Sabyasachi Bandyopadhyay

All Publications

• Deep Learning-Based Continuous QT Monitoring to Identify High-Risk Prolongation Events After Class III Antiarrhythmic Initiation. Circulation Ansari, R. A., Bandyopadhyay, S., Trivedi, R. K., Brennan, K. A., Liu, X., Ganesan, P., Hughes, J. W., Perino, A. C., Ashley, E. A., Wang, P. J., Coleman, T., Perez, M. V., Ouyang, D., Narayan, S. M., Rogers, A. J. 2026; 153 (1): 35-46

  Abstract

  Drug-induced QT prolongation after successful inpatient loading of class III antiarrhythmics may occur during routine outpatient care. Insertable cardiac monitors offer continuous signals but are limited by single-lead configuration. We hypothesized that a spatially aware deep learning system (3DRECON-QT) can reconstruct spatial information from a single lead vector to quantify QT/QTc and identify high-risk prolongation.We developed 3DRECON-QT using a multitask encoder-decoder that ingests a 10-s single-lead signal, reconstructs 12 leads, and predicts QT/QTc. The model was developed using 12-lead ECGs with clinician-adjudicated QT/RR from a large health system and tested in an external center with different ECG hardware. Continuous monitoring performance was assessed in a public dofetilide-loading data set with serial ECGs. In a real-world cohort of outpatients on dofetilide or sotalol presenting to the hospital or emergency room for any reason, rates of ventricular arrhythmias and QT prolongation were assessed. Device validation was tested in patients with insertable cardiac monitor recordings paired with clinical 12-lead ECGs.3DRECON-QT classified prolonged QTc from single-lead signals with area under the receiver operating characteristics curve, 0.942 (mean absolute error, 17.5 ms) in the internal test set and 0.943 (mean absolute error, 21.1 ms) externally. During continuous dofetilide monitoring, predictions correlated with ground truth (r, 0.851; mean absolute error, 17.8 ms; area under the receiver operating characteristics curve, 0.936 for prolonged QTc, 0.816 for ≥15% QTc rise). QTc prediction from true insertable cardiac monitor recordings showed r=0.824 and mean absolute error, 17.5 ms. In outpatients on class III antiarrhythmics (n=1676), 16.5% had high-risk QTc prolongation. Ventricular arrhythmia events were 3.97% versus 0.86% without prolongation (adjusted odds ratio, 4.24 [95% CI, 1.81-9.90]). 3DRECON-QT detected these events with area under the receiver operating characteristics curve 0.94 (F1 score, 0.60).A single-lead, deep-learning approach can achieve guideline-level measurement accuracy, enable continuous QTc surveillance from nonstandard ECG vectors, and identify clinically meaningful outpatient QTc prolongation associated with a >4-fold increase in serious ventricular arrhythmias. This strategy may enhance safety monitoring after class III antiarrhythmic initiation and support targeted intervention.

  View details for DOI 10.1161/CIRCULATIONAHA.125.077494

  View details for PubMedID 41460938

• Long-term, ambulatory 12-lead ECG from a single non-standard lead using perceptual reconstruction. medRxiv : the preprint server for health sciences Bandyopadhyay, S., Chiu, I. M., Ansari, R., Liu, S., Hughes, J. W., Perino, A. C., Bhatia, N. K., Ouyang, D., Ashley, E. A., Perez, M. V., Zou, J., Narayan, S. M., Rogers, A. J. 2025

