are rejected sequentially. In our numerical experiments, a cascade of 10 steps is able to reject 98.65% of all background segments in the dataset, while preserving 90.6% of the ETs.

  View details for DOI 10.1109/ICASSP.2016.7471774

  View details for PubMedID 29507536

  View details for PubMedCentralID PMC5835012

• Clinical Prediction Models for Sleep Apnea: The Importance of Medical History over Symptoms. Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine Ustun, B., Westover, M. B., Rudin, C., Bianchi, M. T. 2016; 12 (2): 161-8

  Abstract

  Obstructive sleep apnea (OSA) is a treatable contributor to morbidity and mortality. However, most patients with OSA remain undiagnosed. We used a new machine learning method known as SLIM (Supersparse Linear Integer Models) to test the hypothesis that a diagnostic screening tool based on routinely available medical information would be superior to one based solely on patient-reported sleep-related symptoms.We analyzed polysomnography (PSG) and self-reported clinical information from 1,922 patients tested in our clinical sleep laboratory. We used SLIM and 7 state-of-the-art classification methods to produce predictive models for OSA screening using features from: (i) self-reported symptoms; (ii) self-reported medical information that could, in principle, be extracted from electronic health records (demographics, comorbidities), or (iii) both.For diagnosing OSA, we found that model performance using only medical history features was superior to model performance using symptoms alone, and similar to model performance using all features. Performance was similar to that reported for other widely used tools: sensitivity 64.2% and specificity 77%. SLIM accuracy was similar to state-of-the-art classification models applied to this dataset, but with the benefit of full transparency, allowing for hands-on prediction using yes/no answers to a small number of clinical queries.To predict OSA, variables such as age, sex, BMI, and medical history are superior to the symptom variables we examined for predicting OSA. SLIM produces an actionable clinical tool that can be applied to data that is routinely available in modern electronic health records, which may facilitate automated, rather than manual, OSA screening.A commentary on this article appears in this issue on page 159.

  View details for DOI 10.5664/jcsm.5476

  View details for PubMedID 26350602

  View details for PubMedCentralID PMC4751423

• XGBoost: A Scalable Tree Boosting System Chen, T., Guestrin, C., Assoc Comp Machinery ASSOC COMPUTING MACHINERY. 2016: 785-794

  View details for DOI 10.1145/2939672.2939785

  View details for Web of Science ID 000485529800092

• Quantification of EEG reactivity in comatose patients. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Hermans, M. C., Westover, M. B., van Putten, M. J., Hirsch, L. J., Gaspard, N. 2016; 127 (1): 571-580

  Abstract

  EEG reactivity is an important predictor of outcome in comatose patients. However, visual analysis of reactivity is prone to subjectivity and may benefit from quantitative approaches.In EEG segments recorded during reactivity testing in 59 comatose patients, 13 quantitative EEG parameters were used to compare the spectral characteristics of 1-minute segments before and after the onset of stimulation (spectral temporal symmetry). Reactivity was quantified with probability values estimated using combinations of these parameters. The accuracy of probability values as a reactivity classifier was evaluated against the consensus assessment of three expert clinical electroencephalographers using visual analysis.The binary classifier assessing spectral temporal symmetry in four frequency bands (delta, theta, alpha and beta) showed best accuracy (Median AUC: 0.95) and was accompanied by substantial agreement with the individual opinion of experts (Gwet's AC1: 65-70%), at least as good as inter-expert agreement (AC1: 55%). Probability values also reflected the degree of reactivity, as measured by the inter-experts' agreement regarding reactivity for each individual case.Automated quantitative EEG approaches based on probabilistic description of spectral temporal symmetry reliably quantify EEG reactivity.Quantitative EEG may be useful for evaluating reactivity in comatose patients, offering increased objectivity.

  View details for DOI 10.1016/j.clinph.2015.06.024

  View details for PubMedID 26183757

  View details for PubMedCentralID PMC4885124

• Lighting, sleep and circadian rhythm: An intervention study in the intensive care unit. Intensive & critical care nursing Engwall, M., Fridh, I., Johansson, L., Bergbom, I., Lindahl, B. 2015; 31 (6): 325-35

  Abstract

  Patients in an intensive care unit (ICU) may risk disruption of their circadian rhythm. In an intervention research project a cycled lighting system was set up in an ICU room to support patients' circadian rhythm. Part I aimed to compare experiences of the lighting environment in two rooms with different lighting environments by lighting experiences questionnaire. The results indicated differences in advantage for the patients in the intervention room (n=48), in perception of daytime brightness (p=0.004). In nighttime, greater lighting variation (p=0.005) was found in the ordinary room (n=52). Part II aimed to describe experiences of lighting in the room equipped with the cycled lighting environment. Patients (n=19) were interviewed and the results were presented in categories: "A dynamic lighting environment", "Impact of lighting on patients' sleep", "The impact of lighting/lights on circadian rhythm" and "The lighting calms". Most had experiences from sleep disorders and half had nightmares/sights and circadian rhythm disruption. Nearly all were pleased with the cycled lighting environment, which together with daylight supported their circadian rhythm. In night's actual lighting levels helped patients and staff to connect which engendered feelings of calm.

  View details for DOI 10.1016/j.iccn.2015.07.001

  View details for PubMedID 26215384

• Feasibility and validity of monitoring subarachnoid hemorrhage by a noninvasive MRI imaging perfusion technique: Pulsed Arterial Spin Labeling (PASL). Journal of neuroradiology = Journal de neuroradiologie Labriffe, M., Ter Minassian, A., Pasco-Papon, A., N'Guyen, S., Aubé, C. 2015; 42 (6): 358-67

  Abstract

  To evaluate the validity of pulsed arterial spin labeling (PASL) imaging with cerebral blood flow (CBF) quantification for monitoring subarachnoid hemorrhage (SAH); to describe changes in the perfusion signal in the absence of or following several classic complications.Fifteen patients and 14 healthy volunteers were assigned to SAH and control populations, respectively. ASL imaging was performed three times: between Day 0 (D0, i.e., day of onset of SAH symptoms) and D3, between D7 and D9 and between D12 and D14. ASL points were classified as complicated (symptomatic vasospasm, intraparenchymal hematoma or severe intracranial hypertension) or uncomplicated. Perfusion and CBF maps were generated after automated processing. The inversion time (TI) was fixed at 1800 ms.CBF mean value of Day0-3 uncomplicated SAH patients (47 ± 11.7 mL/min/100g) was significantly higher than that of the volunteers (36.5 ± 7.6 mL/min/100g; P=0.014). In a case-by-case analysis, we observed a global or regional hypoperfusion pattern when SAH was complicated by vasospasm or severe intracranial hypertension, particularly at the junctional areas. Furthermore, we have faced major vascular artefacts, visible as serpiginous high signals and related to the retention of labeled protons in arteries concerning by angiographic vasospasm.PASL is an interesting perfusion technique to non-invasively highlight perfusion changes in complicated SAH and can provide a new element in the decision to perform urgent endovascular treatment. However, the increase in arterial transit time makes the Buxton quantification model inapplicable and leads to false high CBF values in the single-TI PASL technique.

  View details for DOI 10.1016/j.neurad.2015.04.001

  View details for PubMedID 26048296

• The number of seizures needed in the EMU. Epilepsia Struck, A. F., Cole, A. J., Cash, S. S., Westover, M. B. 2015; 56 (11): 1753-9

  Abstract

  The purpose of this study was to develop a quantitative framework to estimate the likelihood of multifocal epilepsy based on the number of unifocal seizures observed in the epilepsy monitoring unit (EMU).Patient records from the EMU at Massachusetts General Hospital (MGH) from 2012 to 2014 were assessed for the presence of multifocal seizures as well the presence of multifocal interictal discharges and multifocal structural imaging abnormalities during the course of the EMU admission. Risk factors for multifocal seizures were assessed using sensitivity and specificity analysis. A Kaplan-Meier survival analysis was used to estimate the risk of multifocal epilepsy for a given number of consecutive seizures. To overcome the limits of the Kaplan-Meier analysis, a parametric survival function was fit to the EMU subjects with multifocal seizures and this was used to develop a Bayesian model to estimate the risk of multifocal seizures during an EMU admission.Multifocal interictal discharges were a significant predictor of multifocal seizures within an EMU admission with a p < 0.01, albeit with only modest sensitivity 0.74 and specificity 0.69. Multifocal potentially epileptogenic lesions on MRI were not a significant predictor p = 0.44. Kaplan-Meier analysis was limited by wide confidence intervals secondary to significant patient dropout and concern for informative censoring. The Bayesian framework provided estimates for the number of unifocal seizures needed to predict absence of multifocal seizures. To achieve 90% confidence for the absence of multifocal seizure, three seizures are needed when the pretest probability for multifocal epilepsy is 20%, seven seizures for a pretest probability of 50%, and nine seizures for a pretest probability of 80%.These results provide a framework to assist clinicians in determining the utility of trying to capture a specific number of seizures in EMU evaluations of candidates for epilepsy surgery.

  View details for DOI 10.1111/epi.13090

  View details for PubMedID 26222350

  View details for PubMedCentralID PMC4877132

• The human burst suppression electroencephalogram of deep hypothermia. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Westover, M. B., Ching, S., Kumaraswamy, V. M., Akeju, S. O., Pierce, E., Cash, S. S., Kilbride, R., Brown, E. N., Purdon, P. L. 2015; 126 (10): 1901-1914

  Abstract

  Deep hypothermia induces 'burst suppression' (BS), an electroencephalogram pattern with low-voltage 'suppressions' alternating with high-voltage 'bursts'. Current understanding of BS comes mainly from anesthesia studies, while hypothermia-induced BS has received little study. We set out to investigate the electroencephalogram changes induced by cooling the human brain through increasing depths of BS through isoelectricity.We recorded scalp electroencephalograms from eleven patients undergoing deep hypothermia during cardiac surgery with complete circulatory arrest, and analyzed these using methods of spectral analysis.Within patients, the depth of BS systematically depends on the depth of hypothermia, though responses vary between patients except at temperature extremes. With decreasing temperature, burst lengths increase, and burst amplitudes and lengths decrease, while the spectral content of bursts remains constant.These findings support an existing theoretical model in which the common mechanism of burst suppression across diverse etiologies is the cyclical diffuse depletion of metabolic resources, and suggest the new hypothesis of local micro-network dropout to explain decreasing burst amplitudes at lower temperatures.These results pave the way for accurate noninvasive tracking of brain metabolic state during surgical procedures under deep hypothermia, and suggest new testable predictions about the network mechanisms underlying burst suppression.

  View details for DOI 10.1016/j.clinph.2014.12.022

  View details for PubMedID 25649968

  View details for PubMedCentralID PMC4504839

• Transitions of Care for Stroke Patients: Opportunities to Improve Outcomes. Circulation. Cardiovascular quality and outcomes Broderick, J. P., Abir, M. 2015; 8 (6 Suppl 3): S190-2

  View details for DOI 10.1161/CIRCOUTCOMES.115.002288

  View details for PubMedID 26515208

• Practice variability and efficacy of clonazepam, lorazepam, and midazolam in status epilepticus: A multicenter comparison. Epilepsia Alvarez, V., Lee, J. W., Drislane, F. W., Westover, M. B., Novy, J., Dworetzky, B. A., Rossetti, A. O. 2015; 56 (8): 1275-85

  Abstract

  Benzodiazepines (BZD) are recommended as first-line treatment for status epilepticus (SE), with lorazepam (LZP) and midazolam (MDZ) being the most widely used drugs and part of current treatment guidelines. Clonazepam (CLZ) is also utilized in many countries; however, there is no systematic comparison of these agents for treatment of SE to date.We identified all patients treated with CLZ, LZP, or MDZ as a first-line agent from a prospectively collected observational cohort of adult patients treated for SE in four tertiary care centers. Relative efficacies of CLZ, LZP, and MDZ were compared by assessing the risk of developing refractory SE and the number of antiseizure drugs (ASDs) required to control SE.Among 177 patients, 72 patients (40.62%) received CLZ, 82 patients (46.33%) LZP, and 23 (12.99%) MDZ; groups were similar in demographics and SE characteristics. Loading dose was considered insufficient in the majority of cases for LZP, with a similar rate (84%, 95%, and 87.5%) in the centers involved, and CLZ was used as recommended in 52% of patients. After adjustment for relevant variables, LZP was associated with an increased risk of refractoriness as compared to CLZ (odds ratio [OR] 6.4, 95% confidence interval [CI] 2.66-15.5) and with an increased number of ASDs needed for SE control (OR 4.35, 95% CI 1.8-10.49).CLZ seems to be an effective alternative to LZP and MDZ. LZP is frequently underdosed in this setting. These findings are highly relevant, since they may impact daily practice.

  View details for DOI 10.1111/epi.13056

  View details for PubMedID 26140660

  View details for PubMedCentralID PMC4877129

• Variability in clinical assessment of neuroimaging in temporal lobe epilepsy. Seizure Struck, A. F., Westover, M. B. 2015; 30: 132-5

  Abstract

  Neuroimaging is critical in deciding candidacy for epilepsy surgery. Currently imaging is primarily assessed qualitatively, which may affect patient selection and outcomes.The epilepsy surgery database at MGH was reviewed for temporal lobectomy patients from the last 10 years. Radiology reports for MRI and FDG-PET were compared to the epilepsy conference consensus. First, specific findings of ipsi/contra hippocampal atrophy and T2 signal changes were directly compared. Next the overall impression of presence of hippocampal sclerosis (HS) for MRI and temporal hypometabolism for PET was used for sensitivity/specificity analysis. To assess predictive power of imaging findings logistic regression was used.104 subjects were identified. 70% of subjects were ILAE class I at 1-year. Radiology reports and the conference consensus differed in 31% of FDG-PET studies and 41% of MRIs. For PET most disagreement (50%) stemmed for discrepancy regarding contralateral temporal hypometabolism. For MRI discrepancy in ipsilateral hippocampal atrophy/T2 signal accounted for 59% of disagreements. When overall impression of the image was used the overall reliability between groups was high with only MRI sensitivity to detect HS (0.75 radiology, 0.91 conference, p=0.02) was significantly different between groups. On logistic regression MRI was a significant predictor of HS, but still 36% of patients with normal MRI as read by both groups had HS on pathology.Despite some difference in specific radiologic findings, overall accuracy for MRI and PET is similar in clinical practice between radiology and conference; nonetheless there are still cases of hippocampal pathology not detected by standard imaging methods.

  View details for DOI 10.1016/j.seizure.2015.06.011

  View details for PubMedID 26216698

  View details for PubMedCentralID PMC4887849

• Estimating Total Cerebral Microinfarct Burden From Diffusion-Weighted Imaging. Stroke Auriel, E., Westover, M. B., Bianchi, M. T., Reijmer, Y., Martinez-Ramirez, S., Ni, J., Van Etten, E., Frosch, M. P., Fotiadis, P., Schwab, K., Vashkevich, A., Boulouis, G., Younger, A. P., Johnson, K. A., Sperling, R. A., Hedden, T., Gurol, M. E., Viswanathan, A., Greenberg, S. M. 2015; 46 (8): 2129-35

  Abstract

  Cerebral microinfarcts (CMI) are important contributors to vascular cognitive impairment. Magnetic resonance imaging diffusion-weighted imaging (DWI) hyperintensities have been suggested to represent acute CMI. We aim to describe a mathematical method for estimating total number of CMI based on the presence of incidental DWI lesions.We reviewed magnetic resonance imaging scans of subjects with cognitive decline, cognitively normal subjects and previously reported subjects with past intracerebral hemorrhage (ICH). Based on temporal and spatial characteristics of DWI lesions, we estimated the annual rate of CMI needed to explain the observed rate of DWI lesion detection in each group. To confirm our estimates, we performed extensive sampling for CMI in the brain of a deceased subject with past lobar ICH who found to have a DWI lesion during life.Clinically silent DWI lesions were present in 13 of 343 (3.8%) cognitively impaired and 10 of 199 (5%) cognitively intact normal non-ICH patients, both lower than the incidence in the past ICH patients (23 of 178; 12.9%; P<0.0006). The predicted annual incidence of CMI ranges from 16 to 1566 for non-ICH and 50 to 5041 for ICH individuals. Histological sampling revealed a total of 60 lesions in 32 sections. Based on previously reported methods, this density of CMI yields an estimated total brain burden maximum likelihood estimate of 9321 CMIs (95% confidence interval, 7255-11 990).Detecting even a single DWI lesion suggests an annual incidence of hundreds of new CMI. The cumulative effects of these lesions may directly contribute to small-vessel-related vascular cognitive impairment.

  View details for DOI 10.1161/STROKEAHA.115.009208

  View details for PubMedID 26159796

  View details for PubMedCentralID PMC4519384

• Robust control of burst suppression for medical coma. Journal of neural engineering Westover, M. B., Kim, S. E., Ching, S., Purdon, P. L., Brown, E. N. 2015; 12 (4): 046004

  Abstract

  Medical coma is an anesthetic-induced state of brain inactivation, manifest in the electroencephalogram by burst suppression. Feedback control can be used to regulate burst suppression, however, previous designs have not been robust. Robust control design is critical under real-world operating conditions, subject to substantial pharmacokinetic and pharmacodynamic parameter uncertainty and unpredictable external disturbances. We sought to develop a robust closed-loop anesthesia delivery (CLAD) system to control medical coma.We developed a robust CLAD system to control the burst suppression probability (BSP). We developed a novel BSP tracking algorithm based on realistic models of propofol pharmacokinetics and pharmacodynamics. We also developed a practical method for estimating patient-specific pharmacodynamics parameters. Finally, we synthesized a robust proportional integral controller. Using a factorial design spanning patient age, mass, height, and gender, we tested whether the system performed within clinically acceptable limits. Throughout all experiments we subjected the system to disturbances, simulating treatment of refractory status epilepticus in a real-world intensive care unit environment.In 5400 simulations, CLAD behavior remained within specifications. Transient behavior after a step in target BSP from 0.2 to 0.8 exhibited a rise time (the median (min, max)) of 1.4 [1.1, 1.9] min; settling time, 7.8 [4.2, 9.0] min; and percent overshoot of 9.6 [2.3, 10.8]%. Under steady state conditions the CLAD system exhibited a median error of 0.1 [-0.5, 0.9]%; inaccuracy of 1.8 [0.9, 3.4]%; oscillation index of 1.8 [0.9, 3.4]%; and maximum instantaneous propofol dose of 4.3 [2.1, 10.5] mg kg(-1). The maximum hourly propofol dose was 4.3 [2.1, 10.3] mg kg(-1) h(-1). Performance fell within clinically acceptable limits for all measures.A CLAD system designed using robust control theory achieves clinically acceptable performance in the presence of realistic unmodeled disturbances and in spite of realistic model uncertainty, while maintaining infusion rates within acceptable safety limits.

  View details for DOI 10.1088/1741-2560/12/4/046004

  View details for PubMedID 26020243

  View details for PubMedCentralID PMC4517835

• Age-dependency of sevoflurane-induced electroencephalogram dynamics in children. British journal of anaesthesia Akeju, O., Pavone, K. J., Thum, J. A., Firth, P. G., Westover, M. B., Puglia, M., Shank, E. S., Brown, E. N., Purdon, P. L. 2015; 115 Suppl 1 (Suppl 1): i66-i76

  Abstract

  General anaesthesia induces highly structured oscillations in the electroencephalogram (EEG) in adults, but the anaesthesia-induced EEG in paediatric patients is less understood. Neural circuits undergo structural and functional transformations during development that might be reflected in anaesthesia-induced EEG oscillations. We therefore investigated age-related changes in the EEG during sevoflurane general anaesthesia in paediatric patients.We analysed the EEG recorded during routine care of patients between 0 and 28 yr of age (n=54), using power spectral and coherence methods. The power spectrum quantifies the energy in the EEG at each frequency, while the coherence measures the frequency-dependent correlation or synchronization between EEG signals at different scalp locations. We characterized the EEG as a function of age and within 5 age groups: <1 yr old (n=4), 1-6 yr old (n=12), >6-14 yr old (n=14), >14-21 yr old (n=11), >21-28 yr old (n=13).EEG power significantly increased from infancy through ∼6 yr, subsequently declining to a plateau at approximately 21 yr. Alpha (8-13 Hz) coherence, a prominent EEG feature associated with sevoflurane-induced unconsciousness in adults, is absent in patients <1 yr.Sevoflurane-induced EEG dynamics in children vary significantly as a function of age. These age-related dynamics likely reflect ongoing development within brain circuits that are modulated by sevoflurane. These readily observed paediatric-specific EEG signatures could be used to improve brain state monitoring in children receiving general anaesthesia.

