Ivan Lopez

All Publications

• TeleHelp Ukraine: A distributed international telemedicine response to the ongoing war. Journal of global health Narayan, A., Petryk, M., Savchuk, S., Villarino, K., Lopez, I., Morgun, E., Bakirova, A., Kamets, B., Le Tran, Q., Komzyuk, S., Kharbas, V., Asch, S., Pickering, A. 2024; 14: 04158

  Abstract

  Humanitarian crises frequently garner solidarity and robust volunteer recruitment among health care communities. However, a common obstacle is matching providers to those in need across geographic and other barriers. We examined the application of a decentralised governance strategy in establishing an emergency telemedicine response, TeleHelp Ukraine (THU).Using a case study approach, we explored how global networking and technological advancements empower organisations to generate, access, disseminate, and utilise knowledge for sustainable health care delivery.Preliminary results suggest that a non-profit, decentralised model strengthened by robust team dynamics may optimise the distribution of clinical workload and scheduling procedures. Institutional and cultural diversity among health care providers and volunteers fosters the mobilisation of knowledge resources, synergistic collaboration, and tailored care standards that align with both provider and patient expectations. By integrating these diverse, distributed networks, a synergistic effect is achieved, combining effective learning mechanisms with intellectual capital.Our study provides insights into the structure, implementation strategies, dissemination methodologies, and initial results of THU's operation. These findings may inform future emergency telemedicine responses in humanitarian scenarios, thereby reinforcing the practical implementation of health as a human right.

  View details for DOI 10.7189/jogh.14.04158

  View details for PubMedID 39451063

• Predictability of buprenorphine-naloxone treatment retention: A multi-site analysis combining electronic health records and machine learning. Addiction (Abingdon, England) Nateghi Haredasht, F., Fouladvand, S., Tate, S., Chan, M. M., Yeow, J. J., Griffiths, K., Lopez, I., Bertz, J. W., Miner, A. S., Hernandez-Boussard, T., Chen, C. A., Deng, H., Humphreys, K., Lembke, A., Vance, L. A., Chen, J. H. 2024

  Abstract

  Opioid use disorder (OUD) and opioid dependence lead to significant morbidity and mortality, yet treatment retention, crucial for the effectiveness of medications like buprenorphine-naloxone, remains unpredictable. Our objective was to determine the predictability of 6-month retention in buprenorphine-naloxone treatment using electronic health record (EHR) data from diverse clinical settings and to identify key predictors.This retrospective observational study developed and validated machine learning-based clinical risk prediction models using EHR data.Data were sourced from Stanford University's healthcare system and Holmusk's NeuroBlu database, reflecting a wide range of healthcare settings. The study analyzed 1800 Stanford and 7957 NeuroBlu treatment encounters from 2008 to 2023 and from 2003 to 2023, respectively.Predict continuous prescription of buprenorphine-naloxone for at least 6 months, without a gap of more than 30 days. The performance of machine learning prediction models was assessed by area under receiver operating characteristic (ROC-AUC) analysis as well as precision, recall and calibration. To further validate our approach's clinical applicability, we conducted two secondary analyses: a time-to-event analysis on a single site to estimate the duration of buprenorphine-naloxone treatment continuity evaluated by the C-index and a comparative evaluation against predictions made by three human clinical experts.Attrition rates at 6 months were 58% (NeuroBlu) and 61% (Stanford). Prediction models trained and internally validated on NeuroBlu data achieved ROC-AUCs up to 75.8 (95% confidence interval [CI] = 73.6-78.0). Addiction medicine specialists' predictions show a ROC-AUC of 67.8 (95% CI = 50.4-85.2). Time-to-event analysis on Stanford data indicated a median treatment retention time of 65 days, with random survival forest model achieving an average C-index of 65.9. The top predictor of treatment retention identified included the diagnosis of opioid dependence.US patients with opioid use disorder or opioid dependence treated with buprenorphine-naloxone prescriptions appear to have a high (∼60%) treatment attrition by 6 months. Machine learning models trained on diverse electronic health record datasets appear to be able to predict treatment continuity with accuracy comparable to that of clinical experts.