  Abstract

  Despite its broadening indications, the implantable cardiac monitor (ICM) records a narrow, nonstandard electrocardiogram (ECG) signal which precludes morphological and functional assessments or the application of 12-lead ECG models. We hypothesize that deep learning can be used to reconstruct 12-lead ECG from a single ICM lead for continuously assessing clinical endpoints outside of rhythm detection alone.To reconstruct 12-lead ECG from a single ICM lead to detect conduction, repolarization, rhythm, and cardiac functional changes in a large, diverse patient population.We annotated 75,450 echocardiogram-ECG pairs with five disease labels a) right bundle branch block, b) left bundle branch block, c) atrial fibrillation, d) QT-prolongation and e) low left ventricular ejection fraction (LVEF) using regex-based parsing of clinician interpretations. We used perceptual loss to train a deep U-Net (ECG12-PerceptNet) to reconstruct 12-lead ECG from a simulated ICM signal. We compared the classification performance of the reconstructed 12-lead ECG against the original 12-lead and single lead ECG in an internal and external test set. Furthermore, we trained a regression model to predict the absolute LVEF using original and reconstructed 12-lead ECGs.The reconstructed ECG approached the original 12-lead ECG in classification performance across all endpoints while significantly outperforming the single lead ECG. We show two case studies where sequential LVEF measurements were tracked using LVEF predicted with the original and reconstructed 12-lead ECG.In this paper, we report the ECG12-PerceptNet which reconstructs 12-lead ECG from a simulated ICM signal. This can enable continuous in-home or ambulatory monitoring of cardiac functional changes, potentially reducing hospitalizations and out-of-hospital cardiac arrest.

  View details for DOI 10.64898/2025.12.17.25342224

  View details for PubMedID 41445642

  View details for PubMedCentralID PMC12724160

• Perioperative Artificial Intelligence Driven Integrated Modeling of Surgeries using Anesthetic, Physical and Cognitive Statuses for Predicting Hospital Outcomes. Research square Bandyopadhyay, S., Zhang, J., Ison, R. L., Cherukuvada, B. P., Libon, D. J., Tighe, P., Rashidi, P., Price, C. 2025

  Abstract

  The association between preoperative cognitive status and surgical outcomes is a critical yet scarcely explored area. We assessed how preoperative cognitive status, as measured by clock drawing tests, contributed to predicting length of hospital stay, charges, pain during follow-up, and 1-year mortality beyond intraoperative variables, demographics, physical status, and comorbidities. We expanded our analysis to 6 surgical groups where sufficient data was available. Clock drawings were represented by 10 constructional features discovered by a semi-supervised deep learning algorithm, validated to differentiate between dementia and non-dementia patients. Machine learning models were trained using 5-fold cross-validation to classify postoperative outcomes. Shapley Additive Explanations analysis was used to find the most predictive features. Our results showed that the perioperative cognitive dataset served as the best dataset for 12 of 18 possible surgery-outcome combinations. Interpretability analysis showed that surgery duration was the most significant predictor of adverse outcomes, followed by anesthetic concentration. Disruptions in baseline correlations between intraoperative variables revealed that low average blood pressure and high standard deviation of blood pressure predicted adverse outcomes. Among the clock features, clock size was the most significant predictor of adverse outcomes. Our findings have relevance for improving healthcare modeling and perioperative risk prediction.

  View details for DOI 10.21203/rs.3.rs-8000504/v1

  View details for PubMedID 41333422

• Deep Learning-Based Continuous QT Monitoring Identifies High-Risk Prolongation Events After Class III Antiarrhythmic Initiation Rogers, A., Ansari, R., Bandyopadhyay, S., Trivedi, R., Brennan, K., Ganesan, P., Perino, A., Ashley, E., Wang, P., Perez, M., Ouyang, D., Narayan, S. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for DOI 10.1161/circ.152.suppl_3.4370942

  View details for Web of Science ID 001613807100048

• Development of Personalized Myocardial Surface Mesh Models with LGE Scar Integration: a Pipeline for Machine Learning and Digital Twins Liu, X., Qayyum, A., Ganesan, P., Bandyopadhyay, S., Somani, S., Brennan, K., Wang, P., Niederer, S., Narayan, S., Rogers, A. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for DOI 10.1161/circ.152.suppl_3.4367687

  View details for Web of Science ID 001613944300010

• Abstract 4367773: Predicting Peak Heart Rate from Resting 12-Lead ECGs in Patients Undergoing Stress Testing using Deep Learning Liu, X., Bandyopadhyay, S., Ganesan, P., Somani, S., Brennan, K., Karius, A., Baykaner, T., Perino, A., Wang, P., Ashley, E., Perez, M., Narayan, S., Rogers, A. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for DOI 10.1161/circ.152.suppl_3.4367773