  View details for DOI 10.1093/bja/aev114

  View details for PubMedID 26174303

  View details for PubMedCentralID PMC4501917

• Characteristics and role in outcome prediction of continuous EEG after status epilepticus: A prospective observational cohort. Epilepsia Alvarez, V., Drislane, F. W., Westover, M. B., Dworetzky, B. A., Lee, J. W. 2015; 56 (6): 933-41

  Abstract

  Continuous electroencephalography (cEEG) is important for treatment guidance in status epilepticus (SE) management, but its role in clinical outcome prediction is unclear. Our aim is to determine which cEEG features give independent outcome information after correction for clinical predictor.cEEG data of 120 consecutive adult patients with SE were prospectively collected in three academic medical centers using the 2012 American Clinical Neurophysiology Society's Standardized Critical Care EEG Terminology. Association between cEEG features and two clinical outcome measures (mortality and complete recovery) was assessed.In the first 24 h of EEG recording, 49 patients (40.8%) showed no periodic or rhythmic pattern, 45 (37.5%) had periodic discharges, 20 (16.7%) had rhythmic delta activity, and 6 (5%) had spike-and-wave discharges. Seizures were recorded in 68.3% of patients. After adjusting for known clinical predictive factors for mortality including the STatus Epilepticus Severity Score (STESS) and the presence of a potentially fatal etiology, the only EEG features (among rhythmic and periodic patterns, seizures, and background activity) that remained significantly associated with outcome were the absence of a posterior dominant rhythm (odds ratio [OR] 9.8; p = 0.033) for mortality and changes in stage II sleep pattern characteristics (OR 2.59 for each step up among these categories: absent, present and abnormal, present and normal; p = 0.002) for complete recovery.After adjustment for relevant clinical findings, including SE severity and etiology, cEEG background information (posterior dominant rhythm and sleep patterns) is more predictive for clinical outcome after SE than are rhythmic and periodic patterns or seizures.

  View details for DOI 10.1111/epi.12996

  View details for PubMedID 25953195

  View details for PubMedCentralID PMC4878827

• The probability of seizures during EEG monitoring in critically ill adults. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Westover, M. B., Shafi, M. M., Bianchi, M. T., Moura, L. M., O'Rourke, D., Rosenthal, E. S., Chu, C. J., Donovan, S., Hoch, D. B., Kilbride, R. D., Cole, A. J., Cash, S. S. 2015; 126 (3): 463-71

  Abstract

  To characterize the risk for seizures over time in relation to EEG findings in hospitalized adults undergoing continuous EEG monitoring (cEEG).Retrospective analysis of cEEG data and medical records from 625 consecutive adult inpatients monitored at a tertiary medical center. Using survival analysis methods, we estimated the time-dependent probability that a seizure will occur within the next 72-h, if no seizure has occurred yet, as a function of EEG abnormalities detected so far.Seizures occurred in 27% (168/625). The first seizure occurred early (<30min of monitoring) in 58% (98/168). In 527 patients without early seizures, 159 (30%) had early epileptiform abnormalities, versus 368 (70%) without. Seizures were eventually detected in 25% of patients with early epileptiform discharges, versus 8% without early discharges. The 72-h risk of seizures declined below 5% if no epileptiform abnormalities were present in the first two hours, whereas 16h of monitoring were required when epileptiform discharges were present. 20% (74/388) of patients without early epileptiform abnormalities later developed them; 23% (17/74) of these ultimately had seizures. Only 4% (12/294) experienced a seizure without preceding epileptiform abnormalities.Seizure risk in acute neurological illness decays rapidly, at a rate dependent on abnormalities detected early during monitoring. This study demonstrates that substantial risk stratification is possible based on early EEG abnormalities.These findings have implications for patient-specific determination of the required duration of cEEG monitoring in hospitalized patients.

  View details for DOI 10.1016/j.clinph.2014.05.037

  View details for PubMedID 25082090

  View details for PubMedCentralID PMC4289643

• Relationships between sleep stages and changes in cognitive function in older men: the MrOS Sleep Study. Sleep Song, Y., Blackwell, T., Yaffe, K., Ancoli-Israel, S., Redline, S., Stone, K. L. 2015; 38 (3): 411-21

  Abstract

  To investigate the associations between sleep stage distributions and subsequent decline in cognitive function in older men over time.A population-based prospective substudy of the Osteoporotic Fractures in Men Study.Six sites in the United States.Community-dwelling men aged 67 y or older (n = 2,601), who were free of probable dementia at sleep visit. Follow-up averaged 3.4 y.Sleep stages were identified by in-home polysomnography at the initial sleep visit (2003-2005). Cognitive outcomes were assessed with the Trail Making Test Part B and Modified Mini-Mental State Examination (3MS) at sleep visit and two follow-up visits. After adjusting for multiple confounders compared with men in the lowest quartile of percent of sleep time spent in Stage N1, those in the highest quartile had a twofold increase in cognitive decline for both cognitive tests (adjusted annualized percent change/y: Trail Making Test Part B Q1 = 1.06, Q4 = 2.45, P = 0.01; 3MS Q1 = -0.27, Q4 = -0.48, P = 0.03). In addition, compared with men in the highest quartile, men in the lowest quartile of percent of sleep time in Stage R revealed more cognitive decline on the 3MS (adjusted annualized percent change/y: Q1 = -0.49, Q4 = -0.22, P = 0.003). These findings were consistent even after further adjustment of total sleep time and sleep disordered breathing. No significant relationships between other sleep stages (N2, N3) and cognitive change were found.Increased time in Stage N1 and less time in Stage R are associated with worsening cognitive performance in older men over time.

  View details for DOI 10.5665/sleep.4500

  View details for PubMedID 25325465

  View details for PubMedCentralID PMC4335525

• Physiological consequences of abnormal connectivity in a developmental epilepsy. Annals of neurology Shafi, M. M., Vernet, M., Klooster, D., Chu, C. J., Boric, K., Barnard, M. E., Romatoski, K., Westover, M. B., Christodoulou, J. A., Gabrieli, J. D., Whitfield-Gabrieli, S., Pascual-Leone, A., Chang, B. S. 2015; 77 (3): 487-503

  Abstract

  Many forms of epilepsy are associated with aberrant neuronal connections, but the relationship between such pathological connectivity and the underlying physiological predisposition to seizures is unclear. We sought to characterize the cortical excitability profile of a developmental form of epilepsy known to have structural and functional connectivity abnormalities.We employed transcranial magnetic stimulation (TMS) with simultaneous electroencephalographic (EEG) recording in 8 patients with epilepsy from periventricular nodular heterotopia and matched healthy controls. We used connectivity imaging findings to guide TMS targeting and compared the evoked responses to single-pulse stimulation from different cortical regions.Heterotopia patients with active epilepsy demonstrated a relatively augmented late cortical response that was greater than that of matched controls. This abnormality was specific to cortical regions with connectivity to subcortical heterotopic gray matter. Topographic mapping of the late response differences showed distributed cortical networks that were not limited to the stimulation site, and source analysis in 1 subject revealed that the generator of abnormal TMS-evoked activity overlapped with the spike and seizure onset zone.Our findings indicate that patients with epilepsy from gray matter heterotopia have altered cortical physiology consistent with hyperexcitability, and that this abnormality is specifically linked to the presence of aberrant connectivity. These results support the idea that TMS-EEG could be a useful biomarker in epilepsy in gray matter heterotopia, expand our understanding of circuit mechanisms of epileptogenesis, and have potential implications for therapeutic neuromodulation in similar epileptic conditions associated with deep lesions.

  View details for DOI 10.1002/ana.24343

  View details for PubMedID 25858773

  View details for PubMedCentralID PMC4394240

• Cerebrospinal fluid shunt-induced chorea: case report and review of the literature on shunt-related movement disorders. Practical neurology de Gusmäo, C. M., Berkowitz, A. L., Hung, A. Y., Westover, M. B. 2015; 15 (1): 42-4

  View details for DOI 10.1136/practneurol-2014-000913

  View details for PubMedID 24997172

  View details for PubMedCentralID PMC4870013

• Clustering analysis to identify distinct spectral components of encephalogram burst suppression in critically ill patients. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Zhou, D. W., Westover, M. B., McClain, L. M., Nagaraj, S. B., Bajwa, E. K., Quraishi, S. A., Akeju, O., Cobb, J. P., Purdon, P. L. 2015; 2015: 7258-61

  Abstract

  Millions of patients are admitted each year to intensive care units (ICUs) in the United States. A significant fraction of ICU survivors develop life-long cognitive impairment, incurring tremendous financial and societal costs. Delirium, a state of impaired awareness, attention and cognition that frequently develops during ICU care, is a major risk factor for post-ICU cognitive impairment. Recent studies suggest that patients experiencing electroencephalogram (EEG) burst suppression have higher rates of mortality and are more likely to develop delirium than patients who do not experience burst suppression. Burst suppression is typically associated with coma and deep levels of anesthesia or hypothermia, and is defined clinically as an alternating pattern of high-amplitude "burst" periods interrupted by sustained low-amplitude "suppression" periods. Here we describe a clustering method to analyze EEG spectra during burst and suppression periods. We used this method to identify a set of distinct spectral patterns in the EEG during burst and suppression periods in critically ill patients. These patterns correlate with level of patient sedation, quantified in terms of sedative infusion rates and clinical sedation scores. This analysis suggests that EEG burst suppression in critically ill patients may not be a single state, but instead may reflect a plurality of states whose specific dynamics relate to a patient's underlying brain function.

  View details for DOI 10.1109/EMBC.2015.7320067

  View details for PubMedID 26737967

  View details for PubMedCentralID PMC4870011

• Automated information extraction from free-text EEG reports. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Biswal, S., Nip, Z., Moura Junior, V., Bianchi, M. T., Rosenthal, E. S., Westover, M. B. 2015; 2015: 6804-7

  Abstract

  In this study we have developed a supervised learning to automatically detect with high accuracy EEG reports that describe seizures and epileptiform discharges. We manually labeled 3,277 documents as describing one or more seizures vs no seizures, and as describing epileptiform discharges vs no epileptiform discharges. We then used Naïve Bayes to develop a system able to automatically classify EEG reports into these categories. Our system consisted of normalization techniques, extraction of key sentences, and automated feature selection using cross validation. As candidate features we used key words and special word patterns called elastic word sequences (EWS). Final feature selection was accomplished via sequential backward selection. We used cross validation to predict out of sample performance. Our automated feature selection procedure resulted in a classifier with 38 features for seizure detection, and 23 features for epileptiform discharge detection. The average [95% CI] area under the receiver operating curve was 99.05 [98.79, 99.32]% for detecting reports with seizures, and 96.15 [92.31, 100.00]% for detecting reports with epileptiform discharges. The methodology described herein greatly reduces the manual labor involved in identifying large cohorts of patients for retrospective neurophysiological studies of patients with epilepsy.

  View details for DOI 10.1109/EMBC.2015.7319956

  View details for PubMedID 26737856

  View details for PubMedCentralID PMC4872711

• An enhanced cerebral recovery index for coma prognostication following cardiac arrest. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Ghassemi, M. M., Amorim, E., Pati, S. B., Mark, R. G., Brown, E. N., Purdon, P. L., Westover, M. B. 2015; 2015: 534-7

  Abstract

  Prognostication of coma outcomes following cardiac arrest is both qualitative and poorly understood in current practice. Existing quantitative metrics are powerful, but lack rigorous approaches to classification. This is due, in part, to a lack of available data on the population of interest. In this paper we describe a novel retrospective data set of 167 cardiac arrest patients (spanning three institutions) who received electroencephalography (EEG) monitoring. We utilized a subset of the collected data to generate features that measured the connectivity, complexity and category of EEG activity. A subset of these features was included in a logistic regression model to estimate a dichotomized cerebral performance category score at discharge. We compared the predictive performance of our method against an established EEG-based alternative, the Cerebral Recovery Index (CRI) and show that our approach more reliably classifies patient outcomes, with an average increase in AUC of 0.27.

  View details for DOI 10.1109/EMBC.2015.7318417

  View details for PubMedID 26736317

  View details for PubMedCentralID PMC4870018

• Spatial variation in automated burst suppression detection in pharmacologically induced coma. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference An, J., Jonnalagadda, D., Moura, V., Purdon, P. L., Brown, E. N., Westover, M. B. 2015; 2015: 7430-3

  Abstract

  Burst suppression is actively studied as a control signal to guide anesthetic dosing in patients undergoing medically induced coma. The ability to automatically identify periods of EEG suppression and compactly summarize the depth of coma using the burst suppression probability (BSP) is crucial to effective and safe monitoring and control of medical coma. Current literature however does not explicitly account for the potential variation in burst suppression parameters across different scalp locations. In this study we analyzed standard 19-channel EEG recordings from 8 patients with refractory status epilepticus who underwent pharmacologically induced burst suppression as medical treatment for refractory seizures. We found that although burst suppression is generally considered a global phenomenon, BSP obtained using a previously validated algorithm varies systematically across different channels. A global representation of information from individual channels is proposed that takes into account the burst suppression characteristics recorded at multiple electrodes. BSP computed from this representative burst suppression pattern may be more resilient to noise and a better representation of the brain state of patients. Multichannel data integration may enhance the reliability of estimates of the depth of medical coma.

  View details for DOI 10.1109/EMBC.2015.7320109

  View details for PubMedID 26738009

  View details for PubMedCentralID PMC4876722

• The standardization debate: A conflation trap in critical care electroencephalography. Seizure Ng, M. C., Gaspard, N., Cole, A. J., Hoch, D. B., Cash, S. S., Bianchi, M., O'Rourke, D. A., Rosenthal, E. S., Chu, C. J., Westover, M. B. 2015; 24: 52-8

  Abstract

  Persistent uncertainty over the clinical significance of various pathological continuous electroencephalography (cEEG) findings in the intensive care unit (ICU) has prompted efforts to standardize ICU cEEG terminology and an ensuing debate. We set out to understand the reasons for, and a satisfactory resolution to, this debate.We review the positions for and against standardization, and examine their deeper philosophical basis.We find that the positions for and against standardization are not fundamentally irreconcilable. Rather, both positions stem from conflating the three cardinal steps in the classic approach to EEG, which we term "description", "interpretation", and "prescription". Using real-world examples we show how this conflation yields muddled clinical reasoning and unproductive debate among electroencephalographers that is translated into confusion among treating clinicians. We propose a middle way that judiciously uses both standardized terminology and clinical reasoning to disentangle these critical steps and apply them in proper sequence.The systematic approach to ICU cEEG findings presented herein not only resolves the standardization debate but also clarifies clinical reasoning by helping electroencephalographers assign appropriate weights to cEEG findings in the face of uncertainty.

  View details for DOI 10.1016/j.seizure.2014.09.017

  View details for PubMedID 25457454

  View details for PubMedCentralID PMC4465375

• High risk for seizures following subarachnoid hemorrhage regardless of referral bias. Neurocritical care O'Connor, K. L., Westover, M. B., Phillips, M. T., Iftimia, N. A., Buckley, D. A., Ogilvy, C. S., Shafi, M. M., Rosenthal, E. S. 2014; 21 (3): 476-82

  Abstract

  To investigate the frequency, predictors, and clinical impact of electrographic seizures in patients with high clinical or radiologic grade non-traumatic subarachnoid hemorrhage (SAH), independent of referral bias.We compared rates of electrographic seizures and associated clinical variables and outcomes in patients with high clinical or radiologic grade non-traumatic SAH. Rates of electrographic seizure detection before and after institution of a guideline which made continuous EEG monitoring routine in this population were compared.Electrographic seizures occurred in 17.6 % of patients monitored expressly because of clinically suspected subclinical seizures. In unselected patients, seizures still occurred in 9.6 % of all cases, and in 8.6 % of cases in which there was no a priori suspicion of seizures. The first seizure detected occurred 5.4 (IQR 2.9-7.3) days after onset of subarachnoid hemorrhage with three of eight patients (37.5 %) having the first recorded seizure more than 48 h following EEG initiation, and 2/8 (25 %) at more than 72 h following EEG initiation. High clinical grade was associated with poor outcome at time of hospital discharge; electrographic seizures were not associated with poor outcome.Electrographic seizures occur at a relatively high rate in patients with non-traumatic SAH even after accounting for referral bias. The prolonged time to the first detected seizure in this cohort may reflect dynamic clinical features unique to the SAH population.

  View details for DOI 10.1007/s12028-014-9974-y

  View details for PubMedID 24723663

  View details for PubMedCentralID PMC4878846

• Evaluation of a clinical tool for early etiology identification in status epilepticus. Epilepsia Alvarez, V., Westover, M. B., Drislane, F. W., Dworetzky, B. A., Curley, D., Lee, J. W., Rossetti, A. O. 2014; 55 (12): 2059-2068

  Abstract

  Because early etiologic identification is critical to select appropriate specific status epilepticus (SE) management, we aim to validate a clinical tool we developed that uses history and readily available investigations to guide prompt etiologic assessment.This prospective multicenter study included all adult patients treated for SE of all but anoxic causes from four academic centers. The proposed tool is designed as a checklist covering frequent precipitating factors for SE. The study team completed the checklist at the time the patient was identified by electroencephalography (EEG) request. Only information available in the emergency department or at the time of in-hospital SE identification was used. Concordance between the etiology indicated by the tool and the determined etiology at hospital discharge was analyzed, together with interrater agreement.Two hundred twelve patients were included. Concordance between the etiology hypothesis generated using the tool and the finally determined etiology was 88.7% (95% confidence interval (CI) 86.4-89.8) (κ = 0.88). Interrater agreement was 83.3% (95% CI 80.4-96) (κ = 0.81).This tool is valid and reliable for identification early the etiology of an SE. Physicians managing patients in SE may benefit from using it to identify promptly the underlying etiology, thus facilitating selection of the appropriate treatment.

  View details for DOI 10.1111/epi.12852

  View details for PubMedID 25385281

  View details for PubMedCentralID PMC4870016

• A comparison of propofol- and dexmedetomidine-induced electroencephalogram dynamics using spectral and coherence analysis. Anesthesiology Akeju, O., Pavone, K. J., Westover, M. B., Vazquez, R., Prerau, M. J., Harrell, P. G., Hartnack, K. E., Rhee, J., Sampson, A. L., Habeeb, K., Gao, L., Pierce, E. T., Walsh, J. L., Brown, E. N., Purdon, P. L. 2014; 121 (5): 978-89

  Abstract

  Electroencephalogram patterns observed during sedation with dexmedetomidine appear similar to those observed during general anesthesia with propofol. This is evident with the occurrence of slow (0.1 to 1 Hz), delta (1 to 4 Hz), propofol-induced alpha (8 to 12 Hz), and dexmedetomidine-induced spindle (12 to 16 Hz) oscillations. However, these drugs have different molecular mechanisms and behavioral properties and are likely accompanied by distinguishing neural circuit dynamics.The authors measured 64-channel electroencephalogram under dexmedetomidine (n = 9) and propofol (n = 8) in healthy volunteers, 18 to 36 yr of age. The authors administered dexmedetomidine with a 1-µg/kg loading bolus over 10 min, followed by a 0.7 µg kg h infusion. For propofol, the authors used a computer-controlled infusion to target the effect-site concentration gradually from 0 to 5 μg/ml. Volunteers listened to auditory stimuli and responded by button press to determine unconsciousness. The authors analyzed the electroencephalogram using multitaper spectral and coherence analysis.Dexmedetomidine was characterized by spindles with maximum power and coherence at approximately 13 Hz (mean ± SD; power, -10.8 ± 3.6 dB; coherence, 0.8 ± 0.08), whereas propofol was characterized with frontal alpha oscillations with peak frequency at approximately 11 Hz (power, 1.1 ± 4.5 dB; coherence, 0.9 ± 0.05). Notably, slow oscillation power during a general anesthetic state under propofol (power, 13.2 ± 2.4 dB) was much larger than during sedative states under both propofol (power, -2.5 ± 3.5 dB) and dexmedetomidine (power, -0.4 ± 3.1 dB).The results indicate that dexmedetomidine and propofol place patients into different brain states and suggest that propofol enables a deeper state of unconsciousness by inducing large-amplitude slow oscillations that produce prolonged states of neuronal silence.