  View details for DOI 10.1111/add.16587

  View details for PubMedID 38923168

• Impact of Supine versus Prone Positioning on Segmental Lumbar Lordosis in Patients Undergoing ALIF Followed by PSF: A Comparative Study. Journal of clinical medicine Sadeghzadeh, S., Yoo, K. H., Lopez, I., Johnstone, T., Schonfeld, E., Haider, G., Marianayagam, N. J., Stienen, M. N., Veeravagu, A. 2024; 13 (12)

  Abstract

  Background: Anterior lumbar interbody fusion (ALIF) and posterior spinal fusion (PSF) play pivotal roles in restoring lumbar lordosis in spinal surgery. There is an ongoing debate between combined single-position surgery and traditional prone-position PSF for optimizing segmental lumbar lordosis. Methods: This retrospective study analyzed 59 patients who underwent ALIF in the supine position followed by PSF in the prone position at a single institution. Cobb angles were measured preoperatively, post-ALIF, and post-PSF using X-ray imaging. One-way repeated measures ANOVA and post-hoc analyses with Bonferroni adjustment were employed to compare mean Cobb angles at different time points. Cohen's d effect sizes were calculated to assess the magnitude of changes. Sample size calculations were performed to ensure statistical power. Results: The mean segmental Cobb angle significantly increased from preoperative (32.2 ± 13.8 degrees) to post-ALIF (42.2 ± 14.3 degrees, Cohen's d: -0.71, p < 0.0001) and post-PSF (43.6 ± 14.6 degrees, Cohen's d: -0.80, p < 0.0001). There was no significant difference between Cobb angles after ALIF and after PSF (Cohen's d: -0.10, p = 0.14). The findings remained consistent when Cobb angles were analyzed separately for single-screw and double-screw ALIF constructs. Conclusions: Both supine ALIF and prone PSF significantly increased segmental lumbar lordosis compared to preoperative measurements. The negligible difference between post-ALIF and post-PSF lordosis suggests that supine ALIF followed by prone PSF can be an effective approach, providing flexibility in surgical positioning without compromising lordosis improvement.

  View details for DOI 10.3390/jcm13123555

  View details for PubMedID 38930084

• Single-cell transcriptomic atlas reveals increased regeneration in diseased human inner ear balance organs. Nature communications Wang, T., Ling, A. H., Billings, S. E., Hosseini, D. K., Vaisbuch, Y., Kim, G. S., Atkinson, P. J., Sayyid, Z. N., Aaron, K. A., Wagh, D., Pham, N., Scheibinger, M., Zhou, R., Ishiyama, A., Moore, L. S., Maria, P. S., Blevins, N. H., Jackler, R. K., Alyono, J. C., Kveton, J., Navaratnam, D., Heller, S., Lopez, I. A., Grillet, N., Jan, T. A., Cheng, A. G. 2024; 15 (1): 4833

  Abstract

  Mammalian inner ear hair cell loss leads to permanent hearing and balance dysfunction. In contrast to the cochlea, vestibular hair cells of the murine utricle have some regenerative capacity. Whether human utricular hair cells regenerate in vivo remains unknown. Here we procured live, mature utricles from organ donors and vestibular schwannoma patients, and present a validated single-cell transcriptomic atlas at unprecedented resolution. We describe markers of 13 sensory and non-sensory cell types, with partial overlap and correlation between transcriptomes of human and mouse hair cells and supporting cells. We further uncover transcriptomes unique to hair cell precursors, which are unexpectedly 14-fold more abundant in vestibular schwannoma utricles, demonstrating the existence of ongoing regeneration in humans. Lastly, supporting cell-to-hair cell trajectory analysis revealed 5 distinct patterns of dynamic gene expression and associated pathways, including Wnt and IGF-1 signaling. Our dataset constitutes a foundational resource, accessible via a web-based interface, serving to advance knowledge of the normal and diseased human inner ear.