  View details for Web of Science ID 001613944300042

• AI-based prediction of mortality in patients with ventricular tachycardia Bandyopadhyay, S., Sadri, S., Brennan, K., Ganesan, P., Clopton, P., Ruiperez-Campillo, S., Peralta, E., Sillett, C., Rogers, A., Narayan, S. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for DOI 10.1161/circ.152.suppl_3.4370585

  View details for Web of Science ID 001613876200024

• Identifying optimum ECG features to predict sudden cardiac arrest at varying time points before the event Bandyopadhyay, S., Ganesan, P., Brennan, K., Ruiperez-Campillo, S., Ansari, R., Clopton, P., Perino, A., Wang, P., Ashley, E., Perez, M., Narayan, S., Rogers, A. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for DOI 10.1161/circ.152.suppl_3.4369502

  View details for Web of Science ID 001613825200023

• Novel Foundation Models for Detecting and Generating Text Reports of Atrial Fibrillation from 12-lead ECGs in a Large Registry Ganesan, P., Peralta, E., Ruiperez-Campillo, S., Bandyopadhyay, S., Rogers, A., Chang, H., Brennan, K., Sillett, C., Clopton, P., Perino, A., Niederer, S., Narayan, S. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for DOI 10.1161/circ.152.suppl_3.4370248

  View details for Web of Science ID 001613838800021

• Automated End-to-End Framework for Extracting Raw ECG Waveforms and ST Segment Values from ECG Reports and Predicting ST Elevation by Machine Learning Ganesan, P., Liu, X., Bandyopadhyay, S., Ansari, R., Somani, S., Brennan, K., Karius, A., Baykaner, T., Perino, A., Wang, P., Ashley, E., Perez, M., Narayan, S., Rogers, A. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for DOI 10.1161/circ.152.suppl_3.4371591

  View details for Web of Science ID 001613816800012

• Non-Contact Magnetocardiography Localizes Atrial Foci as Accurately as High-Resolution Contact ECG Brennan, K., Bandyopadhyay, S., Ganesan, P., Ansari, R., Somani, S., Liu, X., Baykaner, T., Perino, A., Wang, P., Narayan, S., Rogers, A. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for DOI 10.1161/circ.152.suppl_3.4358583

  View details for Web of Science ID 001613911000027

• Transformer-based ECG beat foundation model reconstructs full 12-Lead morphology, vectorcardiogram and predicts peak heart rate in stress ECG Bandyopadhyay, S., Liu, X., Ganesan, P., Somani, S., Karius, A., Baykaner, T., Wang, P., Ashley, E., Perez, M., Narayan, S., Rogers, A. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for DOI 10.1161/circ.152.suppl_3.4370718

  View details for Web of Science ID 001613779500045

• Longitudinal Evaluation of Anti-Arrhythmic Drug Use to Predict Hospitalization or Death in Patients with Ventricular Tachycardia Sadri, S., Brennan, K., Bandyopadhyay, S., Ganesan, P., Desai, Y., Peralta, E., Feng, R., Sillett, C., Ruiperez-Campillo, S., Wang, P., Clopton, P., Rogers, A., Narayan, S. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for DOI 10.1161/circ.152.suppl_3.4370694

  View details for Web of Science ID 001613779500004

• Large Language Models Detect Ventricular Tachycardia Recurrence in Clinical Notes and Enable Prediction of Clinical Outcomes at Scale Sadri, S., Brennan, K., Bandyopadhyay, S., Desai, Y., Ganesan, P., Peralta, E., Feng, R., Sillett, C., Ruiperez-Campillo, S., Wang, P., Clopton, P., Rogers, A., Narayan, S. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for DOI 10.1161/circ.152.suppl_3.4366827