  View details for DOI 10.1097/ALN.0000000000000419

  View details for PubMedID 25187999

  View details for PubMedCentralID PMC4304638

• Effects of sevoflurane and propofol on frontal electroencephalogram power and coherence. Anesthesiology Akeju, O., Westover, M. B., Pavone, K. J., Sampson, A. L., Hartnack, K. E., Brown, E. N., Purdon, P. L. 2014; 121 (5): 990-8

  Abstract

  The neural mechanisms of anesthetic vapors have not been studied in depth. However, modeling and experimental studies on the intravenous anesthetic propofol indicate that potentiation of γ-aminobutyric acid receptors leads to a state of thalamocortical synchrony, observed as coherent frontal alpha oscillations, associated with unconsciousness. Sevoflurane, an ether derivative, also potentiates γ-aminobutyric acid receptors. However, in humans, sevoflurane-induced coherent frontal alpha oscillations have not been well detailed.To study the electroencephalogram dynamics induced by sevoflurane, the authors identified age- and sex-matched patients in which sevoflurane (n = 30) or propofol (n = 30) was used as the sole agent for maintenance of general anesthesia during routine surgery. The authors compared the electroencephalogram signatures of sevoflurane with that of propofol using time-varying spectral and coherence methods.Sevoflurane general anesthesia is characterized by alpha oscillations with maximum power and coherence at approximately 10 Hz, (mean ± SD; peak power, 4.3 ± 3.5 dB; peak coherence, 0.73 ± 0.1). These alpha oscillations are similar to those observed during propofol general anesthesia, which also has maximum power and coherence at approximately 10 Hz (peak power, 2.1 ± 4.3 dB; peak coherence, 0.71 ± 0.1). However, sevoflurane also exhibited a distinct theta coherence signature (peak frequency, 4.9 ± 0.6 Hz; peak coherence, 0.58 ± 0.1). Slow oscillations were observed in both cases, with no significant difference in power or coherence.The study results indicate that sevoflurane, like propofol, induces coherent frontal alpha oscillations and slow oscillations in humans to sustain the anesthesia-induced unconscious state. These results suggest a shared molecular and systems-level mechanism for the unconscious state induced by these drugs.

  View details for DOI 10.1097/ALN.0000000000000436

  View details for PubMedID 25233374

  View details for PubMedCentralID PMC4206606

• Weighing the value of memory loss in the surgical evaluation of left temporal lobe epilepsy: a decision analysis. Epilepsia Akama-Garren, E. H., Bianchi, M. T., Leveroni, C., Cole, A. J., Cash, S. S., Westover, M. B. 2014; 55 (11): 1844-53

  Abstract

  Anterior temporal lobectomy is curative for many patients with disabling medically refractory temporal lobe epilepsy, but carries an inherent risk of disabling verbal memory loss. Although accurate prediction of iatrogenic memory loss is becoming increasingly possible, it remains unclear how much weight such predictions should have in surgical decision making. Here we aim to create a framework that facilitates a systematic and integrated assessment of the relative risks and benefits of surgery versus medical management for patients with left temporal lobe epilepsy.We constructed a Markov decision model to evaluate the probabilistic outcomes and associated health utilities associated with choosing to undergo a left anterior temporal lobectomy versus continuing with medical management for patients with medically refractory left temporal lobe epilepsy. Three base-cases were considered, representing a spectrum of surgical candidates encountered in practice, with varying degrees of epilepsy-related disability and potential for decreased quality of life in response to post-surgical verbal memory deficits.For patients with moderately severe seizures and moderate risk of verbal memory loss, medical management was the preferred decision, with increased quality-adjusted life expectancy. However, the preferred choice was sensitive to clinically meaningful changes in several parameters, including quality of life impact of verbal memory decline, quality of life with seizures, mortality rate with medical management, probability of remission following surgery, and probability of remission with medical management.Our decision model suggests that for patients with left temporal lobe epilepsy, quantitative assessment of risk and benefit should guide recommendation of therapy. In particular, risk for and potential impact of verbal memory decline should be carefully weighed against the degree of disability conferred by continued seizures on a patient-by-patient basis.

  View details for DOI 10.1111/epi.12790

  View details for PubMedID 25244498

  View details for PubMedCentralID PMC4877127

• Applications of a Capacitor-Based Respiratory Position Sensing Device: Implications for Radiation Therapy. Austin journal of medical oncology Y, W., Mb, W., C, S., G, S., Mt, B., Kd, W. 2014; 1 (2)

  Abstract

  Respiratory motion may significantly affect the outcome in a number of medical imaging techniques and some radiation therapy applications. 4-dimensional computed tomography (4DCT) and respiratory gating technology, which account for the dynamics of respiration, are expensive and often unavailable in smaller radiation treatment centers. Here we evaluate the ability of an inexpensive, technology comprised of two capacitors placed next to the skin to provide real-time respiratory phase information. Three subjects were simultaneously monitored by the new capacitor-based device (CBD) and a commercially available Real time Position Management (RPM) system by Varian. All respiratory phases detected by the RPM system were also detected by the CBD. Automatically detected peaks were not significantly different in timing when comparing RPM and CBD-derived respiratory amplitudes. The anatomic locations of the CBD were varied to evaluate the change in signal quality across the abdomen and thorax. CBD signals were reliable on the abdomen and lower thorax but degraded when recorded from the upper thorax. We also used computed tomography (CT) to assess the imaging characteristics of CBD and found that there were minimal artifacts. We therefore conclude that CBD respiratory amplitude measurements may be useful for tracking respiratory movements as part of a number of advanced radiation therapy technologies including 4DCT image resorting, adaptive radiation therapy and gated radiation therapy.

  View details for PubMedID 31934681

  View details for PubMedCentralID PMC6956860

• 3D-CAM: derivation and validation of a 3-minute diagnostic interview for CAM-defined delirium: a cross-sectional diagnostic test study. Annals of internal medicine Marcantonio, E. R., Ngo, L. H., O'Connor, M., Jones, R. N., Crane, P. K., Metzger, E. D., Inouye, S. K. 2014; 161 (8): 554-61

  Abstract

  Delirium is common, leads to other adverse outcomes, and is costly. However, it often remains unrecognized in most clinical settings. The Confusion Assessment Method (CAM) is the most widely used diagnostic algorithm, and operationalizing its features would be a substantial advance for clinical care.To derive the 3D-CAM, a new 3-minute diagnostic assessment for CAM-defined delirium, and validate it against a clinical reference standard.Derivation and validation study.4 general medicine units in an academic medical center.201 inpatients aged 75 years or older.20 items that best operationalized the 4 CAM diagnostic features were identified to create the 3D-CAM. For prospective validation, 3D-CAM assessments were administered by trained research assistants. Clinicians independently did an extensive assessment, including patient and family interviews and medical record reviews. These data were considered by an expert panel to determine the presence or absence of delirium and dementia (reference standard). The 3D-CAM delirium diagnosis was compared with the reference standard in all patients and subgroups with and without dementia.The 201 participants in the prospective validation study had a mean age of 84 years, and 28% had dementia. The expert panel identified 21% with delirium, 88% of whom had hypoactive or normal psychomotor features. Median administration time for the 3D-CAM was 3 minutes (interquartile range, 2 to 5 minutes), sensitivity was 95% (95% CI, 84% to 99%), and specificity was 94% (CI, 90% to 97%). The 3D-CAM did well in patients with dementia (sensitivity, 96% [CI, 82% to 100%]; specificity, 86% [CI, 67% to 96%]) and without dementia (sensitivity, 93% [CI, 66% to 100%]; specificity, 96% [CI, 91% to 99%]).Limited to single-center, cross-sectional, and medical patients only.The 3D-CAM operationalizes the CAM algorithm using a 3-minute structured assessment with high sensitivity and specificity relative to a reference standard and could be an important tool for improving recognition of delirium.National Institute on Aging.

  View details for DOI 10.7326/M14-0865

  View details for PubMedID 25329203

  View details for PubMedCentralID PMC4319978

• Sparse extreme learning machine for classification. IEEE transactions on cybernetics Bai, Z., Huang, G. B., Wang, D., Wang, H., Westover, M. B. 2014; 44 (10): 1858-70

  Abstract

  Extreme learning machine (ELM) was initially proposed for single-hidden-layer feedforward neural networks (SLFNs). In the hidden layer (feature mapping), nodes are randomly generated independently of training data. Furthermore, a unified ELM was proposed, providing a single framework to simplify and unify different learning methods, such as SLFNs, least square support vector machines, proximal support vector machines, and so on. However, the solution of unified ELM is dense, and thus, usually plenty of storage space and testing time are required for large-scale applications. In this paper, a sparse ELM is proposed as an alternative solution for classification, reducing storage space and testing time. In addition, unified ELM obtains the solution by matrix inversion, whose computational complexity is between quadratic and cubic with respect to the training size. It still requires plenty of training time for large-scale problems, even though it is much faster than many other traditional methods. In this paper, an efficient training algorithm is specifically developed for sparse ELM. The quadratic programming problem involved in sparse ELM is divided into a series of smallest possible sub-problems, each of which are solved analytically. Compared with SVM, sparse ELM obtains better generalization performance with much faster training speed. Compared with unified ELM, sparse ELM achieves similar generalization performance for binary classification applications, and when dealing with large-scale binary classification problems, sparse ELM realizes even faster training speed than unified ELM.

  View details for DOI 10.1109/TCYB.2014.2298235

  View details for PubMedID 25222727

  View details for PubMedCentralID PMC4883115

• Aspirin for secondary prevention after stroke of unknown etiology in resource-limited settings. Neurology Berkowitz, A. L., Westover, M. B., Bianchi, M. T., Chou, S. H. 2014; 83 (11): 1004-11

  Abstract

  To analyze the potential impact of aspirin therapy for long-term secondary prevention after stroke of undetermined etiology in resource-limited settings without access to neuroimaging to distinguish ischemic stroke from intracerebral hemorrhage (ICH).We conducted a decision analysis using a Markov state transition model. Sensitivity analyses were performed across the worldwide reported range of the proportion of strokes due to ICH and the 95% confidence intervals (CIs) of aspirin-associated relative risks in patients with ICH.For patients with stroke of undetermined etiology, long-term aspirin was the preferred treatment strategy across the worldwide reported range of the proportion of strokes due to ICH. At 34% of strokes due to ICH (the highest proportion reported in a large epidemiologic study), the benefit of aspirin remained beyond the upper bounds of the 95% CIs of aspirin-associated post-ICH relative risks most concerning to clinicians (ICH recurrence risk and mortality risk if ICH recurs on aspirin). Based on the estimated 11,590,204 strokes in low- and middle-income countries in 2010, our model predicts that aspirin therapy for secondary stroke prevention in all patients with stroke in these countries could lead to an estimated yearly decrease of 84,492 recurrent strokes and 4,056 stroke-related mortalities.The concern that the risks of aspirin in patients with stroke of unknown etiology could outweigh the benefits is not supported by our model, which predicts that aspirin for secondary prevention in patients with stroke of undetermined etiology in resource-limited settings could lead to decreased stroke-related mortality and stroke recurrence.

  View details for DOI 10.1212/WNL.0000000000000779

  View details for PubMedID 25122202

  View details for PubMedCentralID PMC4162302

• Interrater agreement for Critical Care EEG Terminology. Epilepsia Gaspard, N., Hirsch, L. J., LaRoche, S. M., Hahn, C. D., Westover, M. B. 2014; 55 (9): 1366-73

  Abstract

  The interpretation of critical care electroencephalography (EEG) studies is challenging because of the presence of many periodic and rhythmic patterns of uncertain clinical significance. Defining the clinical significance of these patterns requires standardized terminology with high interrater agreement (IRA). We sought to evaluate IRA for the final, published American Clinical Neurophysiology Society (ACNS)-approved version of the critical care EEG terminology (2012 version). Our evaluation included terms not assessed previously and incorporated raters with a broad range of EEG reading experience.After reviewing a set of training slides, 49 readers independently completed a Web-based test consisting of 11 identical questions for each of 37 EEG samples (407 questions). Questions assessed whether a pattern was an electrographic seizure; pattern location (main term 1), pattern type (main term 2); and presence and classification of eight other key features ("plus" modifiers, sharpness, absolute and relative amplitude, frequency, number of phases, fluctuation/evolution, and the presence of "triphasic" morphology).IRA statistics (κ values) were almost perfect (90-100%) for seizures, main terms 1 and 2, the +S modifier (superimposed spikes/sharp waves or sharply contoured rhythmic delta activity), sharpness, absolute amplitude, frequency, and number of phases. Agreement was substantial for the +F (superimposed fast activity) and +R (superimposed rhythmic delta activity) modifiers (66% and 67%, respectively), moderate for triphasic morphology (58%), and fair for evolution (21%).IRA for most terms in the ACNS critical care EEG terminology is high. These terms are suitable for multicenter research on the clinical significance of critical care EEG patterns. A PowerPoint slide summarizing this article is available for download in the Supporting Information section http://dx.doi.org/10.1111/epi.12653/supinfo.

  View details for DOI 10.1111/epi.12653

  View details for PubMedID 24888711

  View details for PubMedCentralID PMC4879939

• Aspirin for acute stroke of unknown etiology in resource-limited settings A decision analysis NEUROLOGY Berkowitz, A. L., Westover, M., Bianchi, M. T., Chou, S. 2014; 83 (9): 787-793

  View details for DOI 10.1212/WNL.0000000000000730

  View details for Web of Science ID 000341096100007

• The challenge of undiagnosed sleep apnea in low-risk populations: a decision analysis. Military medicine Bianchi, M. T., Hershman, S., Bahadoran, M., Ferguson, M., Westover, M. B. 2014; 179 (8 Suppl): 47-54

  Abstract

  Obstructive sleep apnea (OSA) may contribute to impaired performance among otherwise healthy active duty military personnel. We used decision analysis to evaluate three approaches to identifying and treating OSA in low-risk populations, which may differ from current standard practice for high-risk populations.We developed a decision tree to compare two simple strategies for diagnosis and management of sleep apnea in a low-risk population. In one strategy, a simple screening inventory was followed by conventional laboratory polysomnography (split-night), whereas the alternative strategy involved performing home testing in all individuals. This allowed us to weigh the costs associated with large-scale diagnostic approaches against the costs of untreated OSA in a small fraction of the population.We found that the home testing approach was less expensive than the screen-then-test approach across a broad range of other important parameters, including the annual performance cost associated with untreated OSA, the prevalence of OSA, and the duration of active duty.Assuming even modest annual performance costs associated with untreated OSA, a population strategy involving large-scale home testing is less expensive than a screening inventory approach. These results may inform either targeted or large-scale investigation of undiagnosed OSA in low-risk populations such as active duty military.

  View details for DOI 10.7205/MILMED-D-13-00483

  View details for PubMedID 25102549

  View details for PubMedCentralID PMC6788752

• Spectrogram screening of adult EEGs is sensitive and efficient. Neurology Moura, L. M., Shafi, M. M., Ng, M., Pati, S., Cash, S. S., Cole, A. J., Hoch, D. B., Rosenthal, E. S., Westover, M. B. 2014; 83 (1): 56-64

  Abstract

  Quantitatively evaluate whether screening with compressed spectral arrays (CSAs) is a practical and time-effective protocol for assisting expert review of continuous EEG (cEEG) studies in hospitalized adults.Three neurophysiologists reviewed the reported findings of the first 30 minutes of 118 cEEGs, then used CSA to guide subsequent review ("CSA-guided review" protocol). Reviewers viewed 120 seconds of raw EEG data surrounding suspicious CSA segments. The same neurophysiologists performed independent page-by-page visual interpretation ("conventional review") of all cEEGs. Independent conventional review by 2 additional, more experienced neurophysiologists served as a gold standard. We compared review times and detection rates for seizures and other pathologic patterns relative to conventional review.A total of 2,092 hours of cEEG data were reviewed. Average times to review 24 hours of cEEG data were 8 (±4) minutes for CSA-guided review vs 38 (±17) minutes for conventional review (p < 0.005). Studies containing seizures required longer review: 10 (±4) minutes for CSA-guided review vs 44 (±20) minutes for conventional review (p < 0.005). CSA-guided review was sensitive for seizures (87.3%), periodic epileptiform discharges (100%), rhythmic delta activity (97.1%), focal slowing (98.7%), generalized slowing (100%), and epileptiform discharges (88.5%).CSA-guided review reduces cEEG review time by 78% with minimal loss of sensitivity compared with conventional review.This study provides Class IV evidence that screening of cEEG with CSAs efficiently and accurately identifies seizures and other EEG abnormalities as compared with standard cEEG visual interpretation.

  View details for DOI 10.1212/WNL.0000000000000537

  View details for PubMedID 24857926

  View details for PubMedCentralID PMC4114174

• Insomnia and morning motor vehicle accidents: a decision analysis of the risk of hypnotics versus the risk of untreated insomnia. Journal of clinical psychopharmacology Bianchi, M. T., Westover, M. B. 2014; 34 (3): 400-2

  View details for DOI 10.1097/JCP.0000000000000134

  View details for PubMedID 24743722

  View details for PubMedCentralID PMC6794095

• Randomized ICU trials do not demonstrate an association between interventions that reduce delirium duration and short-term mortality: a systematic review and meta-analysis. Critical care medicine Al-Qadheeb, N. S., Balk, E. M., Fraser, G. L., Skrobik, Y., Riker, R. R., Kress, J. P., Whitehead, S., Devlin, J. W. 2014; 42 (6): 1442-54

  Abstract

  We reviewed randomized trials of adult ICU patients of interventions hypothesized to reduce delirium burden to determine whether interventions that are more effective at reducing delirium duration are associated with a reduction in short-term mortality.We searched CINHAHL, EMBASE, MEDLINE, and the Cochrane databases from 2001 to 2012.Citations were screened for randomized trials that enrolled critically ill adults, evaluated delirium at least daily, compared a drug or nondrug intervention hypothesized to reduce delirium burden with standard care (or control), and reported delirium duration and/or short-term mortality (≤ 45 d).In duplicate, we abstracted trial characteristics and results and evaluated quality using the Cochrane risk of bias tool. We performed random effects model meta-analyses and meta-regressions.We included 17 trials enrolling 2,849 patients which evaluated a pharmacologic intervention (n = 13) (dexmedetomidine [n = 6], an antipsychotic [n = 4], rivastigmine [n = 2], and clonidine [n = 1]), a multimodal intervention (n = 2) (spontaneous awakening [n = 2]), or a nonpharmacologic intervention (n = 2) (early mobilization [n = 1] and increased perfusion [n = 1]). Overall, average delirium duration was lower in the intervention groups (difference = -0.64 d; 95% CI, -1.15 to -0.13; p = 0.01) being reduced by more than or equal to 3 days in three studies, 0.1 to less than 3 days in six studies, 0 day in seven studies, and less than 0 day in one study. Across interventions, for 13 studies where short-term mortality was reported, short-term mortality was not reduced (risk ratio = 0.90; 95% CI, 0.76-1.06; p = 0.19). Across 13 studies that reported mortality, meta-regression revealed that delirium duration was not associated with reduced short-term mortality (p = 0.11).A review of current evidence fails to support that ICU interventions that reduce delirium duration reduce short-term mortality. Larger controlled studies are needed to establish this relationship.

  View details for DOI 10.1097/CCM.0000000000000224

  View details for PubMedID 24557420

  View details for PubMedCentralID PMC4799649

• Automated sleep apnea quantification based on respiratory movement. International journal of medical sciences Bianchi, M. T., Lipoma, T., Darling, C., Alameddine, Y., Westover, M. B. 2014; 11 (8): 796-802

  Abstract

  Obstructive sleep apnea (OSA) is a prevalent and treatable disorder of neurological and medical importance that is traditionally diagnosed through multi-channel laboratory polysomnography(PSG). However, OSA testing is increasingly performed with portable home devices using limited physiological channels. We tested the hypothesis that single channel respiratory effort alone could support automated quantification of apnea and hypopnea events. We developed a respiratory event detection algorithm applied to thoracic strain-belt data from patients with variable degrees of sleep apnea. We optimized parameters on a training set (n=57) and then tested performance on a validation set (n=59). The optimized algorithm correlated significantly with manual scoring in the validation set (R2=0.73 for training set, R2=0.55 for validation set; p<0.05). For dichotomous classification, the AUC was >0.92 and >0.85 using apnea-hypopnea index cutoff values of 5 and 15, respectively. Our findings demonstrate that manually scored AHI values can be approximated from thoracic movements alone. This finding has potential applications for automating laboratory PSG analysis as well as improving the performance of limited channel home monitors.