  View details for DOI 10.1038/s41467-024-48491-y

  View details for PubMedID 38844821

• Extraction of Unstructured Electronic Health Records to Evaluate Glioblastoma Treatment Patterns. JCO clinical cancer informatics Swaminathan, A., Ren, A. L., Wu, J. Y., Bhargava-Shah, A., Lopez, I., Srivastava, U., Alexopoulos, V., Pizzitola, R., Bui, B., Alkhani, L., Lee, S., Mohit, N., Seo, N., Macedo, N., Cheng, W., Wang, W., Tran, E., Thomas, R., Gevaert, O. 2024; 8: e2300091

  Abstract

  Data on lines of therapy (LOTs) for cancer treatment are important for clinical oncology research, but LOTs are not explicitly recorded in electronic health records (EHRs). We present an efficient approach for clinical data abstraction and a flexible algorithm to derive LOTs from EHR-based medication data on patients with glioblastoma multiforme (GBM).Nonclinicians were trained to abstract the diagnosis of GBM from EHRs, and their accuracy was compared with abstraction performed by clinicians. The resulting data were used to build a cohort of patients with confirmed GBM diagnosis. An algorithm was developed to derive LOTs using structured medication data, accounting for the addition and discontinuation of therapies and drug class. Descriptive statistics were calculated and time-to-next-treatment (TTNT) analysis was performed using the Kaplan-Meier method.Treating clinicians as the gold standard, nonclinicians abstracted GBM diagnosis with a sensitivity of 0.98, specificity 1.00, positive predictive value 1.00, and negative predictive value 0.90, suggesting that nonclinician abstraction of GBM diagnosis was comparable with clinician abstraction. Of 693 patients with a confirmed diagnosis of GBM, 246 patients contained structured information about the types of medications received. Of them, 165 (67.1%) received a first-line therapy (1L) of temozolomide, and the median TTNT from the start of 1L was 179 days.We described a workflow for extracting diagnosis of GBM and LOT from EHR data that combines nonclinician abstraction with algorithmic processing, demonstrating comparable accuracy with clinician abstraction and highlighting the potential for scalable and efficient EHR-based oncology research.

  View details for DOI 10.1200/CCI.23.00091

  View details for PubMedID 38857465

• Electronic Phenotyping of Urinary Tract Infections as a Silver Standard Label for Machine Learning. AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Ma, S. P., Hosgur, E., Corbin, C. K., Lopez, I., Chang, A., Chen, J. H. 2024; 2024: 182-189

  Abstract

  This study explored the efficacy of electronic phenotyping in data labeling for machine learning with a focus on urinary tract infections (UTIs). We contrasted labels from electronic phenotyping against previously published labels such as urine culture positivity. In comparison, electronic phenotyping showed the potential to enhance specificity in UTI labeling while maintaining similar sensitivity and was easily scaled for application to a large dataset suitable for machine learning, which we used to train and validate a machine learning model. Electronic phenotyping offers a valuable method for machine learning label generation in healthcare, with potential benefits for patient care and antimicrobial stewardship. Further research will expand its application and optimize techniques for increased performance.

  View details for PubMedID 38827068

  View details for PubMedCentralID PMC11141812

• Clinical use of polygenic risk scores for detection of peripheral artery disease and cardiovascular events. PloS one Omiye, J. A., Ghanzouri, I., Lopez, I., Wang, F., Cabot, J., Amal, S., Ye, J., Lopez, N. G., Adebayo-Tijani, F., Ross, E. G. 2024; 19 (5): e0303610

  Abstract

  We have previously shown that polygenic risk scores (PRS) can improve risk stratification of peripheral artery disease (PAD) in a large, retrospective cohort. Here, we evaluate the potential of PRS in improving the detection of PAD and prediction of major adverse cardiovascular and cerebrovascular events (MACCE) and adverse events (AE) in an institutional patient cohort. We created a cohort of 278 patients (52 cases and 226 controls) and fit a PAD-specific PRS based on the weighted sum of risk alleles. We built traditional clinical risk models and machine learning (ML) models using clinical and genetic variables to detect PAD, MACCE, and AE. The models' performances were measured using the area under the curve (AUC), net reclassification index (NRI), integrated discrimination improvement (IDI), and Brier score. We also evaluated the clinical utility of our PAD model using decision curve analysis (DCA). We found a modest, but not statistically significant improvement in the PAD detection model's performance with the inclusion of PRS from 0.902 (95% CI: 0.846-0.957) (clinical variables only) to 0.909 (95% CI: 0.856-0.961) (clinical variables with PRS). The PRS inclusion significantly improved risk re-classification of PAD with an NRI of 0.07 (95% CI: 0.002-0.137), p = 0.04. For our ML model predicting MACCE, the addition of PRS did not significantly improve the AUC, however, NRI analysis demonstrated significant improvement in risk re-classification (p = 2e-05). Decision curve analysis showed higher net benefit of our combined PRS-clinical model across all thresholds of PAD detection. Including PRS to a clinical PAD-risk model was associated with improvement in risk stratification and clinical utility, although we did not see a significant change in AUC. This result underscores the potential clinical utility of incorporating PRS data into clinical risk models for prevalent PAD and the need for use of evaluation metrics that can discern the clinical impact of using new biomarkers in smaller populations.