  View details for Web of Science ID 001613801100038

• Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling. Nature communications Contreras, M., Silva, B., Shickel, B., Davidson, A., Ozrazgat-Baslanti, T., Ren, Y., Guan, Z., Balch, J., Zhang, J., Bandyopadhyay, S., Loftus, T., Khezeli, K., Lipori, G., Sena, J., Nerella, S., Bihorac, A., Rashidi, P. 2025; 16 (1): 7315

  Abstract

  Intensive care unit (ICU) patients often experience rapid changes in clinical status, requiring timely identification of deterioration to guide life-sustaining interventions. Current artificial intelligence (AI) models for acuity assessment rely on mortality as a proxy and lack direct prediction of clinical instability or treatment needs. Here we present APRICOT-M, a state-space model to predict real-time ICU acuity outcomes and transitions, and the need for life-sustaining therapies within the next four hours. The model integrates vital signs, laboratory results, medications, assessment scores, and patient characteristics, to make predictions, handling sparse, irregular data efficiently. Our model is trained on over 140,000 ICU admissions across 55 hospitals and validated on external and real-time data, outperforming clinical scores in predicting mortality and instability. The model demonstrates clinical relevance, with physicians reporting alerts as actionable and timely in a substantial portion of cases. These results highlight APRICOT-M's potential to support earlier, more informed ICU interventions.

  View details for DOI 10.1038/s41467-025-62121-1

  View details for PubMedID 40781071

  View details for PubMedCentralID 4057290

• Physics-Inspired Diffusion Probabilistic Models for Improved Denoising in Intracardiac Time Series. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Ruiperez-Campillo, S., Rau, M., Ganesan, P., Brennan, K. A., Feng, R., Bandyopadhyay, S., Rogers, A. J., Narayan, S. M., Vogt, J. E. 2025; 2025: 1-5

  Abstract

  Intracardiac electrophysiological (EP) signals are frequently contaminated by diverse noise sources, posing a major obstacle to accurate arrhythmia diagnosis. We hypothesized that a physics-inspired conditional denoising diffusion probabilistic model (cDDPM) could outperform both classical filters and variational autoencoders by preserving subtle morphological features. Using 5706 monophasic action potentials from 42 patients, we introduced a range of simulated and real EP noise, then trained the cDDPM in an iterative process analogous to Brownian motion. The proposed model achieved superior performance across RMSE, PCC, and PSNR metrics, confirming its robustness against complex noise while maintaining essential signal fidelity. These findings suggest that diffusion-based methods can significantly enhance the clinical utility of EP signals for arrhythmia management and intervention.Clinical Relevance- We propose a denoising diffusion probabilistic model to reconstruct intracardiac signals in the presence of complex noise, which holds the potential to enhance diagnostic accuracy in EP procedures and inform more targeted treatment strategies.

  View details for DOI 10.1109/EMBC58623.2025.11252692

  View details for PubMedID 41336909

• CONTINUOUS LONG-TERM QT INTERVAL MONITORING USING SPATIALLY ENCODED DEEP LEARNING OF DERIVED IMPLANTABLE CARDIAC MONITOR SIGNALS Ansari, R., Bandyopadhyay, S., Brennan, K., Srivastava, V., Ganesan, P., Feng, R., Baykaner, T., Perez, M., Perino, A., Narayan, S. M., Rogers, A. J. ELSEVIER SCIENCE INC. 2025: 24

  View details for Web of Science ID 001463283800024

• LARGE LANGUAGE MODELS IDENTIFY ATRIAL FIBRILLATION PROGRESSION ON UNPRECEDENTED SCALE Brennan, K., Feng, R., Goyal, J., Chang, H., Deb, B., Srivastava, V., Ganesan, P., Bandyopadhyay, S., Ansari, R., Ruiperez-Campilo, S., Clopton, P., De Larocheliere, H., Rogers, A. J., Narayan, S. M. ELSEVIER SCIENCE INC. 2025: 237