  View details for DOI 10.7150/ijms.9303

  View details for PubMedID 24936142

  View details for PubMedCentralID PMC4057486

• The information theoretic perspective on medical diagnostic inference. Hospital practice (1995) Eiseman, N. A., Bianchi, M. T., Westover, M. B. 2014; 42 (2): 125-38

  Abstract

  The goal of this work is to present information theory, specifically Claude Shannon's mathematical theory of communication, in a clinical context and elucidate its potential contributions to understanding the process of diagnostic inference. We use probability theory, information theory, and clinical examples to develop information theory as a means to examine uncertainty in diagnostic testing situations. We begin our discussion with a brief review of probability theory as it relates to diagnostic testing. An outline of Shannon's theory of communication theory and how it directly translates to the medical diagnostic process serves as the essential justification for this article. Finally, we introduce the mathematical tools of information theory that allow for an understanding of diagnostic uncertainty and test effectiveness in a variety of contexts. We show that information theory provides a quantitative framework for understanding uncertainty that readily extends to medical diagnostic contexts.

  View details for DOI 10.3810/hp.2014.04.1110

  View details for PubMedID 24769791

  View details for PubMedCentralID PMC6993929

• Burst suppression in sleep in a routine outpatient EEG. Epilepsy & behavior case reports Kheder, A., Bianchi, M. T., Westover, M. B. 2014; 2: 71-4

  Abstract

  Burst suppression (BS) is an electroencephalogram (EEG) pattern that is characterized by brief bursts of spikes, sharp waves, or slow waves of relatively high amplitude alternating with periods of relatively flat EEG or isoelectric periods. The pattern is usually associated with coma, severe encephalopathy of various etiologies, or general anesthesia. We describe an unusual case of anoxic brain injury in which a BS pattern was seen during behaviorally defined sleep during a routine outpatient EEG study.

  View details for DOI 10.1016/j.ebcr.2014.01.003

  View details for PubMedID 25667874

  View details for PubMedCentralID PMC4308090

• Treating seizures in Creutzfeldt-Jakob disease. Epilepsy & behavior case reports Ng, M. C., Westover, M. B., Cole, A. J. 2014; 2: 75-9

  Abstract

  Seizures are known to occur in Creutzfeldt-Jakob disease (CJD). In the setting of a rapidly progressive condition with no effective therapy, determining appropriate treatment for seizures can be difficult if clinical morbidity is not obvious yet the electroencephalogram (EEG) demonstrates a worrisome pattern such as status epilepticus. Herein, we present the case of a 39-year-old man with CJD and electrographic seizures, discuss how this case challenges conventional definitions of seizures, and discuss a rational approach toward treatment. Coincidentally, our case is the first report of CJD in a patient with Stickler syndrome.

  View details for DOI 10.1016/j.ebcr.2014.01.004

  View details for PubMedID 25667875

  View details for PubMedCentralID PMC4308028

• Sensitivity of compressed spectral arrays for detecting seizures in acutely ill adults. Neurocritical care Williamson, C. A., Wahlster, S., Shafi, M. M., Westover, M. B. 2014; 20 (1): 32-9

  Abstract

  Continuous EEG recordings (cEEGs) are increasingly used in evaluation of acutely ill adults. Pre-screening using compressed data formats, such as compressed spectral array (CSA), may accelerate EEG review. We tested whether screening with CSA can enable detection of seizures and other relevant patterns.Two individuals reviewed the CSA displays of 113 cEEGs. While blinded to the raw EEG data, they marked each visually homogeneous CSA segment. An independent experienced electroencephalographer reviewed the raw EEG within 60 s on either side of each mark and recorded any seizures (and isolated epileptiform discharges, periodic epileptiform discharges (PEDs), rhythmic delta activity (RDA), and focal or generalized slowing). Seizures were considered to have been detected if the CSA mark was within 60 s of the seizure. The electroencephalographer then determined the total number of seizures (and other critical findings) for each record by exhaustive, page-by-page review of the entire raw EEG.Within each of the 39 cEEG recordings containing seizures, one CSA reviewer identified at least one seizure, while the second CSA reviewer identified 38/39 patients with seizures. The overall detection rate was 89.0 % of 1,190 total seizures. When present, an average of 87.9 % of seizures were detected per individual patient. Detection rates for other critical findings were as follows: epileptiform discharges, 94.0 %; PEDs, 100 %; RDA, 97.9 %; focal slowing, 100 %; and generalized slowing, 100 %.CSA-guided review can support sensitive screening of critical pathological information in cEEG recordings. However, some patients with seizures may not be identified.

  View details for DOI 10.1007/s12028-013-9912-4

  View details for PubMedID 24052456

  View details for PubMedCentralID PMC6794096

• SpikeGUI: software for rapid interictal discharge annotation via template matching and online machine learning. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference , Dauwels, J., Cash, S., Westover, M. B. 2014; 2014: 4435-8

  Abstract

  Detection of interictal discharges is a key element of interpreting EEGs during the diagnosis and management of epilepsy. Because interpretation of clinical EEG data is time-intensive and reliant on experts who are in short supply, there is a great need for automated spike detectors. However, attempts to develop general-purpose spike detectors have so far been severely limited by a lack of expert-annotated data. Huge databases of interictal discharges are therefore in great demand for the development of general-purpose detectors. Detailed manual annotation of interictal discharges is time consuming, which severely limits the willingness of experts to participate. To address such problems, a graphical user interface "SpikeGUI" was developed in our work for the purposes of EEG viewing and rapid interictal discharge annotation. "SpikeGUI" substantially speeds up the task of annotating interictal discharges using a custom-built algorithm based on a combination of template matching and online machine learning techniques. While the algorithm is currently tailored to annotation of interictal epileptiform discharges, it can easily be generalized to other waveforms and signal types.

  View details for DOI 10.1109/EMBC.2014.6944608

  View details for PubMedID 25570976

  View details for PubMedCentralID PMC4416962

• Technology and the future of healthcare. Journal of public health research Thimbleby, H. 2013; 2 (3): e28

  Abstract

  Healthcare changes dramatically because of technological developments, from anesthetics and antibiotics to magnetic resonance imaging scanners and radiotherapy. Future technological innovation is going to keep transforming healthcare, yet while technologies (new drugs and treatments, new devices, new social media support for healthcare, etc) will drive innovation, human factors will remain one of the stable limitations of breakthroughs. No predictions can satisfy everybody; instead, this article explores fragments of the future to see how to think more clearly about how to get where we want to go. Significance for public healthTechnology drives healthcare more than any other force, and in the future it will continue to develop in dramatic ways. While we can glimpse and debate the details of future trends in healthcare, we need to be clear about the drivers so we can align with them and actively work to ensure the best outcomes for society as a whole.

  View details for DOI 10.4081/jphr.2013.e28

  View details for PubMedID 25170499

  View details for PubMedCentralID PMC4147743

• Anterior nucleus of the thalamus: functional organization and clinical implications. Neurology Child, N. D., Benarroch, E. E. 2013; 81 (21): 1869-76

  Abstract

  The anterior nucleus of thalamus (ANT) is a key component of the hippocampal system for episodic memory. The ANT consist of 3 subnuclei with distinct connectivity with the subicular cortex, retrosplenial cortex, and mammillary bodies. Via its connections with the anterior cingulate and orbitomedial prefrontal cortex, the ANT may also contribute to reciprocal hippocampal-prefrontal interactions involved in emotional and executive functions. As in other thalamic nuclei, neurons of the ANT have 2 different state-dependent patterns of discharge, tonic and burst-firing; some ANT neurons also contribute to propagation of the theta rhythm, which is important for mechanisms of synaptic plasticity of the hippocampal circuit. Clinical and experimental evidence indicate that damage of the ANT or its inputs from the mammillary bodies are primarily responsible for the episodic memory deficit observed in Wernicke-Korsakoff syndrome and thalamic stroke. Experimental models also indicate that the ANT may have a role in the propagation of seizure activity both in absence and in focal seizures. Because of its central connectivity and possible role in propagation of seizure activity, the ANT has become an attractive target for deep brain stimulation (DBS) for treatment of medically refractory epilepsy. The ANT is one of the nuclei preferentially affected in prion disorders, such as fatal familial insomnia, but the relationship between ANT involvement and the clinical manifestations of these disorders remains unclear. The connectivity patterns and electrophysiology of the ANT have been the subject of several reviews.(1-4.)

  View details for DOI 10.1212/01.wnl.0000436078.95856.56

  View details for PubMedID 24142476

• Sleep drives metabolite clearance from the adult brain. Science (New York, N.Y.) Xie, L., Kang, H., Xu, Q., Chen, M. J., Liao, Y., Thiyagarajan, M., O'Donnell, J., Christensen, D. J., Nicholson, C., Iliff, J. J., Takano, T., Deane, R., Nedergaard, M. 2013; 342 (6156): 373-7

  Abstract

  The conservation of sleep across all animal species suggests that sleep serves a vital function. We here report that sleep has a critical function in ensuring metabolic homeostasis. Using real-time assessments of tetramethylammonium diffusion and two-photon imaging in live mice, we show that natural sleep or anesthesia are associated with a 60% increase in the interstitial space, resulting in a striking increase in convective exchange of cerebrospinal fluid with interstitial fluid. In turn, convective fluxes of interstitial fluid increased the rate of β-amyloid clearance during sleep. Thus, the restorative function of sleep may be a consequence of the enhanced removal of potentially neurotoxic waste products that accumulate in the awake central nervous system.

  View details for DOI 10.1126/science.1241224

  View details for PubMedID 24136970

  View details for PubMedCentralID PMC3880190

• Real-time segmentation and tracking of brain metabolic state in ICU EEG recordings of burst suppression. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Westover, M. B., Ching, S., Shafi, M. M., Cash, S. S., Brown, E. N. 2013; 2013: 7108-11

  Abstract

  We provide a method for estimating brain metabolic state based on a reduced-order model of EEG burst suppression. The model, derived from previously suggested biophysical mechanisms of burst suppression, describes important electrophysiological features and provides a direct link to cerebral metabolic rate. We design and fit the estimation method from EEG recordings of burst suppression from a neurological intensive care unit and test it on real and synthetic data.

  View details for DOI 10.1109/EMBC.2013.6611196

  View details for PubMedID 24111383

  View details for PubMedCentralID PMC3939432

• Electroencephalography of encephalopathy in patients with endocrine and metabolic disorders. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Faigle, R., Sutter, R., Kaplan, P. W. 2013; 30 (5): 505-16

  Abstract

  Patients with acute alteration in mental status from encephalopathy because of underlying metabolic-toxic or endocrine abnormalities are frequently seen in the acute hospital setting. A rapid diagnosis and correction of the underlying cause is essential as a prolonged state of encephalopathy portends a poor outcome. Correct diagnosis and management remain challenging because several encephalopathies may present similarly, and further laboratory, imaging, or other testing may not always reveal the underlying cause. EEG provides rapid additional information on the encephalopathic patient. It may help establish the diagnosis and is indispensable for identifying nonconvulsive status epilepticus, an important possible complication in this context. The EEG may assist the clinician in gauging the severity of brain dysfunction and may aid in predicting outcome. This review summarizes the current knowledge on EEG findings in selected metabolic and endocrine causes of encephalopathy and highlights distinct EEG features associated with particular etiologies.

  View details for DOI 10.1097/WNP.0b013e3182a73db9

  View details for PubMedID 24084183

  View details for PubMedCentralID PMC3826953

• Real-time closed-loop control in a rodent model of medically induced coma using burst suppression. Anesthesiology Ching, S., Liberman, M. Y., Chemali, J. J., Westover, M. B., Kenny, J. D., Solt, K., Purdon, P. L., Brown, E. N. 2013; 119 (4): 848-60

  Abstract

  A medically induced coma is an anesthetic state of profound brain inactivation created to treat status epilepticus and to provide cerebral protection after traumatic brain injuries. The authors hypothesized that a closed-loop anesthetic delivery system could automatically and precisely control the electroencephalogram state of burst suppression and efficiently maintain a medically induced coma.In six rats, the authors implemented a closed-loop anesthetic delivery system for propofol consisting of: a computer-controlled pump infusion, a two-compartment pharmacokinetics model defining propofol's electroencephalogram effects, the burst-suppression probability algorithm to compute in real time from the electroencephalogram the brain's burst-suppression state, an online parameter-estimation procedure and a proportional-integral controller. In the control experiment each rat was randomly assigned to one of the six burst-suppression probability target trajectories constructed by permuting the burst-suppression probability levels of 0.4, 0.65, and 0.9 with linear transitions between levels.In each animal the controller maintained approximately 60 min of tight, real-time control of burst suppression by tracking each burst-suppression probability target level for 15 min and two between-level transitions for 5-10 min. The posterior probability that the closed-loop anesthetic delivery system was reliable across all levels was 0.94 (95% CI, 0.77-1.00; n = 18) and that the system was accurate across all levels was 1.00 (95% CI, 0.84-1.00; n = 18).The findings of this study establish the feasibility of using a closed-loop anesthetic delivery systems to achieve in real time reliable and accurate control of burst suppression in rodents and suggest a paradigm to precisely control medically induced coma in patients.

  View details for DOI 10.1097/ALN.0b013e31829d4ab4

  View details for PubMedID 23770601

  View details for PubMedCentralID PMC3857134

• Automatic detection of interictal epileptiform discharges based on time-series sequence merging method NEUROCOMPUTING Zhang, J., Zou, J., Wang, M., Chen, L., Wang, C., Wang, G. 2013; 110: 35-43

  View details for DOI 10.1016/j.neucom.2012.11.017

  View details for Web of Science ID 000318457700005

• Estimating cerebral microinfarct burden from autopsy samples. Neurology Westover, M. B., Bianchi, M. T., Yang, C., Schneider, J. A., Greenberg, S. M. 2013; 80 (15): 1365-9

  Abstract

  To estimate whole-brain microinfarct burden from microinfarct counts in routine postmortem examination.We developed a simple mathematical method to estimate the total number of cerebral microinfarcts from counts obtained in the small amount of tissue routinely examined in brain autopsies. We derived estimates of total microinfarct burden from autopsy brain specimens from 648 older participants in 2 community-based clinical-pathologic cohort studies of aging and dementia.Our results indicate that observing 1 or 2 microinfarcts in 9 routine neuropathologic specimens implies a maximum-likelihood estimate of 552 or 1,104 microinfarcts throughout the brain. Similar estimates were obtained when validating in larger sampled brain volumes.The substantial whole-brain burden of cerebral microinfarcts suggested by even a few microinfarcts on routine pathologic sampling suggests a potential mechanism by which these lesions could cause neurologic dysfunction in individuals with small-vessel disease. The estimation framework developed here may generalize to clinicopathologic correlations of other imaging-negative micropathologies.

  View details for DOI 10.1212/WNL.0b013e31828c2f52

  View details for PubMedID 23486880

  View details for PubMedCentralID PMC3662273

• Agreement in Computer-Assisted Manual Scoring of Polysomnograms across Sleep Centers SLEEP Kuna, S. T., Benca, R., Kushida, C. A., Walsh, J., Younes, M., Staley, B., Hanlon, A., Pack, A. I., Pien, G. W., Malhotra, A. 2013; 36 (4): 583-589

  Abstract

  To determine intersite agreement in respiratory event scoring of polysomnograms (PSGs) using different hypopnea definitions.Technical assessment.Five academic medical centers.N/A.N/A.Seventy good-quality PSGs performed in middle-aged women were manually scored by two experienced technologists at each of the five sleep centers using the particular laboratory's own software system. Studies were scored once by each scorer using American Academy of Sleep Medicine (AASM) standards for scoring sleep stages, arousals, and apneas. Hypopneas were then scored using three different AASM criteria: recommended, alternate, and research (Chicago). Means of each PSG variable for the scorers at each site were used to calculate an across-site intraclass correlation coefficient (ICC). Average AHI across the 10 scorers was 7.4 ± 12.3 (standard deviation) events/h using recommended criteria (ICC 0.984; 95% confidence interval [CI] 0.977-0.990), 12.1 ± 13.3 events/h using alternate criteria (ICC 0.947; 95% CI 0.889-0.972), and 15.1 ± 13.9 events/h with Chicago criteria (ICC 0.800; 95% CI 0.768-0.828). ICC across sites was 0.870 (95% CI = 0.847-0.889) for total sleep time, 0.861 (95% CI 0.837-0.881) for number of obstructive apneas and 0.683 (95% CI 0.640-0.722) for number of central apneas. ICCs across sites for hypopneas were very good using recommended criteria (ICC 0.843; 95% CI 0.820-0.870) but decreased when alternate criteria (ICC 0.728; 95% CI 0.689-0.763) and Chicago criteria (ICC 0.535; 95% CI 0.485-0.583) were used.Experienced scorers at different laboratories have very good agreement in hypopnea and AHI results when good-quality PSGs are scored using AASM-recommended criteria. Substantial degradation of reliability was observed for alternative definitions of hypopneas, particularly that proposed for research.

  View details for DOI 10.5665/sleep.2550

  View details for Web of Science ID 000316939000018

  View details for PubMedID 23565004

  View details for PubMedCentralID PMC3612259

• Inferring seizure frequency from brief EEG recordings. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Westover, M. B., Bianchi, M. T., Shafi, M., Hoch, D. B., Cole, A. J., Chiappa, K., Cash, S. S. 2013; 30 (2): 174-7

  Abstract

  Routine EEGs remain a cornerstone test in caring for people with epilepsy. Although rare, a self-limited seizure (clinical or electrographic only) may be observed during such brief EEGs. The implications of observing a seizure in this situation, especially with respect to inferring the underlying seizure frequency, are unclear. The issue is complicated by the inaccuracy of patient-reported estimations of seizure frequency. The treating clinician is often left to wonder whether the single seizure indicates very frequent seizures, or if it is of lesser significance. We applied standard concepts of probabilistic inference to a simple model of seizure incidence to provide some guidance for clinicians facing this situation. Our analysis establishes upper and lower bounds on the seizure rate implied by observing a single seizure during routine EEG. Not surprisingly, with additional information regarding the expected seizure rate, these bounds can be further constrained. This framework should aid the clinician in applying a more principled approach toward decision making in the setting of a single seizure on a routine EEG.

  View details for DOI 10.1097/WNP.0b013e3182767c35

  View details for PubMedID 23545768

  View details for PubMedCentralID PMC3616271

• Calculating the risk benefit equation for aggressive treatment of non-convulsive status epilepticus. Neurocritical care Ferguson, M., Bianchi, M. T., Sutter, R., Rosenthal, E. S., Cash, S. S., Kaplan, P. W., Westover, M. B. 2013; 18 (2): 216-27

  Abstract

  To address the question: does non-convulsive status epilepticus warrant the same aggressive treatment as convulsive status epilepticus?We used a decision model to evaluate the risks and benefits of treating non-convulsive status epilepticus with intravenous anesthetics and ICU-level aggressive care. We investigated how the decision to use aggressive versus non-aggressive management for non-convulsive status epilepticus impacts expected patient outcome for four etiologies: absence epilepsy, discontinued antiepileptic drugs, intraparenchymal hemorrhage, and hypoxic ischemic encephalopathy. Each etiology was defined by distinct values for five key parameters: baseline mortality rate of the inciting etiology; efficacy of non-aggressive treatment in gaining control of seizures; the relative contribution of seizures to overall mortality; the degree of excess disability expected in the case of delayed seizure control; and the mortality risk of aggressive treatment.Non-aggressive treatment was favored for etiologies with low morbidity and mortality such as absence epilepsy and discontinued antiepileptic drugs. The risk of aggressive treatment was only warranted in etiologies where there was significant risk of seizure-induced neurologic damage. In the case of post-anoxic status epilepticus, expected outcomes were poor regardless of the treatment chosen. The favored strategy in each case was determined by strong interactions of all five model parameters.Determination of the optimal management approach to non-convulsive status epilepticus is complex and is ultimately determined by the inciting etiology.

  View details for DOI 10.1007/s12028-012-9785-y

  View details for PubMedID 23065689

  View details for PubMedCentralID PMC3767472

• Reversible vasoconstriction syndrome with bilateral basal ganglia hemorrhages. Journal of neuroimaging : official journal of the American Society of Neuroimaging Westover, M. B., Cohen, A. B. 2013; 23 (1): 122-5

  Abstract

  Reversible cerebral vasoconstriction syndrome (RCVS) is an increasingly recognized acute cerebrovascular condition that may produce myriad transient and sustained neurologic deficits as well as a host of radiologic features. We report the case of a woman with RCVS and a severe clinical syndrome with bilateral basal ganglia hemorrhages, cerebral infarctions, and marked vascular abnormalities. The patient made a near complete clinical recovery, representing an extreme and illustrative form of RCVS.