  View details for DOI 10.1371/journal.pone.0303610

  View details for PubMedID 38758931

• Extracellular release of mitochondria induced by pre-hematopoietic stem cell transplant conditioning exacerbates GVHD. Blood advances Vijayan, V., Yan, H., Lohmeyer, J. K., Prentiss, K. A., Patil, R. V., Barbarito, G., Lopez, I., Elezaby, A., Peterson, K., Baker, J., Ostberg, N. P., Bertaina, A., Negrin, R. S., Mochly-Rosen, D., Weinberg, K. I., Haileselassie, B. 2024

  Abstract

  Despite therapeutic advancements, GVHD is a major complication of HSCT. In current models of GVHD, tissue injury induced by cytotoxic conditioning regimens, along with translocation of microbes expressing Pathogen Associated Molecular Patterns (PAMPs), result in activation of host antigen-presenting cells (APC) to stimulate alloreactive donor T lymphocytes. Recent studies have demonstrated that in many pathologic states, tissue injury results in the release of mitochondria from the cytoplasm to the extracellular space. We hypothesized that extracellular mitochondria, which are related to archaebacteria, could also trigger GVHD by stimulation of host APC. We found that clinically relevant doses of radiation or busulfan induced extracellular release of mitochondria by various cell types, including cultured intestinal epithelial cells. Conditioning-mediated mitochondrial release was associated with mitochondrial damage and impaired quality control but did not affect the viability of the cells. Extracellular mitochondria directly stimulated host APCs to express higher levels of MHC-II, co-stimulatory CD86, and pro-inflammatory cytokines, resulting in increased donor T cell activation, and proliferation in mixed lymphocyte reactions. Analyses of plasma from both experimental mice and a cohort of children undergoing HSCT demonstrated that conditioning induced extracellular mitochondrial release in vivo. In mice undergoing MHC mismatched HSCT, administration of purified syngeneic extracellular mitochondria increased host APC activation and exacerbated GVHD. Our data suggests that pre-HSCT conditioning results in extracellular release of damaged mitochondria which increase alloreactivity and exacerbate GVHD. Therefore, decreasing the extracellular release of damaged mitochondria following conditioning could serve as a novel strategy for GVHD prevention.

  View details for DOI 10.1182/bloodadvances.2023012328

  View details for PubMedID 38701354

• Experience with the utilization of new-generation shared-control robotic system for spinal instrumentation. Journal of neurosurgical sciences Haider, G., Shah, V., Lopez, I., Wagner, K. E., Stienen, M. N., Veeravagu, A. 2024

  Abstract

  Robotic assistance in spine surgery is emerging as an accurate, effective and enabling technology utilized in the treatment of patients with surgical spinal pathology. The safety and reproducibility of robotic assistance in the placement of pedicle screw instrumentation is still being investigated. The objective of this study was to present our experience of instrumented spinal fusion utilizing an intraoperative robotic guidance system.We retrospectively reviewed all cases of spinal instrumentation of the thoracic and lumbo-sacral spine using the Mazor X robotic system (Medtronic Inc, Minneapolis, MN, USA), performed at our institution by one surgeon between July 2017 and June 2020. Wilcoxon Rank test was used to compare time taken to place each screw during the first 20 cases and the cases thereafter.A total of 28 patients were included. A total of 159 screws were placed using the Mazor X robotic system. The overall mean time for screw placement was 7.8±2.3 minutes and there was a significant reduction in the mean time for screw placement after the 20th case or 120 screws (8.70 vs. 5.42 min, P=0.008). No postoperative neurologic deficit or new radiculopathy was noted to occur secondary to hardware placement. No revision surgery was required for replacement or removal of a mispositioned screw.From this single-center, single-surgeon series we conclude that robot-assisted spine surgery can be safely and efficiently integrated into the operating room workflow, which improves after a learning curve of approximately 20 operative interventions. We found robot-assisted spinal instrumentation to be reliable, safe, effective and highly precise.