  View details for Web of Science ID 001463312500038

• Identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram. NPJ digital medicine Rogers, A. J., Bhatia, N. K., Bandyopadhyay, S., Tooley, J., Ansari, R., Thakkar, V., Xu, J., Soto, J. T., Tung, J. S., Alhusseini, M. I., Clopton, P., Sameni, R., Clifford, G. D., Hughes, J. W., Ashley, E. A., Perez, M. V., Zaharia, M., Narayan, S. M. 2025; 8 (1): 21

  Abstract

  Cardiac wall motion abnormalities (WMA) are strong predictors of mortality, but current screening methods using Q waves from electrocardiograms (ECGs) have limited accuracy and vary across racial and ethnic groups. This study aimed to identify novel ECG features using deep learning to enhance WMA detection, referencing echocardiography as the gold standard. We collected ECG and echocardiogram data from 35,210 patients in California and labeled WMA using unstructured language parsing of echocardiographic reports. A deep neural network (ECG-WMA-Net) was trained and outperformed both expert ECG interpretation and Q-wave indices, achieving an AUROC of 0.781 (CI: 0.762-0.799). The model was externally validated in a diverse cohort from Georgia (n = 2338), with an AUC of 0.723 (CI: 0.685-0.757). Explainability analysis revealed significant contributions from QRS and T-wave regions. This deep learning approach improves WMA screening accuracy, potentially addressing physiological differences not captured by standard ECG-based methods.

  View details for DOI 10.1038/s41746-024-01407-y

  View details for PubMedID 39799179

  View details for PubMedCentralID PMC11724909

• Advances in Electrocardiogram-Based Artificial Intelligence Reveal Multisystem Biomarkers. Journal of clinical & experimental cardiology Liu, X., Bandyopadhyay, S., Rogers, A. J. 2025; 16 (2)

  Abstract

  As Artificial Intelligence (AI) plays an increasingly prominent role in society, its application in clinical cardiology is gaining traction by providing innovative diagnostic, prognostic, and therapeutic solutions. Electrocardiogram (ECG), as a ubiquitous diagnostic tool in cardiology, has emerged as the leading data source for Deep Learning (DL) applications. A recent study from our group used ECG-based DL model to identify cardiac wall motion abnormalities and outperformed expert human interpretation. Motivated by this work and that of many others, we aim to discuss advances, limitations, future directions, and equity considerations in DL models for ECG-based AI applications.

  View details for PubMedID 40443717

• ConvexECG: Lightweight and Explainable Neural Networks for Personalized, Continuous Cardiac Monitoring Ansari, R., Cao, J., Bandyopadhyay, S., Narayan, S. M., Rogers, A. J., Pilanci, M., IEEE IEEE. 2025

  View details for DOI 10.1109/ICASSP49660.2025.10889573

  View details for Web of Science ID 001611517600350

• APRICOT-Mamba: Acuity Prediction in Intensive Care Unit (ICU): Development and Validation of a Stability, Transitions, and Life-Sustaining Therapies Prediction Model. Research square Contreras, M., Silva, B., Shickel, B., Davidson, A., Ozrazgat-Baslanti, T., Ren, Y., Guan, Z., Balch, J., Zhang, J., Bandyopadhyay, S., Loftus, T., Khezeli, K., Nerella, S., Bihorac, A., Rashidi, P. 2024