  View details for DOI 10.1111/j.1552-6569.2011.00645.x

  View details for PubMedID 21899647

  View details for PubMedCentralID PMC6788746

• The impact of body posture and sleep stages on sleep apnea severity in adults. Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine Eiseman, N. A., Westover, M. B., Ellenbogen, J. M., Bianchi, M. T. 2012; 8 (6): 655-66A

  Abstract

  Determining the presence and severity of obstructive sleep apnea (OSA) is based on apnea and hypopnea event rates per hour of sleep. Making this determination presents a diagnostic challenge, given that summary metrics do not consider certain factors that influence severity, such as body position and the composition of sleep stages.We retrospectively analyzed 300 consecutive diagnostic PSGs performed at our center to determine the impact of body position and sleep stage on sleep apnea severity.The median percent of REM sleep was 16% (reduced compared to a normal value of ~25%). The median percent supine sleep was 65%. Fewer than half of PSGs contained > 10 min in each of the 4 possible combinations of REM/NREM and supine/non-supine. Half of patients had > 2-fold worsening of the apnea-hypopnea index (AHI) in REM sleep, and 60% had > 2-fold worsening of AHI while supine. Adjusting for body position had greater impact on the AHI than adjusting for reduced REM%. Misclassification--specifically underestimation of OSA severity--is attributed more commonly to body position (20% to 40%) than to sleep stage (~10%).Supine-dominance and REM-dominance commonly contribute to AHI underestimation in single-night PSGs. Misclassification of OSA severity can be mitigated in a patient-specific manner by appropriate consideration of these variables. The results have implications for the interpretation of single-night measurements in clinical practice, especially with trends toward home testing devices that may not measure body position or sleep stage.

  View details for DOI 10.5664/jcsm.2258

  View details for PubMedID 23243399

  View details for PubMedCentralID PMC3501662

• Information theoretic quantification of diagnostic uncertainty. The open medical informatics journal Westover, M. B., Eiseman, N. A., Cash, S. S., Bianchi, M. T. 2012; 6: 36-50

  Abstract

  Diagnostic test interpretation remains a challenge in clinical practice. Most physicians receive training in the use of Bayes' rule, which specifies how the sensitivity and specificity of a test for a given disease combine with the pre-test probability to quantify the change in disease probability incurred by a new test result. However, multiple studies demonstrate physicians' deficiencies in probabilistic reasoning, especially with unexpected test results. Information theory, a branch of probability theory dealing explicitly with the quantification of uncertainty, has been proposed as an alternative framework for diagnostic test interpretation, but is even less familiar to physicians. We have previously addressed one key challenge in the practical application of Bayes theorem: the handling of uncertainty in the critical first step of estimating the pre-test probability of disease. This essay aims to present the essential concepts of information theory to physicians in an accessible manner, and to extend previous work regarding uncertainty in pre-test probability estimation by placing this type of uncertainty within a principled information theoretic framework. We address several obstacles hindering physicians' application of information theoretic concepts to diagnostic test interpretation. These include issues of terminology (mathematical meanings of certain information theoretic terms differ from clinical or common parlance) as well as the underlying mathematical assumptions. Finally, we illustrate how, in information theoretic terms, one can understand the effect on diagnostic uncertainty of considering ranges instead of simple point estimates of pre-test probability.

  View details for DOI 10.2174/1874431101206010036

  View details for PubMedID 23304251

  View details for PubMedCentralID PMC3537080

• Detrended fluctuation analysis: a scale-free view on neuronal oscillations. Frontiers in physiology Hardstone, R., Poil, S. S., Schiavone, G., Jansen, R., Nikulin, V. V., Mansvelder, H. D., Linkenkaer-Hansen, K. 2012; 3: 450

  Abstract

  Recent years of research have shown that the complex temporal structure of ongoing oscillations is scale-free and characterized by long-range temporal correlations. Detrended fluctuation analysis (DFA) has proven particularly useful, revealing that genetic variation, normal development, or disease can lead to differences in the scale-free amplitude modulation of oscillations. Furthermore, amplitude dynamics is remarkably independent of the time-averaged oscillation power, indicating that the DFA provides unique insights into the functional organization of neuronal systems. To facilitate understanding and encourage wider use of scaling analysis of neuronal oscillations, we provide a pedagogical explanation of the DFA algorithm and its underlying theory. Practical advice on applying DFA to oscillations is supported by MATLAB scripts from the Neurophysiological Biomarker Toolbox (NBT) and links to the NBT tutorial website http://www.nbtwiki.net/. Finally, we provide a brief overview of insights derived from the application of DFA to ongoing oscillations in health and disease, and discuss the putative relevance of criticality for understanding the mechanism underlying scale-free modulation of oscillations.

  View details for DOI 10.3389/fphys.2012.00450

  View details for PubMedID 23226132

  View details for PubMedCentralID PMC3510427

• Absence of early epileptiform abnormalities predicts lack of seizures on continuous EEG. Neurology Shafi, M. M., Westover, M. B., Cole, A. J., Kilbride, R. D., Hoch, D. B., Cash, S. S. 2012; 79 (17): 1796-801

  Abstract

  To determine whether the absence of early epileptiform abnormalities predicts absence of later seizures on continuous EEG monitoring of hospitalized patients.We retrospectively reviewed 242 consecutive patients without a prior generalized convulsive seizure or active epilepsy who underwent continuous EEG monitoring lasting at least 18 hours for detection of nonconvulsive seizures or evaluation of unexplained altered mental status. The findings on the initial 30-minute screening EEG, subsequent continuous EEG recordings, and baseline clinical data were analyzed. We identified early EEG findings associated with absence of seizures on subsequent continuous EEG.Seizures were detected in 70 (29%) patients. A total of 52 patients had their first seizure in the initial 30 minutes of continuous EEG monitoring. Of the remaining 190 patients, 63 had epileptiform discharges on their initial EEG, 24 had triphasic waves, while 103 had no epileptiform abnormalities. Seizures were later detected in 22% (n = 14) of studies with epileptiform discharges on their initial EEG, vs 3% (n = 3) of the studies without epileptiform abnormalities on initial EEG (p < 0.001). In the 3 patients without epileptiform abnormalities on initial EEG but with subsequent seizures, the first epileptiform discharge or electrographic seizure occurred within the first 4 hours of recording.In patients without epileptiform abnormalities during the first 4 hours of recording, no seizures were subsequently detected. Therefore, EEG features early in the recording may indicate a low risk for seizures, and help determine whether extended monitoring is necessary.

  View details for DOI 10.1212/WNL.0b013e3182703fbc

  View details for PubMedID 23054233

  View details for PubMedCentralID PMC3475619

• Propagation of Uncertainty in Bayesian Diagnostic Test Interpretation SOUTHERN MEDICAL JOURNAL Srinivasan, P., Westover, M., Bianchi, M. T. 2012; 105 (9): 452–59

  Abstract

  Bayesian interpretation of diagnostic test results usually involves point estimates of the pretest probability and the likelihood ratio corresponding to the test result; however, it may be more appropriate in clinical situations to consider instead a range of possible values to express uncertainty in the estimates of these parameters. We thus sought to demonstrate how uncertainty in sensitivity, specificity, and disease pretest probability can be accommodated in Bayesian interpretation of diagnostic testing.We investigated three questions: How does uncertainty in the likelihood ratio propagate to the posttest probability range, assuming a point estimate of pretest probability? How does uncertainty in the sensitivity and specificity of a test affect uncertainty in the likelihood ratio? How does uncertainty propagate when present in both the pretest probability and the likelihood ratio?Propagation of likelihood ratio uncertainty depends on the pretest probability and is more prominent for unexpected test results. Uncertainty in sensitivity and specificity propagates into the calculation of likelihood ratio prominently as these parameters approach 100%; even modest errors of ± 10% caused dramatic propagation. Combining errors of ± 20% in the pretest probability and in the likelihood ratio exhibited modest propagation to posttest probability, suggesting a realistic target range for clinical estimations.The results provide a framework for incorporating ranges of uncertainty into Bayesian reasoning. Although point estimates simplify the implementation of Bayesian reasoning, it is important to recognize the implications of error propagation when ranges are considered in this multistep process.

  View details for DOI 10.1097/SMJ.0b013e3182621a2c

  View details for Web of Science ID 000308669000002

  View details for PubMedID 22948322

  View details for PubMedCentralID PMC6785978

• Delayed cerebral ischaemia after subarachnoid haemorrhage: looking beyond vasospasm. British journal of anaesthesia Rowland, M. J., Hadjipavlou, G., Kelly, M., Westbrook, J., Pattinson, K. T. 2012; 109 (3): 315-29

  Abstract

  Despite improvements in the clinical management of aneurysmal subarachnoid haemorrhage over the last decade, delayed cerebral ischaemia (DCI) remains the single most important cause of morbidity and mortality in those patients who survive the initial bleed. The pathological mechanisms underlying DCI are still unclear and the calcium channel blocker nimodipine remains the only therapeutic intervention proven to improve functional outcomes after SAH. The recent failure of the drug clazosentan to improve functional outcomes despite reducing vasoconstriction has moved the focus of research into DCI away from cerebral artery constriction towards a more multifactorial aetiology. Novel pathological mechanisms have been suggested, including damage to cerebral tissue in the first 72 h after aneurysm rupture ('early brain injury'), cortical spreading depression, and microthrombosis. A greater understanding of the significance of these pathophysiological mechanisms and potential genetic risk factors is required, if new approaches to the prophylaxis, diagnosis, and treatment of DCI are to be developed. Furthermore, objective and reliable biomarkers are needed for the diagnosis of DCI in poor grade SAH patients requiring sedation and to assess the efficacy of new therapeutic interventions. The purpose of this article is to appraise these recent advances in research into DCI, relate them to current clinical practice, and suggest potential novel avenues for future research.

  View details for DOI 10.1093/bja/aes264

  View details for PubMedID 22879655

• Should risky treatments be reserved for secondary prevention? Theoretical considerations regarding risk-benefit tradeoffs. Journal of clinical epidemiology Westover, M. B., Eiseman, N. A., Bianchi, M. T. 2012; 65 (8): 877-86

  Abstract

  Clinical intuition suggests that risk-reducing treatments are more beneficial for patients with greater risk of disease. This intuition contributes to our rationale for tolerating greater adverse event risk in the setting of secondary prevention of certain diseases such as myocardial infarction or stroke. However, under certain conditions treatment benefits may be greater in primary prevention, even when the treatment carries harmful adverse effect potential.We present simple decision-theoretic models that illustrate conditions of risk and benefit under which a treatment is predicted to be more beneficial in primary than in secondary prevention.The models cover a spectrum of possible clinical circumstances, and demonstrate that net benefit in primary prevention can occur despite no benefit (or even net harm) in secondary prevention.This framework provides a rationale for extending the familiar concept of balancing risks and benefits to account for disease-specific considerations of primary vs. secondary prevention.

  View details for DOI 10.1016/j.jclinepi.2012.02.011

  View details for PubMedID 22640567

  View details for PubMedCentralID PMC6794097

• Seizure diaries for clinical research and practice: Limitations and future prospects EPILEPSY & BEHAVIOR Fisher, R. S., Blum, D. E., Diventura, B., Vannest, J., Hixson, J. D., Moss, R., Herman, S. T., Fureman, B. E., French, J. A. 2012; 24 (3): 304-310

  Abstract

  An NINDS-sponsored conference in April of 2011 reviewed issues in epilepsy clinical trials. One goal was to clarify new electronic methods for recording seizure information and other data in clinical trials.This selective literature review and compilation of expert opinion considers advantages and limitations of traditional paper-based seizure diaries in comparison to electronic diaries.Seizure diaries are a type of patient-reported outcome. All seizure diaries depend first on accurate recognition and recording of seizures, which is a problem since about half of seizures recorded during video-EEG monitoring are not known to the patient. Reliability of recording is another key issue. Diaries may not be at hand after a seizure, lost or not brought to clinic visits. On-line electronic diaries have several potential advantages over paper diaries. Smartphones are increasingly accessible as data entry gateways. Data are not easily lost and are accessible from clinic. Entries can be time-stamped and provide immediate feedback, validation or reminders. Data can also can be graphed and pasted into an EMR. Disadvantages include need for digital sophistication, higher cost, increased setup time, and requiring attention to potential privacy issues. The Epilepsy Diary by epilepsy.com and Irody, Inc. has over 13,000 registrants and SeizureTracker over 10,000, and both are used for clinical and research purposes. Some studies have documented patient preference and increased compliance for electronic versus paper diaries. Seizure diaries can be challenging in the pediatric population. Children often have multiple seizure types and limited reporting of subjective symptoms. Multiple caregivers during the day require more training to produce reliable and consistent data. Diary-based observational studies have the advantages of low cost, allowing locus-of-control by the patient and testing in a "real-world" environment. Diary-based studies can also be useful as descriptive "snapshots" of a population. However, the type of information available is very different from that obtained by prospective controlled studies. The act of self-recording observations may itself influence the observation, for example, by causing the subject to attend more vigilantly to seizures after changing medication. Pivotal anti-seizure drug or device trials still mostly rely on paper-based seizure diaries. Industry is aware of the potential advantages of electronic diaries, particularly, the promise of real-time transmission of data, time-stamping of entries, reminders to subjects, and potentially automatic interfaces to other devices. However, until diaries are validated as research tools and the regulatory environment becomes clearer, adoption of new types of diaries as markers for a primary study outcome will be cautious.Recommendations from the conference included: further studies of validity of epilepsy diaries and how they can be used to improve adherence; use and further development of core data sets, such as the one recently developed by NINDS; encouraging links of diaries to electronic sensors; development of diary privacy and legal policies; examination of special pediatric diary issues; development of principles for observational research from diaries; and work with the FDA to make electronic diaries more useful in industry-sponsored clinical trials.

  View details for DOI 10.1016/j.yebeh.2012.04.128

  View details for PubMedID 22652423

• Effect of levetiracetam monotherapy on background EEG activity and cognition in drug-naïve epilepsy patients. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Cho, J. R., Koo, D. L., Joo, E. Y., Yoon, S. M., Ju, E., Lee, J., Kim, D. Y., Hong, S. B. 2012; 123 (5): 883-91

  Abstract

  To investigate the cognitive effect of levetiracetam (LEV) monotherapy with quantitative electroencephalogram (EEG) analysis and neuropsychological (NP) tests.Twenty-two drug-naïve epilepsy patients were enrolled. EEG recordings were performed before and after LEV therapy. Relative power of discrete frequency bands was computed, as well as alpha peak frequency (APF) at occipital electrodes. Eighteen patients performed a battery of NP tests twice across LEV treatment.LEV therapy decreased the power of delta (1-3 Hz, p<0.01) and theta (3-7 Hz, p<0.05) bands and increased that of alpha-2 (10-13 Hz, p<0.05) and beta-2 (19-24 Hz, p<0.05) bands. Region-specific spectral change was observed: delta power change was significant in fronto-polar region, theta in anterior region, alpha-2 in broad region, and beta-2 in left fronto-central region. APF change was not significant. Improvement in diverse NP tests requiring attention, working memory, language and executive function was observed. Change in theta, alpha-2, and beta-2 power was correlated with improvement in several NP tests.Our data suggest LEV is associated with acceleration of background EEG frequencies and improved cognitive function. Change in frequency band power could predict improvement in several cognitive domains across LEV therapy.Combined study of quantitative EEG analysis and NP tests can be useful in identifying cognitive effect of antiepileptic drugs.

  View details for DOI 10.1016/j.clinph.2011.09.012

  View details for PubMedID 22000706

• Exploration and modulation of brain network interactions with noninvasive brain stimulation in combination with neuroimaging. The European journal of neuroscience Shafi, M. M., Westover, M. B., Fox, M. D., Pascual-Leone, A. 2012; 35 (6): 805-25

  Abstract

  Much recent work in systems neuroscience has focused on how dynamic interactions between different cortical regions underlie complex brain functions such as motor coordination, language and emotional regulation. Various studies using neuroimaging and neurophysiologic techniques have suggested that in many neuropsychiatric disorders, these dynamic brain networks are dysregulated. Here we review the utility of combined noninvasive brain stimulation and neuroimaging approaches towards greater understanding of dynamic brain networks in health and disease. Brain stimulation techniques, such as transcranial magnetic stimulation and transcranial direct current stimulation, use electromagnetic principles to alter brain activity noninvasively, and induce focal but also network effects beyond the stimulation site. When combined with brain imaging techniques such as functional magnetic resonance imaging, positron emission tomography and electroencephalography, these brain stimulation techniques enable a causal assessment of the interaction between different network components, and their respective functional roles. The same techniques can also be applied to explore hypotheses regarding the changes in functional connectivity that occur during task performance and in various disease states such as stroke, depression and schizophrenia. Finally, in diseases characterized by pathologic alterations in either the excitability within a single region or in the activity of distributed networks, such techniques provide a potential mechanism to alter cortical network function and architectures in a beneficial manner.

  View details for DOI 10.1111/j.1460-9568.2012.08035.x

  View details for PubMedID 22429242

  View details for PubMedCentralID PMC3313459

• Emergence of stable functional networks in long-term human electroencephalography. The Journal of neuroscience : the official journal of the Society for Neuroscience Chu, C. J., Kramer, M. A., Pathmanathan, J., Bianchi, M. T., Westover, M. B., Wizon, L., Cash, S. S. 2012; 32 (8): 2703-13

  Abstract

  Functional connectivity networks have become a central focus in neuroscience because they reveal key higher-dimensional features of normal and abnormal nervous system physiology. Functional networks reflect activity-based coupling between brain regions that may be constrained by relatively static anatomical connections, yet these networks appear to support tremendously dynamic behaviors. Within this growing field, the stability and temporal characteristics of functional connectivity brain networks have not been well characterized. We evaluated the temporal stability of spontaneous functional connectivity networks derived from multi-day scalp encephalogram (EEG) recordings in five healthy human subjects. Topological stability and graph characteristics of networks derived from averaged data epochs ranging from 1 s to multiple hours across different states of consciousness were compared. We show that, although functional networks are highly variable on the order of seconds, stable network templates emerge after as little as ∼100 s of recording and persist across different states and frequency bands (albeit with slightly different characteristics in different states and frequencies). Within these network templates, the most common edges are markedly consistent, constituting a network "core." Although average network topologies persist across time, measures of global network connectivity, density and clustering coefficient, are state and frequency specific, with sparsest but most highly clustered networks seen during sleep and in the gamma frequency band. These findings support the notion that a core functional organization underlies spontaneous cortical processing and may provide a reference template on which unstable, transient, and rapidly adaptive long-range assemblies are overlaid in a frequency-dependent manner.

  View details for DOI 10.1523/JNEUROSCI.5669-11.2012

  View details for PubMedID 22357854

  View details for PubMedCentralID PMC3361717

• Classification algorithms for predicting sleepiness and sleep apnea severity. Journal of sleep research Eiseman, N. A., Westover, M. B., Mietus, J. E., Thomas, R. J., Bianchi, M. T. 2012; 21 (1): 101-12

  Abstract

  Identifying predictors of subjective sleepiness and severity of sleep apnea are important yet challenging goals in sleep medicine. Classification algorithms may provide insights, especially when large data sets are available. We analyzed polysomnography and clinical features available from the Sleep Heart Health Study. The Epworth Sleepiness Scale and the apnea-hypopnea index were the targets of three classifiers: k-nearest neighbor, naive Bayes and support vector machine algorithms. Classification was based on up to 26 features including demographics, polysomnogram, and electrocardiogram (spectrogram). Naive Bayes was best for predicting abnormal Epworth class (0-10 versus 11-24), although prediction was weak: polysomnogram features had 16.7% sensitivity and 88.8% specificity; spectrogram features had 5.3% sensitivity and 96.5% specificity. The support vector machine performed similarly to naive Bayes for predicting sleep apnea class (0-5 versus >5): 59.0% sensitivity and 74.5% specificity using clinical features and 43.4% sensitivity and 83.5% specificity using spectrographic features compared with the naive Bayes classifier, which had 57.5% sensitivity and 73.7% specificity (clinical), and 39.0% sensitivity and 82.7% specificity (spectrogram). Mutual information analysis confirmed the minimal dependency of the Epworth score on any feature, while the apnea-hypopnea index showed modest dependency on body mass index, arousal index, oxygenation and spectrogram features. Apnea classification was modestly accurate, using either clinical or spectrogram features, and showed lower sensitivity and higher specificity than common sleep apnea screening tools. Thus, clinical prediction of sleep apnea may be feasible with easily obtained demographic and electrocardiographic analysis, but the utility of the Epworth is questioned by its minimal relation to clinical, electrocardiographic, or polysomnographic features.

  View details for DOI 10.1111/j.1365-2869.2011.00935.x

  View details for PubMedID 21752133

  View details for PubMedCentralID PMC3698244

• Revising the "Rule of Three" for inferring seizure freedom. Epilepsia Westover, M. B., Cormier, J., Bianchi, M. T., Shafi, M., Kilbride, R., Cole, A. J., Cash, S. S. 2012; 53 (2): 368-76

  Abstract

  How long after starting a new medication must a patient go without seizures before they can be regarded as seizure-free? A recent International League Against Epilepsy (ILAE) task force proposed using a "Rule of Three" as an operational definition of seizure freedom, according to which a patient should be considered seizure-free following an intervention after a period without seizures has elapsed equal to three times the longest preintervention interseizure interval over the previous year. This rule was motivated in large part by statistical considerations advanced in a classic 1983 paper by Hanley and Lippman-Hand. However, strict adherence to the statistical logic of this rule generally requires waiting much longer than recommended by the ILAE task force. Therefore, we set out to determine whether an alternative approach to the Rule of Three might be possible, and under what conditions the rule may be expected to hold or would need to be extended.Probabilistic modeling and application of Bayes' rule.We find that an alternative approach to the problem of inferring seizure freedom supports using the Rule of Three in the way proposed by the ILAE in many cases, particularly in evaluating responses to a first trial of antiseizure medication, and to favorably-selected epilepsy surgical candidates. In cases where the a priori odds of success are less favorable, our analysis requires longer seizure-free observation periods before declaring seizure freedom, up to six times the average preintervention interseizure interval. The key to our approach is to take into account not only the time elapsed without seizures but also empirical data regarding the a priori probability of achieving seizure freedom conferred by a particular intervention.In many cases it may be reasonable to consider a patient seizure-free after they have gone without seizures for a period equal to three times the preintervention interseizure interval, as proposed on pragmatic grounds in a recent ILAE position paper, although in other commonly encountered cases a waiting time up to six times this interval is required. In this work we have provided a coherent theoretical basis for modified criterion for seizure freedom, which we call the "Rule of Three-To-Six."

  View details for DOI 10.1111/j.1528-1167.2011.03355.x

  View details for PubMedID 22191711

  View details for PubMedCentralID PMC3267849

• Cerebral infarction due to smoker's polycythemia. BMJ case reports Thakur, K. T., Westover, M. B. 2011; 2011

  Abstract

  A 65-year-old man presented with fluctuating focal neurological deficits and neuroimaging findings of multiple small cerebral infarctions. His medical investigation revealed a >100 pack/year smoking history, and a haematocrit >60. Subsequent investigations led to a diagnosis of cerebral infarction due to smoker's polycythemia, the third such case reported in the medical literature. The patient's neurological deficits resolved completely with subsequent haematocrit reduction. This brief report reviews the differential diagnosis of polycythemia, current knowledge of the mechanisms by which smoker's polycythemia may lead to ischemic stroke, and recommendations for management.

  View details for DOI 10.1136/bcr.08.2011.4714

  View details for PubMedID 22675101

  View details for PubMedCentralID PMC3207785

• Fast and slow spindles during the sleep slow oscillation: disparate coalescence and engagement in memory processing. Sleep Mölle, M., Bergmann, T. O., Marshall, L., Born, J. 2011; 34 (10): 1411-21

  Abstract

  Thalamo-cortical spindles driven by the up-state of neocortical slow (< 1 Hz) oscillations (SOs) represent a candidate mechanism of memory consolidation during sleep. We examined interactions between SOs and spindles in human slow wave sleep, focusing on the presumed existence of 2 kinds of spindles, i.e., slow frontocortical and fast centro-parietal spindles.Two experiments were performed in healthy humans (24.5 ± 0.9 y) investigating undisturbed sleep (Experiment I) and the effects of prior learning (word paired associates) vs. non-learning (Experiment II) on multichannel EEG recordings during sleep.Only fast spindles (12-15 Hz) were synchronized to the depolarizing SO up-state. Slow spindles (9-12 Hz) occurred preferentially at the transition into the SO down-state, i.e., during waning depolarization. Slow spindles also revealed a higher probability to follow rather than precede fast spindles. For sequences of individual SOs, fast spindle activity was largest for "initial" SOs, whereas SO amplitude and slow spindle activity were largest for succeeding SOs. Prior learning enhanced this pattern.The finding that fast and slow spindles occur at different times of the SO cycle points to disparate generating mechanisms for the 2 kinds of spindles. The reported temporal relationships during SO sequences suggest that fast spindles, driven by the SO up-state feed back to enhance the likelihood of succeeding SOs together with slow spindles. By enforcing such SO-spindle cycles, particularly after prior learning, fast spindles possibly play a key role in sleep-dependent memory processing.

  View details for DOI 10.5665/SLEEP.1290

  View details for PubMedID 21966073

  View details for PubMedCentralID PMC3174843

• The organization of the human cerebral cortex estimated by intrinsic functional connectivity JOURNAL OF NEUROPHYSIOLOGY Yeo, B., Krienen, F. M., Sepulcre, J., Sabuncu, M. R., Lashkari, D., Hollinshead, M., Roffman, J. L., Smoller, J. W., Zoeller, L., Polimeni, J. R., Fischl, B., Liu, H., Buckner, R. L. 2011; 106 (3): 1125-1165

  Abstract

  Information processing in the cerebral cortex involves interactions among distributed areas. Anatomical connectivity suggests that certain areas form local hierarchical relations such as within the visual system. Other connectivity patterns, particularly among association areas, suggest the presence of large-scale circuits without clear hierarchical relations. In this study the organization of networks in the human cerebrum was explored using resting-state functional connectivity MRI. Data from 1,000 subjects were registered using surface-based alignment. A clustering approach was employed to identify and replicate networks of functionally coupled regions across the cerebral cortex. The results revealed local networks confined to sensory and motor cortices as well as distributed networks of association regions. Within the sensory and motor cortices, functional connectivity followed topographic representations across adjacent areas. In association cortex, the connectivity patterns often showed abrupt transitions between network boundaries. Focused analyses were performed to better understand properties of network connectivity. A canonical sensory-motor pathway involving primary visual area, putative middle temporal area complex (MT+), lateral intraparietal area, and frontal eye field was analyzed to explore how interactions might arise within and between networks. Results showed that adjacent regions of the MT+ complex demonstrate differential connectivity consistent with a hierarchical pathway that spans networks. The functional connectivity of parietal and prefrontal association cortices was next explored. Distinct connectivity profiles of neighboring regions suggest they participate in distributed networks that, while showing evidence for interactions, are embedded within largely parallel, interdigitated circuits. We conclude by discussing the organization of these large-scale cerebral networks in relation to monkey anatomy and their potential evolutionary expansion in humans to support cognition.

  View details for DOI 10.1152/jn.00338.2011

  View details for Web of Science ID 000294775500007

  View details for PubMedID 21653723

  View details for PubMedCentralID PMC3174820

• Should a sentinel node biopsy be performed in patients with high-risk breast cancer? International journal of breast cancer Westover, K. D., Westover, M. B., Winer, E. P., Richardson, A. L., Iglehart, J. D., Punglia, R. S. 2011; 2011: 973245

  Abstract

  A negative sentinel lymph node (SLN) biopsy spares many breast cancer patients the complications associated with lymph node irradiation or additional surgery. However, patients at high risk for nodal involvement based on clinical characteristics may remain at unacceptably high risk of axillary disease even after a negative SLN biopsy result. A Bayesian nomogram was designed to combine the probability of axillary disease prior to nodal biopsy with customized test characteristics for an SLN biopsy and provides the probability of axillary disease despite a negative SLN biopsy. Users may individualize the sensitivity of an SLN biopsy based on factors known to modify the sensitivity of the procedure. This tool may be useful in identifying patients who should have expanded upfront exploration of the axilla or comprehensive axillary irradiation.

  View details for DOI 10.4061/2011/973245

  View details for PubMedID 22295240

  View details for PubMedCentralID PMC3262582

• Depression and risk of developing dementia. Nature reviews. Neurology Byers, A. L., Yaffe, K. 2011; 7 (6): 323-31

  Abstract

  Depression is highly common throughout the life course and dementia is common in late life. Depression has been linked with dementia, and growing evidence implies that the timing of depression may be important in defining the nature of this association. In particular, earlier-life depression (or depressive symptoms) has consistently been associated with a more than twofold increase in dementia risk. By contrast, studies of late-life depression and dementia risk have been conflicting; most support an association, yet the nature of this association (for example, if depression is a prodrome or consequence of, or risk factor for dementia) remains unclear. The likely biological mechanisms linking depression to dementia include vascular disease, alterations in glucocorticoid steroid levels and hippocampal atrophy, increased deposition of amyloid-β plaques, inflammatory changes, and deficits of nerve growth factors. Treatment strategies for depression could interfere with these pathways and alter the risk of dementia. Given the projected increase in dementia incidence in the coming decades, understanding whether treatment for depression alone, or combined with other regimens, improves cognition is of critical importance. In this Review, we summarize and analyze current evidence linking late-life and earlier-life depression and dementia, and discuss the primary underlying mechanisms and implications for treatment.

  View details for DOI 10.1038/nrneurol.2011.60

  View details for PubMedID 21537355

  View details for PubMedCentralID PMC3327554

• Statin use following intracerebral hemorrhage: a decision analysis. Archives of neurology Westover, M. B., Bianchi, M. T., Eckman, M. H., Greenberg, S. M. 2011; 68 (5): 573-9

  Abstract

  Statins are widely prescribed for primary and secondary prevention of ischemic cardiac and cerebrovascular disease. Although serious adverse effects are uncommon, results from a recent clinical trial suggested increased risk of intracerebral hemorrhage (ICH) associated with statin use. For patients with baseline elevated risk of ICH, it is not known whether this potential adverse effect offsets the cardiovascular and cerebrovascular benefits.To address the following clinical question: Given a history of prior ICH, should statin therapy be avoided?A Markov decision model was used to evaluate the risks and benefits of statin therapy in patients with prior ICH.Life expectancy, measured as quality-adjusted life-years. We investigated how statin use affects this outcome measure while varying a range of clinical parameters, including hemorrhage location (deep vs lobar), ischemic cardiac and cerebrovascular risks, and magnitude of ICH risk associated with statins.Avoiding statins was favored over a wide range of values for many clinical parameters, particularly in survivors of lobar ICH who are at highest risk of ICH recurrence. In survivors of lobar ICH without prior cardiovascular events, avoiding statins yielded a life expectancy gain of 2.2 quality-adjusted life-years compared with statin use. This net benefit persisted even at the lower 95% confidence interval of the relative risk of statin-associated ICH. In patients with lobar ICH who had prior cardiovascular events, the annual recurrence risk of myocardial infarction would have to exceed 90% to favor statin therapy. Avoiding statin therapy was also favored, although by a smaller margin, in both primary and secondary prevention settings for survivors of deep ICH.Avoiding statins should be considered for patients with a history of ICH, particularly those cases with a lobar location.

  View details for DOI 10.1001/archneurol.2010.356

  View details for PubMedID 21220650

  View details for PubMedCentralID PMC3158138

• Faciobrachial dystonic seizures precede Lgi1 antibody limbic encephalitis. Annals of neurology Irani, S. R., Michell, A. W., Lang, B., Pettingill, P., Waters, P., Johnson, M. R., Schott, J. M., Armstrong, R. J., S Zagami, A., Bleasel, A., Somerville, E. R., Smith, S. M., Vincent, A. 2011; 69 (5): 892-900

  Abstract

  To describe a distinctive seizure semiology that closely associates with voltage-gated potassium channel (VGKC)-complex/Lgi1 antibodies and commonly precedes the onset of limbic encephalitis (LE).Twenty-nine patients were identified by the authors (n = 15) or referring clinicians (n = 14). The temporal progression of clinical features and serum sodium, brain magnetic resonance imaging (MRI), positron emission tomography/single photon emission computed tomography, and VGKC-complex antibodies was studied.Videos and still images showed a distinctive adult-onset, frequent, brief dystonic seizure semiology that predominantly affected the arm and ipsilateral face. We have termed these faciobrachial dystonic seizures (FBDS). All patients tested during their illness had antibodies to VGKC complexes; the specific antigenic target was Lgi1 in 89%. Whereas 3 patients never developed LE, 20 of the remaining 26 (77%) experienced FBDS prior to the development of the amnesia and confusion that characterize LE. During the prodrome of FBDS alone, patients had normal sodium and brain MRIs, but electroencephalography demonstrated ictal epileptiform activity in 7 patients (24%). Following development of LE, the patients often developed other seizure semiologies, including typical mesial temporal lobe seizures. At this stage, investigations commonly showed hyponatremia and MRI hippocampal high T2 signal; functional brain imaging showed evidence of basal ganglia involvement in 5/8. Antiepileptic drugs (AEDs) were generally ineffective and in 41% were associated with cutaneous reactions that were often severe. By contrast, immunotherapies produced a clear, and often dramatic, reduction in FBDS frequency.Recognition of FBDS should prompt testing for VGKC-complex/Lgi1 antibodies. AEDs often produce adverse effects; treatment with immunotherapies may prevent the development of LE with its potential for cerebral atrophy and cognitive impairment.

  View details for DOI 10.1002/ana.22307

  View details for PubMedID 21416487

• A disk-aware algorithm for time series motif discovery. Data mining and knowledge discovery Mueen, A., Keogh, E., Zhu, Q., Cash, S. S., Westover, M. B., Bigdely-Shamlo, N. 2011; 22 (1-2): 73-105

  Abstract

  Time series motifs are sets of very similar subsequences of a long time series. They are of interest in their own right, and are also used as inputs in several higher-level data mining algorithms including classification, clustering, rule-discovery and summarization. In spite of extensive research in recent years, finding time series motifs exactly in massive databases is an open problem. Previous efforts either found approximate motifs or considered relatively small datasets residing in main memory. In this work, we leverage off previous work on pivot-based indexing to introduce a disk-aware algorithm to find time series motifs exactly in multi-gigabyte databases which contain on the order of tens of millions of time series. We have evaluated our algorithm on datasets from diverse areas including medicine, anthropology, computer networking and image processing and show that we can find interesting and meaningful motifs in datasets that are many orders of magnitude larger than anything considered before.

  View details for DOI 10.1007/s10618-010-0176-8

  View details for PubMedID 32153346

  View details for PubMedCentralID PMC7062370

• Premortem diagnosis of sporadic Creutzfeldt-Jakob disease aided by positron-emission tomography imaging. AJNR. American journal of neuroradiology Zhang, W. J., Westover, M. B., Keary, C. J. 2011; 32 (1): E18

  View details for DOI 10.3174/ajnr.A2292

  View details for PubMedID 21071534

  View details for PubMedCentralID PMC6788750

• Power law versus exponential state transition dynamics: application to sleep-wake architecture. PloS one Chu-Shore, J., Westover, M. B., Bianchi, M. T. 2010; 5 (12): e14204

  Abstract

  Despite the common experience that interrupted sleep has a negative impact on waking function, the features of human sleep-wake architecture that best distinguish sleep continuity versus fragmentation remain elusive. In this regard, there is growing interest in characterizing sleep architecture using models of the temporal dynamics of sleep-wake stage transitions. In humans and other mammals, the state transitions defining sleep and wake bout durations have been described with exponential and power law models, respectively. However, sleep-wake stage distributions are often complex, and distinguishing between exponential and power law processes is not always straightforward. Although mono-exponential distributions are distinct from power law distributions, multi-exponential distributions may in fact resemble power laws by appearing linear on a log-log plot.To characterize the parameters that may allow these distributions to mimic one another, we systematically fitted multi-exponential-generated distributions with a power law model, and power law-generated distributions with multi-exponential models. We used the Kolmogorov-Smirnov method to investigate goodness of fit for the "incorrect" model over a range of parameters. The "zone of mimicry" of parameters that increased the risk of mistakenly accepting power law fitting resembled empiric time constants obtained in human sleep and wake bout distributions.Recognizing this uncertainty in model distinction impacts interpretation of transition dynamics (self-organizing versus probabilistic), and the generation of predictive models for clinical classification of normal and pathological sleep architecture.

  View details for DOI 10.1371/journal.pone.0014204

  View details for PubMedID 21151998

  View details for PubMedCentralID PMC2996311

• Seizure identification in the ICU using quantitative EEG displays. Neurology Stewart, C. P., Otsubo, H., Ochi, A., Sharma, R., Hutchison, J. S., Hahn, C. D. 2010; 75 (17): 1501-8

  Abstract

  To evaluate the diagnostic accuracy of 2 quantitative EEG display tools, color density spectral array (CDSA) and amplitude-integrated EEG (aEEG), for seizure identification in the intensive care unit (ICU).A set of 27 continuous EEG recordings performed in pediatric ICU patients was transformed into 8-channel CDSA and aEEG displays. Three neurophysiologists underwent 2 hours of training to identify seizures using these techniques. They were then individually presented with a series of CDSA and aEEG displays, blinded to the raw EEG, and asked to mark any events suspected to be seizures. Their performance was compared to seizures identified on the underlying conventional EEG.The 27 EEG recordings contained 553 discrete seizures over 487 hours. The median sensitivity for seizure identification across all recordings was 83.3% using CDSA and 81.5% using aEEG. However, among individual recordings, the sensitivity ranged from 0% to 100%. Factors reducing the sensitivity included low-amplitude, short, and focal seizures. False-positive rates were generally very low, with misidentified seizures occurring once every 17-20 hours.Both CDSA and aEEG demonstrate acceptable sensitivity and false-positive rates for seizure identification among critically ill children. Accuracy of these tools would likely improve during clinical use, when findings can be correlated in real-time with the underlying raw EEG. In the hands of neurophysiologists, CDSA and aEEG displays represent useful screening tools for seizures during continuous EEG monitoring in the ICU. The suitability of these tools for bedside use by ICU nurses and physicians requires further study.

  View details for DOI 10.1212/WNL.0b013e3181f9619e

  View details for PubMedID 20861452

  View details for PubMedCentralID PMC2974462

• Automatic extraction of medication information from medical discharge summaries. Journal of the American Medical Informatics Association : JAMIA Yang, H. 2010; 17 (5): 545-8

  Abstract

  This article describes a system developed for the 2009 i2b2 Medication Extraction Challenge. The purpose of this challenge is to extract medication information from hospital discharge summaries.The system explored several linguistic natural language processing techniques (eg, term-based and token-based rule matching) to identify medication-related information in the narrative text. A number of lexical resources was constructed to profile lexical or morphological features for different categories of medication constituents.Performance was evaluated in terms of the micro-averaged F-measure at the horizontal system level.The automated system performed well, and achieved an F-micro of 80% for the term-level results and 81% for the token-level results, placing it sixth in exact matches and fourth in inexact matches in the i2b2 competition.The overall results show that this relatively simple rule-based approach is capable of tackling multiple entity identification tasks such as medication extraction under situations in which few training documents are annotated for machine learning approaches, and the entity information can be characterized with a set of feature tokens.

  View details for DOI 10.1136/jamia.2010.003863

  View details for PubMedID 20819861

  View details for PubMedCentralID PMC2995675

• Misdiagnosis of epileptic and non-epileptic seizures in a neurological intensive care unit. Acta neurologica Scandinavica Boesebeck, F., Freermann, S., Kellinghaus, C., Evers, S. 2010; 122 (3): 189-95

  Abstract

  The etiological misinterpretation of paroxysmal neurological symptoms frequently causes a delayed treatment or an inappropriate utilization of ICU-capacities.In this study, the data of 208 patients admitted to a neurological ICU because of acute transient neurological deficits, loss of consciousness or unclear motor phenomena were retrospectively analyzed. The initial emergency room diagnosis was compared to the final diagnosis and the rate of misdiagnosis was related to the patients' history and diagnostic data.In 13.9%, the emergency room diagnosis of epileptic seizures turned out to be incorrect, whereas in 15.6%, the final diagnosis of epileptic seizures was missed in the emergency room. Factors that were significantly correlated to missing the seizure diagnosis were (i) no prior history of epilepsy, (ii) old age, (iii) multi-morbidity, (iv) pathologic CT-scans demonstrating cerebrovascular lesions, (v) seizure description by non-professionals, (vi) predominantly negative seizure phenomena (aphasia, loss of consciousness, paresis), (vii) lack of tongue-bite lesions.