  Abstract

  On average, more than 5 million patients are admitted to intensive care units (ICUs) in the US, with mortality rates ranging from 10 to 29%. The acuity state of patients in the ICU can quickly change from stable to unstable, sometimes leading to life-threatening conditions. Early detection of deteriorating conditions can assist in more timely interventions and improved survival rates. While Artificial Intelligence (AI)-based models show potential for assessing acuity in a more granular and automated manner, they typically use mortality as a proxy of acuity in the ICU. Furthermore, these methods do not determine the acuity state of a patient (i.e., stable or unstable), the transition between acuity states, or the need for life-sustaining therapies. In this study, we propose APRICOT-M (Acuity Prediction in Intensive Care Unit-Mamba), a 1M-parameter state space-based neural network to predict acuity state, transitions, and the need for life-sustaining therapies in real-time among ICU patients. The model integrates ICU data in the preceding four hours (including vital signs, laboratory results, assessment scores, and medications) and patient characteristics (age, sex, race, and comorbidities) to predict the acuity outcomes in the next four hours. Our state space-based model can process sparse and irregularly sampled data without manual imputation, thus reducing the noise in input data and increasing inference speed. The model was trained on data from 107,473 patients (142,062 ICU admissions) from 55 hospitals between 2014-2017 and validated externally on data from 74,901 patients (101,356 ICU admissions) from 143 hospitals. Additionally, it was validated temporally on data from 12,927 patients (15,940 ICU admissions) from one hospital in 2018-2019 and prospectively on data from 215 patients (369 ICU admissions) from one hospital in 2021-2023. Three datasets were used for training and evaluation: the University of Florida Health (UFH) dataset, the electronic ICU Collaborative Research Database (eICU), and the Medical Information Mart for Intensive Care (MIMIC)-IV dataset. APRICOT-M significantly outperforms the baseline acuity assessment, Sequential Organ Failure Assessment (SOFA), for mortality prediction in both external (AUROC 0.95 CI: 0.94-0.95 compared to 0.78 CI: 0.78-0.79) and prospective (AUROC 0.99 CI: 0.97-1.00 compared to 0.80 CI: 0.65-0.92) cohorts, as well as for instability prediction (external AUROC 0.75 CI: 0.74-0.75 compared to 0.51 CI: 0.51-0.51, and prospective AUROC 0.69 CI: 0.64-0.74 compared to 0.53 CI: 0.50-0.57). This tool has the potential to help clinicians make timely interventions by predicting the transition between acuity states and decision-making on life-sustaining within the next four hours in the ICU.

  View details for DOI 10.21203/rs.3.rs-4790824/v1

  View details for PubMedID 39149454

• Developing a fair and interpretable representation of the clock drawing test for mitigating low education and racial bias. Scientific reports Zhang, J., Bandyopadhyay, S., Kimmet, F., Wittmayer, J., Khezeli, K., Libon, D. J., Price, C. C., Rashidi, P. 2024; 14 (1): 17444

  Abstract

  The clock drawing test (CDT) is a neuropsychological assessment tool to screen an individual's cognitive ability. In this study, we developed a Fair and Interpretable Representation of Clock drawing test (FaIRClocks) to evaluate and mitigate classification bias against people with less than 8 years of education, while screening their cognitive function using an array of neuropsychological measures. In this study, we represented clock drawings by a priorly published 10-dimensional deep learning feature set trained on publicly available data from the National Health and Aging Trends Study (NHATS). These embeddings were further fine-tuned with clocks from a preoperative cognitive screening program at the University of Florida to predict three cognitive scores: the Mini-Mental State Examination (MMSE) total score, an attention composite z-score (ATT-C), and a memory composite z-score (MEM-C). ATT-C and MEM-C scores were developed by averaging z-scores based on normative references. The cognitive screening classifiers were initially tested to see their relative performance in patients with low years of education (< = 8 years) versus patients with higher education (> 8 years) and race. Results indicated that the initial unweighted classifiers confounded lower education with cognitive compromise resulting in a 100% type I error rate for this group. Thereby, the samples were re-weighted using multiple fairness metrics to achieve sensitivity/specificity and positive/negative predictive value (PPV/NPV) balance across groups. In summary, we report the FaIRClocks model, with promise to help identify and mitigate bias against people with less than 8 years of education during preoperative cognitive screening.