  View details for DOI 10.1111/j.1600-0404.2009.01287.x

  View details for PubMedID 20003086

• Delirium in acute stroke--prevalence and risk factors. Acta neurologica Scandinavica. Supplementum Dahl, M. H., Rønning, O. M., Thommessen, B. 2010: 39-43

  Abstract

  Delirium is frequently seen as a major complication among elderly stroke patients. Few studies have prospectively studied delirium as a complication of acute stroke. In these studies, the results are conflicting regarding risk factors and estimated prevalence. The aims of the present study are to assess the prevalence of delirium in patients with acute stroke treated in an acute Stroke Unit, identify characteristics of patients with delirium and important factors associated with the development of delirium.We conducted a prospective study of patients with delirium and acute stroke consecutively admitted to a Stroke Unit. The diagnosis of delirium was based on Confusion Assessment Method (CAM). CAM is devised from DSM-III-R criteria based on the diagnosis of delirium, and is a simple test with high sensitivity and specificity.One hundred and seventy-eight patients with a diagnosis of stroke were eligible for the study. The prevalence of delirium in acute stroke in our study was 10% (18 of 178 patients). Patients with delirium had significantly longer length of stay in the Stroke Unit (12.3 vs 8.5 days, P < 0.004). Prestroke dementia [odds ratio (OR) 18.7], hemianopsia (OR 12.3), apraxia (OR 11.0), higher age (OR 5.5) and infection (UTI or pneumonia) (OR 4.9) during in-hospital stay were associated with increased risk of delirium.One of 10 stroke patients had delirium. This is the lowest prevalence of delirium shown in acute stroke patients. In our study, all patients were treated in a Stroke Unit. A Stroke Unit like the Scandinavian model may be beneficial in preventing delirium.

  View details for DOI 10.1111/j.1600-0404.2010.01374.x

  View details for PubMedID 20586734

• Spreading depolarizations and late secondary insults after traumatic brain injury. Journal of neurotrauma Hartings, J. A., Strong, A. J., Fabricius, M., Manning, A., Bhatia, R., Dreier, J. P., Mazzeo, A. T., Tortella, F. C., Bullock, M. R. 2009; 26 (11): 1857-66

  Abstract

  Here we investigated the incidence of cortical spreading depolarizations (spreading depression and peri-infarct depolarization) after traumatic brain injury (TBI) and their relationship to systemic physiologic values during neurointensive care. Subdural electrode strips were placed on peri-contusional cortex in 32 patients who underwent surgical treatment for TBI. Prospective electrocorticography was performed during neurointensive care with retrospective analysis of hourly nursing chart data. Recordings were 84 hr (median) per patient and 2,503 hr in total. In 17 patients (53%), 280 spreading depolarizations (spreading depressions and peri-infarct depolarizations) were observed. Depolarizations occurred in a bimodal pattern with peak incidence on days 1 and 7. The probability of a depolarization occurring increased significantly as a function of declining mean arterial pressure (MAP; R(2) = 0.78; p < 0.001) and cerebral perfusion pressure (R(2) = 0.85; p < 0.01), and increasing core temperature (R(2) = 0.44; p < 0.05). Depolarization probability was 7% for MAP values of >100 mm Hg but 33% for MAP of < or =70 mm Hg. Temperatures of < or =38.4 degrees C were associated with a 21% depolarization risk, compared to 63% for >38.4 degrees C. Intracranial pressures were higher in patients with depolarizations (18.3 +/- 9.3 vs. 13.5 +/- 6.7 mm Hg; p < 0.001). We conclude that depolarization phenomena are a common cortical pathology in TBI. Their association with lower perfusion levels and higher temperatures suggests that the labile balance of energy supply and demand is an important determinant of their occurrence. Monitoring of depolarizations might serve as a functional measure to guide therapeutic efforts and their blockade may provide an additional line of defense against the effects of secondary insults.

  View details for DOI 10.1089/neu.2009.0961

  View details for PubMedID 19508156

  View details for PubMedCentralID PMC2865988

• How seizure detection by continuous electroencephalographic monitoring affects the prescribing of antiepileptic medications. Archives of neurology Kilbride, R. D., Costello, D. J., Chiappa, K. H. 2009; 66 (6): 723-8

  Abstract

  To assess the effect of continuous electroencephalographic monitoring on the decision to treat seizures in the inpatient setting, particularly in the intensive care unit.Retrospective cohort study.Medical and neuroscience intensive care units and neurological wards.Three hundred consecutive nonelective continuous electroencephalographic monitoring studies, performed on 287 individual inpatients over a 27-month period.Epileptiform electroencephalographic abnormalities and changes in antiepileptic drug (AED) therapy based on the electroencephalographic findings.The findings from the continuous electroencephalographic monitoring led to a change in AED prescribing in 52% of all studies with initiation of an AED therapy in 14%, modification of AED therapy in 33%, and discontinuation of AED therapy in 5% of all studies. Specifically, the detection of electrographic seizures led to a change in AED therapy in 28% of all studies.The findings of continuous electroencephalographic monitoring resulted in a change in AED prescribing during or after half of the studies performed. Most AED changes were made as a result of the detection of electrographic seizures.

  View details for DOI 10.1001/archneurol.2009.100

  View details for PubMedID 19506131

• Impact of nonadherence to antiepileptic drugs on health care utilization and costs: findings from the RANSOM study. Epilepsia Faught, R. E., Weiner, J. R., Guérin, A., Cunnington, M. C., Duh, M. S. 2009; 50 (3): 501-9

  Abstract

  To study the impact of nonadherence to antiepileptic drugs (AEDs) on health care utilization and direct medical costs in a Medicaid population.A retrospective cohort design was employed using state Medicaid claims data from Florida, Iowa, and New Jersey during the period from January 1997 to June 2006. Patients aged >or=18 years with one or more neurologist visit with an epilepsy diagnosis and two or more pharmacy claims for AEDs were included. Medication possession ratio (MPR) was used to evaluate AED adherence with MPR >or= 0.80 considered adherent and <0.80 considered nonadherent. The association of nonadherence with utilization outcomes [hospitalizations, inpatient days, emergency department (ED), and outpatient visits] was assessed with univariate and multivariate Poisson regressions. Quarterly per-patient inpatient, outpatient, ED, and pharmacy costs were calculated across nonadherent and adherent quarters for the younger than 65 population (under-65) and cost differences were computed. Adjusted incremental costs of nonadherence were estimated with multivariate Tobit regression models.A total of 33,658 patients were included (28,470 under-65), together contributing 388,564 treated quarters (26% nonadherent). In multivariate analyses, AED nonadherence was associated with significantly higher incidence of hospitalizations [incident rate ratio (IRR) = 1.39, 95% confidence interval (CI) = 1.37-1.41], inpatient days (IRR = 1.76, 95% CI = 1.75-1.78), and ED visits (IRR = 1.19, 95% CI = 1.18-1.21). Nonadherence was associated with cost increases related to serious outcomes, including inpatient ($4,320 additional cost per quarter, 95% CI = $4,077-$4,564) and ED services ($303 additional cost per quarter, 95% CI = $273-$334), but lower costs for outpatient and pharmacy services, likely because of nonadherent behavior.Nonadherence to AEDs appears to be associated with serious outcomes, as evidenced by increased utilization and costs of inpatient and ED services.

  View details for DOI 10.1111/j.1528-1167.2008.01794.x

  View details for PubMedID 19183224

• Automated surveillance for central line-associated bloodstream infection in intensive care units. Infection control and hospital epidemiology Woeltje, K. F., Butler, A. M., Goris, A. J., Tutlam, N. T., Doherty, J. A., Westover, M. B., Ferris, V., Bailey, T. C. 2008; 29 (9): 842-6

  Abstract

  To develop and evaluate computer algorithms with high negative predictive values that augment traditional surveillance for central line-associated bloodstream infection (CLABSI).Barnes-Jewish Hospital, a 1,250-bed tertiary care academic hospital in Saint Louis, Missouri.We evaluated all adult patients in intensive care units who had blood samples collected during the period from July 1, 2005, to June 30, 2006, that were positive for a recognized pathogen on culture. Each isolate recovered from culture was evaluated using the definitions for nosocomial CLABSI provided by the National Healthcare Safety Network of the Centers for Disease Control and Prevention. Using manual surveillance by infection prevention specialists as the gold standard, we assessed the ability of various combinations of dichotomous rules to determine whether an isolate was associated with a CLABSI. Sensitivity, specificity, and predictive values were calculated.Infection prevention specialists identified 67 cases of CLABSI associated with 771 isolates recovered from blood samples. The algorithms excluded approximately 40%-62% of the isolates from consideration as possible causes of CLABSI. The simplest algorithm, with 2 dichotomous rules (ie, the collection of blood samples more than 48 hours after admission and the presence of a central venous catheter within 48 hours before collection of blood samples), had the highest negative predictive value (99.4%) and the lowest specificity (44.2%) for CLABSI. Augmentation of this algorithm with rules for common skin contaminants confirmed by another positive blood culture result yielded in a negative predictive value of 99.2% and a specificity of 68.0%.An automated approach to surveillance for CLABSI that is characterized by a high negative predictive value can accurately identify and exclude positive culture results not representing CLABSI from further manual surveillance.

  View details for DOI 10.1086/590261

  View details for PubMedID 18713052

  View details for PubMedCentralID PMC6788749

• Detection of asymptomatic cerebral microbleeds: a comparative study at 1.5 and 3.0 T. Academic radiology Stehling, C., Wersching, H., Kloska, S. P., Kirchhof, P., Ring, J., Nassenstein, I., Allkemper, T., Knecht, S., Bachmann, R., Heindel, W. 2008; 15 (7): 895-900

  Abstract

  The magnitude of iron-induced susceptibility changes in gradient echo T2*-weighted magnet resonance imaging (T2* MRI) increases with the field strength and should increase the sensitivity for detection of cerebral microbleeds (CMBs) at 3.0 T. To test these hypotheses, we prospectively examined individuals with documented CMBs at 1.5 and 3.0 T.Five hundred fifty elderly individuals, who participated in an interdisciplinary study of healthy aging, were examined at 3.0 T using T2* MRI sequences (repetition time [TR]/echo time [TE]/flip angle [FA] = 573 ms/16 ms/18 degrees ). Individuals positive for CMBs were asked to undergo an additional examination at 1.5 T (TR/TE/FA = 663 ms/23 ms/18 degrees ). Images were analyzed independently by two observers. CMBs were counted throughout the brain and were qualitatively analyzed comparing the degree of visible hypointensity on a 5-point scale from 1 (complete signal loss) to 5 (no detection) for both field strengths. Contrast-to-noise ratio of CMBs to surrounding brain tissue was calculated.At 3.0 T, CMBs were detected in 45 of 550 individuals; 25 agreed to an additional examination at 1.5 T. In this group (n = 25), a total of 53 CMBs were detected at 3.0 T, compared to 41 CMBs at 1.5 T. The mean contrast-to-noise ratio of CMBs was significantly increased at 3.0 T compared to 1.5 T (27.4 +/- 8.2 vs. 17.4 +/- 8.0; p < .001). On qualitative analysis, visibility of CMBs was ranked significantly higher at 3.0 T (1.3 +/- 0.4 vs. 2.9 +/- 1.1; p < .001).Evidence of past microbleeds may even be found in neurologically normal elderly individuals by MRI. Detection rate and visibility of CMBs benefit from the higher field strength, resulting in a significantly improved depiction of iron-containing brain structures (CMBs) at 3.0 T with potential clinical relevance.

  View details for DOI 10.1016/j.acra.2008.01.013

  View details for PubMedID 18572126

• Asymptotic Geometry of Multiple Hypothesis Testing. IEEE transactions on information theory Westover, M. B. 2008; 54 (7): 3327-3329

  Abstract

  We present a simple geometrical interpretation for the solution to the multiple hypothesis testing problem in the asymptotic limit. Under this interpretation, the optimal decision rule is a nearest neighbor classifier on the probability simplex.

  View details for DOI 10.1109/TIT.2008.924656

  View details for PubMedID 31607755

  View details for PubMedCentralID PMC6788803

• Multiple signals of recognition memory in the medial temporal lobe. Hippocampus Yassa, M. A., Stark, C. E. 2008; 18 (9): 945-54

  Abstract

  The medial temporal lobe (MTL) is known to play an essential role in recognition memory (the ability to judge the prior occurrence of a stimulus). Electrophysiological studies in nonhuman primates have suggested the presence of more than one type of recognition signal in the medial temporal lobe (e.g., novelty, familiarity, and recency). It has also been suggested that the perirhinal cortex plays an essential role in visual recognition memory. Here, we present fMRI results from 16 college-aged participants who underwent a continuous yes/no recognition task of novel and familiar pictures with multiple stimulus presentations. Our goal was to understand the dynamics of recognition in the MTL over multiple trials. We hypothesized that we could see changes in signal with repeated exposure that carry information related to novelty, familiarity, and recency. Whole brain activation maps demonstrated a strong novelty effect, marked by activity in several frontal and occipital regions that decreases with increasing number of presentations. The opposite pattern was observed in several other regions that include the supramarginal gyrus and inferior parietal lobule. In the MTL region, we observed monotonic decreases in activity across trials in the parahippocampal cortex as well as the anterior perirhinal cortex. We also observed monotonic increases in activity in the posterior perirhinal cortex with increasing memory strength. In addition, we observed clear effects of pre-experimental familiarity with the stimulus in several regions. Consistent with previously reported electrophysiological data, we found evidence for several medial temporal lobe signals carrying recency, familiarity, and novelty information.

  View details for DOI 10.1002/hipo.20452

  View details for PubMedID 18493928

• Achievable Rates for Pattern Recognition. IEEE transactions on information theory Westover, M. B., O'Sullivan, J. A. 2008; 54 (1): 299-320

  Abstract

  Biological and machine pattern recognition systems face a common challenge: Given sensory data about an unknown pattern, classify the pattern by searching for the best match within a library of representations stored in memory. In many cases, the number of patterns to be discriminated and the richness of the raw data force recognition systems to internally represent memory and sensory information in a compressed format. However, these representations must preserve enough information to accommodate the variability and complexity of the environment, otherwise recognition will be unreliable. Thus, there is an intrinsic tradeoff between the amount of resources devoted to data representation and the complexity of the environment in which a recognition system may reliably operate. In this paper, we describe a mathematical model for pattern recognition systems subject to resource constraints, and show how the aforementioned resource-complexity tradeoff can be characterized in terms of three rates related to the number of bits available for representing memory and sensory data, and the number of patterns populating a given statistical environment. We prove single-letter information-theoretic bounds governing the achievable rates, and investigate in detail two illustrative cases where the pattern data is either binary or Gaussian.

  View details for DOI 10.1109/tit.2007.911296

  View details for PubMedID 32153303

  View details for PubMedCentralID PMC7062371

• Functions of the left superior frontal gyrus in humans: a lesion study. Brain : a journal of neurology du Boisgueheneuc, F., Levy, R., Volle, E., Seassau, M., Duffau, H., Kinkingnehun, S., Samson, Y., Zhang, S., Dubois, B. 2006; 129 (Pt 12): 3315-28

  Abstract

  The superior frontal gyrus (SFG) is thought to contribute to higher cognitive functions and particularly to working memory (WM), although the nature of its involvement remains a matter of debate. To resolve this issue, methodological tools such as lesion studies are needed to complement the functional imaging approach. We have conducted the first lesion study to investigate the role of the SFG in WM and address the following questions: do lesions of the SFG impair WM and, if so, what is the nature of the WM impairment? To answer these questions, we compared the performance of eight patients with a left prefrontal lesion restricted to the SFG with that of a group of 11 healthy control subjects and two groups of patients with focal brain lesions [prefrontal lesions sparing the SFG (n = 5) and right parietal lesions (n = 4)] in a series of WM tasks. The WM tasks (derived from the classical n-back paradigm) allowed us to study the impact of the SFG lesions on domain (verbal, spatial, face) and complexity (1-, 2- and 3-back) processing within WM. As expected, patients with a left SFG lesion exhibited a WM deficit when compared with all control groups, and the impairment increased with the complexity of the tasks. This complexity effect was significantly more marked for the spatial domain. Voxel-to-voxel mapping of each subject's performance showed that the lateral and posterior portion of the SFG (mostly Brodmann area 8, rostral to the frontal eye field) was the subregion that contributed the most to the WM impairment. These data led us to conclude that (i) the lateral and posterior portion of the left SFG is a key component of the neural network of WM; (ii) the participation of this region in WM is triggered by the highest level of executive processing; (iii) the left SFG is also involved in spatially oriented processing. Our findings support a hybrid model of the anatomical and functional organization of the lateral SFG for WM, according to which this region is involved in higher levels of WM processing (monitoring and manipulation) but remains oriented towards spatial cognition, although the domain specificity is not exclusive and is overridden by an increase in executive demand, regardless of the domain being processed. From a clinical perspective, this study provides new information on the impact of left SFG lesions on cognition that will be of use to neurologists and neurosurgeons.

  View details for DOI 10.1093/brain/awl244

  View details for PubMedID 16984899

• Sleep in the critically ill patient. Sleep Weinhouse, G. L., Schwab, R. J. 2006; 29 (5): 707-16

  Abstract

  Critically ill patients are known to suffer from severely fragmented sleep with a predominance of stage I sleep and a paucity of slow wave and REM sleep. The causes of this sleep disruption include the intensive care unit (ICU) environment, medical illness, psychological stress, and many of the medications and other treatments used to help those who are critically ill. The clinical importance of this type of sleep disruption in critically ill patients, however, is not known. This article reviews the literature on sleep disruption in the ICU, the effects of sepsis on sleep, the effects of commonly used ICU medications on sleep, the relationship between sleep and sedation, and the literature on the biological and psychological consequences of sleep deprivation specifically as it relates to the critically ill. Finally, an integrative approach to improving sleep in the ICU is described.

  View details for DOI 10.1093/sleep/29.5.707

  View details for PubMedID 16774162

• Content analysis: What are they talking about? COMPUTERS & EDUCATION Strijbos, J. W., Martens, R. L., Prins, F. J., Jochems, W. M. 2006; 46 (1): 29-48

  View details for DOI 10.1016/j.compedu.2005.04.002

  View details for Web of Science ID 000233536700003

• Which EEG patterns warrant treatment in the critically ill? Reviewing the evidence for treatment of periodic epileptiform discharges and related patterns. Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Chong, D. J., Hirsch, L. J. 2005; 22 (2): 79-91

  Abstract

  Continuous electroencephalographic monitoring in critically ill patients has improved detection of nonconvulsive seizures and periodic discharges, but when and how aggressively to treat these electrographic patterns is unclear. A review of the literature was conducted to understand the nature of periodic discharges and the strength of the data on which management recommendations have been based. Periodic discharges are seen from a wide variety of etiologies, and the discharges themselves are electrographically heterogeneous. This spectrum suggests a need to consider these phenomena along a continuum between interictal and ictal, but more important clinically is the need to consider the likelihood of neuronal injury from each type of discharge in a given clinical setting. Recommendations for treatment are given, and a modification to current criteria for the diagnosis of nonconvulsive seizures is suggested.

  View details for DOI 10.1097/01.wnp.0000158699.78529.af

  View details for PubMedID 15805807

• A structural approach to selection bias. Epidemiology (Cambridge, Mass.) Hernán, M. A., Hernández-Díaz, S., Robins, J. M. 2004; 15 (5): 615-25

  Abstract

  The term "selection bias" encompasses various biases in epidemiology. We describe examples of selection bias in case-control studies (eg, inappropriate selection of controls) and cohort studies (eg, informative censoring). We argue that the causal structure underlying the bias in each example is essentially the same: conditioning on a common effect of 2 variables, one of which is either exposure or a cause of exposure and the other is either the outcome or a cause of the outcome. This structure is shared by other biases (eg, adjustment for variables affected by prior exposure). A structural classification of bias distinguishes between biases resulting from conditioning on common effects ("selection bias") and those resulting from the existence of common causes of exposure and outcome ("confounding"). This classification also leads to a unified approach to adjust for selection bias.

  View details for DOI 10.1097/01.ede.0000135174.63482.43

  View details for PubMedID 15308962

• Applying support vector machines to imbalanced datasets Akbani, R., Kwek, S., Japkowicz, N. edited by Boulicaut, J. F., Esposito, F., Giannoti, F., Pedreschi, D. SPRINGER-VERLAG BERLIN. 2004: 39-50

  View details for DOI 10.1007/978-3-540-30115-8_7

  View details for Web of Science ID 000223999500007

• Seizure detection: correlation of human experts. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Wilson, S. B., Scheuer, M. L., Plummer, C., Young, B., Pacia, S. 2003; 114 (11): 2156-64

  Abstract

  The description and application of a new, overlap-integral comparison method and the quantification of human vs. human accuracies that can be used as goals for algorithms.Four human experts marked ten 8 h electroencephalography (EEG) records from seizure patients. The seizures varied in origin and type, including complex partial, generalized absence, secondarily generalized and primary generalized tonic-clonic. The traditional any-overlap comparison method is used in addition to the overlap-integral method, which is sensitive to the correct placement of the seizure endpoints.The number of events marked by each reader ranged from 57 to 77. The average any-overlap sensitivity and false positives per hour rate are 0.92 and 0.117. The average overlap-integral correlation, sensitivity and specificity are 0.80, 0.82 and 0.9926. As expected, the correspondence between readers is high, but confounding issues resulted in overlap-integral sensitivities less than 0.5 for 10% of the records. Seven percent of the any-overlap sensitivities are less than 0.5. A comparison of the methods by record shows that the overlap-integral specificity and the any-overlap false positive rate measure different features.There was little variation between readers and they were essentially interchangeable. High seizure rate (many per hour), short seizure durations (<10 s) and long seizure durations (approximately 10 min) with ambiguous offsets can complicate the analysis and result in poor correlation. There may be any number of unmarked events in rigorously marked records and it may be preferable to use records from non-epilepsy patients to compute the false positive rate. The any-overlap and overlap-integral comparison methods are complementary.Correlation between expert human readers can be low on some records, which will complicate testing of seizure detection algorithms.

  View details for DOI 10.1016/s1388-2457(03)00212-8

  View details for PubMedID 14580614

• The neural multiple access channel. Neurocomputing Fischer, B. J., Westover, M. B. 2003; 52-54: 511-518

  Abstract

  In many neural systems, independently encoded information must at some point be transmitted over the spike train of one neuron. We introduce a method for quantitatively studying the effects of the signal encoding and transmission processes on the rates of transmission of multiple sources of information over one spike train, using the multiple access channel model from network information theory. To illustrate this method we study the effects of a small set of synaptic input patterns and input signal power spectra on the information capacity region of a simple three-neuron system.

  View details for DOI 10.1016/s0925-2312(02)00762-2

  View details for PubMedID 32153319

  View details for PubMedCentralID PMC7062373

• Layer 4C in monkey V1 may linearize the output of the LGN. Neurocomputing Westover, M. B., Anderson, C. H. 2003; 52-54: 671-676

  Abstract

  In primates, most LGN fibers terminate in cortical layer 4C, an anatomically prominent structure of unexplained function. We hypothesize that the enormous number of cells in layer 4C of monkey primate visual cortex functions as a neural network "hidden layer" that inverts distortions introduced by transmitting visual signals through the LGN. This hypothesis helps explain how simple cells respond (quasi-) linearly to visual inputs in spite of nonlinearities present in LGN responses. Linearization averts prematurely discarding visual information, in keeping with the role of primary visual cortex as the source of raw visual information to the rest of the brain.

  View details for DOI 10.1016/s0925-2312(02)00863-9

  View details for PubMedID 32153320

  View details for PubMedCentralID PMC7062374

• Acute seizures after intracerebral hemorrhage: a factor in progressive midline shift and outcome. Neurology Vespa, P. M., O'Phelan, K., Shah, M., Mirabelli, J., Starkman, S., Kidwell, C., Saver, J., Nuwer, M. R., Frazee, J. G., McArthur, D. A., Martin, N. A. 2003; 60 (9): 1441-6

  Abstract

  To determine whether early seizures that occur frequently after intracerebral hemorrhage (ICH) lead to increased brain edema as manifested by increased midline shift.A total of 109 patients with ischemic stroke (n = 46) and intraparenchymal hemorrhage (n = 63) prospectively underwent continuous EEG monitoring after admission. The incidence, timing, and factors associated with seizures were defined. Serial CT brain imaging was conducted at admission, 24 hours, and 48 to 72 hours after hemorrhage and assessed for hemorrhage volume and midline shift. Outcome at time of discharge was assessed using the Glasgow Outcome Scale score.Electrographic seizures occurred in 18 of 63 (28%) patients with ICH, compared with 3 of 46 (6%) patients with ischemic stroke (OR = 5.7, 95% CI 1.4 to 26.5, p < 0.004) during the initial 72 hours after admission. Seizures were most often focal with secondary generalization. Seizures were more common in lobar hemorrhages but occurred in 21% of subcortical hemorrhages. Posthemorrhagic seizures were associated with neurologic worsening on the NIH Stroke Scale (14.8 vs 18.6, p < 0.05) and with an increase in midline shift (+ 2.7 mm vs -2.4 mm, p < 0.03). There was a trend toward increased poor outcome (p < 0.06) in patients with posthemorrhagic seizures. On multivariate analysis, age and initial NIH Stroke Scale score were independent predictors of outcome.Seizures occur commonly after ICH and may be nonconvulsive. Seizures are independently associated with increased midline shift after intraparenchymal hemorrhage.

  View details for DOI 10.1212/01.wnl.0000063316.47591.b4

  View details for PubMedID 12743228

• In depolarized and glucose-deprived neurons, Na+ influx reverses plasmalemmal K+-dependent and K+-independent Na+/Ca2+ exchangers and contributes to NMDA excitotoxicity. Journal of neurochemistry Czyz, A., Kiedrowski, L. 2002; 83 (6): 1321-8

  Abstract

  Cerebellar granule cells (CGCs) express K+-dependent (NCKX) and K+-independent (NCX) plasmalemmal Na+/Ca2+ exchangers which, under plasma membrane-depolarizing conditions and high cytosolic [Na+], may reverse and mediate potentially toxic Ca2+ influx. To examine this possibility, we inhibited NCX or NCKX with KB-R7943 or K+-free medium, respectively, and studied how gramicidin affects cytosolic [Ca2+] and 45Ca2+ accumulation. Gramicidin forms pores permeable to alkali cations but not Ca2+. Therefore, gramicidin-induced Ca2+ influx is indirect; it results from fluxes of monovalent cations. In the presence of Na+, but not Li+ or Cs+, gramicidin induced Ca2+ influx that was inhibited by simultaneous application of KB-R7943 and K+-free medium. The data indicate that gramicidin-induced Na+ influx reverses NCX and NCKX. To test the role of NCX and/or NCKX in excitotoxicity, we studied how NMDA affects the viability of glucose-deprived and depolarized CGCs. To assure depolarization of the plasma membrane, we inhibited Na+,K+-ATPase with ouabain. Although inhibition of NCX or NCKX reversal failed to significantly limit 45Ca2+ accumulation and excitotoxicity, simultaneously inhibiting NCX and NCKX reversal was neuroprotective and significantly decreased NMDA-induced 45Ca2+ accumulation. Our data suggest that NMDA-induced Na+ influx reverses NCX and NCKX and leads to the death of depolarized and glucose-deprived neurons.

  View details for DOI 10.1046/j.1471-4159.2002.01227.x

  View details for PubMedID 12472886

• The effects of normal aging on sleep spindle and K-complex production. Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology Crowley, K., Trinder, J., Kim, Y., Carrington, M., Colrain, I. M. 2002; 113 (10): 1615-22

  Abstract

  Despite a relatively large body of literature describing the characteristics of sleep spindles and K-complexes in young adults, relatively little research has been conducted in older individuals. The general consensus from the few studies that have addressed this issue is that there is a progressive decrease in the number of spindles and K-complexes with age, although there is large intra-individual variation. Whether or not these changes are an inevitable consequence of the aging process can be addressed by studying healthy older adults who provide an example of the effects of age independently from those of disease.Fourteen young adults (mean age=21.4+/-2.5 years) and 20 older adults (mean age=75.5+/-6.3 years) participated in the study. All subjects were neurologically and medically healthy and were not taking any medications with a known effect on the central nervous system or sleep. For each subject, a number of characteristics were determined including the number, density (SS/min), amplitude and frequency of all spindles as well as the number and density of K-complexes (KC/min).Spindle number, density and duration as well as K-complex number and density were all significantly lower in the elderly compared to the young adults. The EEG frequency within the spindles was significantly higher in the elderly, although the absolute difference was less than 0.5 Hz. Multiple regression analysis indicated that spindle duration and K-complex density were able to predict over 90% of the variance in age.The age-related decrease in sleep spindle and K-complex density is consistent with previous reports and may be interpreted as an age-related alteration of thalamocortical regulatory mechanisms.

  View details for DOI 10.1016/s1388-2457(02)00237-7

  View details for PubMedID 12350438

• Linearly decodable functions from neural population codes. Neurocomputing Westover, M. B., Eliasmith, C., Anderson, C. H. 2002; 44-46: 691-696

  Abstract

  The population vector is a linear decoder for an ensemble of neurons, whose response properties are nonlinear functions of the input vector. However, previous analyses of this decoder seem to have missed the observation that the population vector can also be used to estimate functions of the input vector. We explore the use of singular value decomposition to delineate the set of functions which are linearly decodable from a given population of noisy neurons.

  View details for DOI 10.1016/s0925-2312(02)00459-9

  View details for PubMedID 32153318

  View details for PubMedCentralID PMC7062372

• A general framework for neurobiological modeling: an application to the vestibular system. Neurocomputing Eliasmith, C., Westover, M. B., Anderson, C. H. 2002; 44-46: 1071-6

  Abstract

  The otolith organs in the vestibular system are excellent detectors of linear accelerations. However, any measurement of linear acceleration is ambiguous between a tilt in a gravitational field and an inertial acceleration. Angelaki et al. have put forward a general hypothesis about how inertial accelerations can be computed based on vestibular signals (J. Neurosci. 19 (1999) 316). We have constructed a realistic, detailed model of the relevant systems to test this hypothesis. The model produces useful predictions about what kinds of neurons should be found in the vestibular nucleus if such a computation is actually performed in the vestibular system. The model is constructed using general principles of neurobiological simulation (J. Neurophys. 84 (2000) 2113).

  View details for DOI 10.1016/s0925-2312(02)00418-6

  View details for PubMedID 12744262

  View details for PubMedCentralID PMC6788744

• A model of sleep spindles generation Zygierewicz, J., Suffczynski, P., Blinowska, K. ELSEVIER SCIENCE BV. 2001: 1619-1625

  View details for DOI 10.1016/S0925-2312(01)00516-1

  View details for Web of Science ID 000169129200211

• Circadian rhythms in systemic hemodynamics and renal function in healthy subjects and patients with nephrotic syndrome. Kidney international Voogel, A. J., Koopman, M. G., Hart, A. A., van Montfrans, G. A., Arisz, L. 2001; 59 (5): 1873-80

  Abstract

  The resemblance of the circadian rhythm of glomerular filtration rate (GFR) to that of arterial blood pressure (BP) suggests that systemic hemodynamic factors contribute to this variation. In the present study, this was investigated using continuous BP monitoring and pulse wave analysis. The study was performed in eight healthy subjects and in seven patients with nephrotic syndrome who had normal or reversed rhythms of GFR.Circadian variations of renal function (continuous infusion of inulin/paraaminohippuric acid), noninvasive finger arterial pressure (Portapres), and vasoactive hormone levels were monitored during 27 hours. With stepwise backward regression analysis, the contributions of the measured variables to the circadian variation of GFR were investigated.Both groups showed a reduction of BP at night. In the controls, this was related to a drop in cardiac output, while in the patients, total peripheral resistance decreased at night. None of the hemodynamic variables explained the circadian GFR variation in both groups. In the controls, only 6% of the effective renal plasma flow (ERPF) rhythm was associated with variations in cardiac output (P = 0.03). In the patients, atrial natriuretic peptide and plasma renin activity were responsible for 36% of the variation in GFR (P < 0.01).These results indicate that the circadian variation of GFR does not result directly from changes in BP or cardiac output. An inverted GFR rhythm in patients with nephrotic syndrome may originate from hormonal mechanisms rather than directly from the hemodynamic effects of edema mobilization.

  View details for DOI 10.1046/j.1523-1755.2001.0590051873.x

  View details for PubMedID 11318959

• EEG findings in dementia with Lewy bodies and Alzheimer's disease. Journal of neurology, neurosurgery, and psychiatry Briel, R. C., McKeith, I. G., Barker, W. A., Hewitt, Y., Perry, R. H., Ince, P. G., Fairbairn, A. F. 1999; 66 (3): 401-3

  Abstract

  To evaluate the role of the EEG in the diagnosis of dementia with Lewy bodies (DLB).Standard EEG recordings from 14 patients with DLB confirmed at postmortem were examined and were compared with the records from 11 patients with Alzheimer's disease confirmed at postmortemSeventeen of the total of 19 records from the patients with DLB were abnormal. Thirteen showed loss of alpha activity as the dominant rhythm and half had slow wave transient activity in the temporal lobe areas. This slow wave transient activity correlated with a clinical history of loss of consciousness. The patients with Alzheimer's disease were less likely to show transient slow waves and tended to have less marked slowing of dominant rhythm.The greater slowing of the EEG in DLB than in Alzheimer's disease may be related to a greater loss of choline acetyltransferase found in DLB. Temporal slow wave transients may be a useful diagnostic feature in DLB and may help to explain the transient disturbance of consciousness which is characteristic of the disorder.

  View details for DOI 10.1136/jnnp.66.3.401

  View details for PubMedID 10084544

  View details for PubMedCentralID PMC1736269

• Value of natriuretic peptides in assessment of patients with possible new heart failure in primary care. Lancet (London, England) Cowie, M. R., Struthers, A. D., Wood, D. A., Coats, A. J., Thompson, S. G., Poole-Wilson, P. A., Sutton, G. C. 1997; 350 (9088): 1349-53

  Abstract

  The reliability of a clinical diagnosis of heart failure in primary care is poor. Concentrations of natriuretic peptides are high in heart failure. This population-based study examined the predictive value of natriuretic peptides in patients with a new primary-care diagnosis of heart failure.Concentrations of plasma atrial (ANP and N-terminal ANP) and B-type (BNP) natriuretic peptides were measured by radioimmunoassay in 122 consecutive patients referred to a rapid-access heart-failure clinic with a new primary-care diagnosis of heart failure. On the basis of clinical assessment, chest radiography, and transthoracic echocardiography, a panel of three cardiologists decided that 35 (29%) patients met the case definition for new heart failure. ANP and NT-ANP results were available for 117 patients (34 with heart failure) and BNP results for 106 (29 with heart failure).Geometric mean concentrations of natriuretic peptides were much higher in patients with heart failure than in those with other diagnoses (29.2 vs 12.4 pmol/L for ANP; 63.9 vs 13.9 pmol/L for BNP; 1187 vs 410.6 pmol/L for NT-ANP; all p < 0.001). At cut-off values chosen to give negative predictive values for heart failure of 98% (ANP > or = 18.1 pmol/L, NT-ANP > or = 537.6 pmol/L, BNP > or = 22.2 pmol/L), the sensitivity, specificity, and positive predictive value for ANP were 97%, 72%, and 55%; for NT-ANP 97%, 66%, and 54%; and for BNP 97%, 84%, and 70%. Addition of ANP or NT-ANP concentration or both did not improve the predictive power of a logistic regression model containing BNP concentration alone.In patients with symptoms suspected by a general practitioner to be due to heart failure, plasma BNP concentration seems to be a useful indicator of which patients are likely to have heart failure and require further clinical assessment.

  View details for DOI 10.1016/S0140-6736(97)06031-5

  View details for PubMedID 9365448

• Correlation of EEG activities between slow-wave sleep and wakefulness in patients with supra-tentorial stroke. Brain topography Yokoyama, E., Nagata, K., Hirata, Y., Satoh, Y., Watahiki, Y., Yuya, H. 1996; 8 (3): 269-73

  Abstract

  Using topographic EEG mapping, we studied the relationships between delta activity during slow-wave sleep (SWS) and the background EEG activity during wakefulness, in 11 normal subjects and 35 stroke patients with unilateral supra-tentorial lesions. Delta-1 power during SWS showed a significant positive correlation with alpha-1 power during wakefulness, in both hemispheres. Delta-1 and delta-2 power during SWS correlated positively not only with alpha-2 power, but also with delta-1 and delta-2 power during wakefulness in the affected hemisphere. these figures indicate that the amount of delta activity during SWS can be associated with that of alpha activity during wakefulness. A close negative correlation was observed between delta power during SWS and the age of the subjects in the patient group. The Barthel index showed no significant correlation with delta-1 or delta-2 power in either hemisphere in patient group. Our results suggest that delta activity during SWS may be associated with dysfunction of the cerebral cortex in stroke patients as well as in normal aged subjects.

  View details for DOI 10.1007/BF01184783

  View details for PubMedID 8728417

• Value of the electroencephalogram in adult patients with untreated idiopathic first seizures. Archives of neurology van Donselaar, C. A., Schimsheimer, R. J., Geerts, A. T., Declerck, A. C. 1992; 49 (3): 231-7

  Abstract

  We prospectively studied the reliability and accuracy of the electroencephalogram as a predictor of the risk of recurrence within 2 years in 157 patients with untreated idiopathic first seizures. In all patients, a standard electroencephalogram and, if necessary, an electroencephalogram after partial sleep deprivation were obtained. All electroencephalograms were scored by one observer according to a fixed protocol. The finding of epileptic discharges was associated with a risk of recurrence of 83% (95% confidence interval, 69% to 97%) vs 41% (95% confidence interval, 29% to 53%) in patients with nonepileptic abnormalities and 12% (95% confidence interval, 3% to 21%) in patients in whom both electroencephalograms were normal. The sensitivity proved to be 48%. Interobserver agreement among four neurologists, who independently read 50 electroencephalograms, was found to be moderate. Predictive value for each observer, however, was good. We conclude that electroencephalogram findings may play a role in the decision to initiate or delay treatment after an idiopathic first seizure.

  View details for DOI 10.1001/archneur.1992.00530270045017

  View details for PubMedID 1536624

• Prediction of delayed cerebral ischemia, rebleeding, and outcome after aneurysmal subarachnoid hemorrhage. Stroke Hijdra, A., van Gijn, J., Nagelkerke, N. J., Vermeulen, M., van Crevel, H. 1988; 19 (10): 1250-6

  Abstract

  Using logistic regression, we analyzed the predictive value of a number of entry variables with respect to the outcome variables delayed cerebral ischemia, rebleeding, and poor outcome (death or severe disability) in patients with aneurysmal subarachnoid hemorrhage. The entry variables were clinical condition on admission (grades on the Glasgow Coma Scale, Hunt and Hess system), the amount of subarachnoid and intraventricular blood and the presence of hydrocephalus on the admission computed tomogram, and antifibrinolytic treatment with tranexamic acid. We used data from a prospectively studied population of 176 patients admitted within 72 hours after subarachnoid hemorrhage. The risk of delayed cerebral ischemia was best predicted by the amount of subarachnoid blood, intraventricular blood, and antifibrinolytic treatment irrespective of clinical condition and hydrocephalus. The site of delayed cerebral ischemia was not related to the location of the subarachnoid hemorrhage. Antifibrinolytic treatment was the only entry variable (negatively) predicting the risk of rebleeding. Death or severe disability after 3 months was best predicted by the amount of subarachnoid blood and the initial clinical condition reflected by the grade on the Glasgow Coma Scale.

  View details for DOI 10.1161/01.str.19.10.1250

  View details for PubMedID 3176085

• Prognostic and neurophysiological implications of concurrent burst suppression and alpha patterns in the EEG of post-anoxic coma. Electroencephalography and clinical neurophysiology Zaret, B. S. 1985; 61 (4): 199-209

  Abstract

  Concurrent burst suppression and alpha pattern coma developed in the EEG of a 2-year-old child who suffered a cardiac arrest secondary to hypoxemia from Haemophilus influenza epiglottis. The neurophysiological implications of this association are discussed and the literature pertaining to the role of barbiturates in the production of post-anoxic coma with an alpha pattern and experimental post-resuscitative alpha frequencies is reviewed.

  View details for DOI 10.1016/0013-4694(85)91085-5

  View details for PubMedID 2411497

• RELIABILITY OF CLINICAL INTERPRETATION OF ELECTROENCEPHALOGRAM CLINICAL ELECTROENCEPHALOGRAPHY STRUVE, F. A., BECKA, D. R., GREEN, M. A., HOWARD, A. 1975; 6 (2): 54-60

  View details for DOI 10.1177/155005947500600202

  View details for Web of Science ID A1975AG80800002

• A mathematical theory of the functional dynamics of cortical and thalamic nervous tissue. Kybernetik Wilson, H. R., Cowan, J. D. 1973; 13 (2): 55-80

  View details for DOI 10.1007/BF00288786

  View details for PubMedID 4767470

• The proof and measurement of association between two things AMERICAN JOURNAL OF PSYCHOLOGY Spearman, C. 1904; 15: 72-101

  View details for DOI 10.2307/1412159

  View details for Web of Science ID 000200130600005