  View details for DOI 10.1038/s41598-024-68481-w

  View details for PubMedID 39075127

  View details for PubMedCentralID 8402420

• Transformers and large language models in healthcare: A review. Artificial intelligence in medicine Nerella, S., Bandyopadhyay, S., Zhang, J., Contreras, M., Siegel, S., Bumin, A., Silva, B., Sena, J., Shickel, B., Bihorac, A., Khezeli, K., Rashidi, P. 2024; 154: 102900

  Abstract

  With Artificial Intelligence (AI) increasingly permeating various aspects of society, including healthcare, the adoption of the Transformers neural network architecture is rapidly changing many applications. Transformer is a type of deep learning architecture initially developed to solve general-purpose Natural Language Processing (NLP) tasks and has subsequently been adapted in many fields, including healthcare. In this survey paper, we provide an overview of how this architecture has been adopted to analyze various forms of healthcare data, including clinical NLP, medical imaging, structured Electronic Health Records (EHR), social media, bio-physiological signals, biomolecular sequences. Furthermore, which have also include the articles that used the transformer architecture for generating surgical instructions and predicting adverse outcomes after surgeries under the umbrella of critical care. Under diverse settings, these models have been used for clinical diagnosis, report generation, data reconstruction, and drug/protein synthesis. Finally, we also discuss the benefits and limitations of using transformers in healthcare and examine issues such as computational cost, model interpretability, fairness, alignment with human values, ethical implications, and environmental impact.

  View details for DOI 10.1016/j.artmed.2024.102900

  View details for PubMedID 38878555

• Wearable sensors in patient acuity assessment in critical care. Frontiers in neurology Sena, J., Mostafiz, M. T., Zhang, J., Davidson, A. E., Bandyopadhyay, S., Nerella, S., Ren, Y., Ozrazgat-Baslanti, T., Shickel, B., Loftus, T., Schwartz, W. R., Bihorac, A., Rashidi, P. 2024; 15: 1386728

  Abstract

  Acuity assessments are vital for timely interventions and fair resource allocation in critical care settings. Conventional acuity scoring systems heavily depend on subjective patient assessments, leaving room for implicit bias and errors. These assessments are often manual, time-consuming, intermittent, and challenging to interpret accurately, especially for healthcare providers. This risk of bias and error is likely most pronounced in time-constrained and high-stakes environments, such as critical care settings. Furthermore, such scores do not incorporate other information, such as patients' mobility level, which can indicate recovery or deterioration in the intensive care unit (ICU), especially at a granular level. We hypothesized that wearable sensor data could assist in assessing patient acuity granularly, especially in conjunction with clinical data from electronic health records (EHR). In this prospective study, we evaluated the impact of integrating mobility data collected from wrist-worn accelerometers with clinical data obtained from EHR for estimating acuity. Accelerometry data were collected from 87 patients wearing accelerometers on their wrists in an academic hospital setting. The data was evaluated using five deep neural network models: VGG, ResNet, MobileNet, SqueezeNet, and a custom Transformer network. These models outperformed a rule-based clinical score (Sequential Organ Failure Assessment, SOFA) used as a baseline when predicting acuity state (for ground truth we labeled as unstable patients if they needed life-supporting therapies, and as stable otherwise), particularly regarding the precision, sensitivity, and F1 score. The results demonstrate that integrating accelerometer data with demographics and clinical variables improves predictive performance compared to traditional scoring systems in healthcare. Deep learning models consistently outperformed the SOFA score baseline across various scenarios, showing notable enhancements in metrics such as the area under the receiver operating characteristic (ROC) Curve (AUC), precision, sensitivity, specificity, and F1 score. The most comprehensive scenario, leveraging accelerometer, demographics, and clinical data, achieved the highest AUC of 0.73, compared to 0.53 when using SOFA score as the baseline, with significant improvements in precision (0.80 vs. 0.23), specificity (0.79 vs. 0.73), and F1 score (0.77 vs. 0.66). This study demonstrates a novel approach beyond the simplistic differentiation between stable and unstable conditions. By incorporating mobility and comprehensive patient information, we distinguish between these states in critically ill patients and capture essential nuances in physiology and functional status. Unlike rudimentary definitions, such as equating low blood pressure with instability, our methodology delves deeper, offering a more holistic understanding and potentially valuable insights for acuity assessment.

  View details for DOI 10.3389/fneur.2024.1386728

  View details for PubMedID 38784909

  View details for PubMedCentralID PMC11112699