  View details for DOI 10.23736/S0390-5616.24.06206-4

  View details for PubMedID 38619188

• Natural language processing system for rapid detection and intervention of mental health crisis chat messages. NPJ digital medicine Swaminathan, A., Lopez, I., Mar, R. A., Heist, T., McClintock, T., Caoili, K., Grace, M., Rubashkin, M., Boggs, M. N., Chen, J. H., Gevaert, O., Mou, D., Nock, M. K. 2023; 6 (1): 213

  Abstract

  Patients experiencing mental health crises often seek help through messaging-based platforms, but may face long wait times due to limited message triage capacity. Here we build and deploy a machine-learning-enabled system to improve response times to crisis messages in a large, national telehealth provider network. We train a two-stage natural language processing (NLP) system with key word filtering followed by logistic regression on 721 electronic medical record chat messages, of which 32% are potential crises (suicidal/homicidal ideation, domestic violence, or non-suicidal self-injury). Model performance is evaluated on a retrospective test set (4/1/21-4/1/22, N=481) and a prospective test set (10/1/22-10/31/22, N=102,471). In the retrospective test set, the model has an AUC of 0.82 (95% CI: 0.78-0.86), sensitivity of 0.99 (95% CI: 0.96-1.00), and PPV of 0.35 (95% CI: 0.309-0.4). In the prospective test set, the model has an AUC of 0.98 (95% CI: 0.966-0.984), sensitivity of 0.98 (95% CI: 0.96-0.99), and PPV of 0.66 (95% CI: 0.626-0.692). The daily median time from message receipt to crisis specialist triage ranges from 8 to 13min, compared to 9h before the deployment of the system. We demonstrate that a NLP-based machine learning model can reliably identify potential crisis chat messages in a telehealth setting. Our system integrates into existing clinical workflows, suggesting that with appropriate training, humans can successfully leverage ML systems to facilitate triage of crisis messages.

  View details for DOI 10.1038/s41746-023-00951-3

  View details for PubMedID 37990134

• Altered profiles of extracellular mitochondrial DNA in immunoparalyzed pediatric patients after thermal injury. Shock (Augusta, Ga.) Tetri, L. H., Penatzer, J. A., Tsegay, K. B., Tawfik, D. S., Burk, S., Lopez, I., Thakkar, R. K., Haileselassie, B. 2023

  Abstract

  Thermal injury is a major cause of morbidity and mortality in the pediatric population world-wide with secondary infection being the most common acute complication. Suppression of innate and adaptive immune function is predictive of infection in pediatric burn patients, but little is known about the mechanisms causing these effects. Circulating mtDNA which induces a proinflammatory signal, has been described in multiple disease states, but has not been studied in pediatric burn injuries. This study examined the quantity of circulating mtDNA and mtDNA mutations in immunocompetent (IC) and immunoparalyzed (IP) pediatric burn patients.Circulating DNA was isolated from plasma of pediatric burn patients treated at Nationwide Children's Hospital Burn Center at early (1-3 days) and late (4-7 days) time points post-injury. These patients were categorized as IP or IC based on previously established immune function testing and secondary infection. Three mitochondrial genes, D loop, ND1, and ND4, were quantified by multiplexed qPCR to assess both mtDNA quantity and mutation load.At the early timepoint, there were no differences in plasma mtDNA quantity, however IC patients had a progressive increase in mtDNA over time when compared to IP patients (change in ND1 copy number over time 3880 vs 87 copies/day, p = 0.0004). Conversely, the IP group had an increase in mtDNA mutation burden over time.IC patients experienced a significant increase in circulating mtDNA quantity over time, demonstrating an association between increased mtDNA release, and proinflammatory phenotype in the burn patients. IP patients had significant increases in mtDNA mutation load likely representative of degree of oxidative damage. Together, these data provide further insight into the inflammatory and immunological mechanisms following pediatric thermal injury.

  View details for DOI 10.1097/SHK.0000000000002253

  View details for PubMedID 38010095

• Extracellular Release of Damaged Mitochondria Induced By Cytotoxic Conditioning Exacerbates Graft-Versus-Host Disease Vijayan, V., Yan, H., Lohmeyer, J., Prentiss, K., Patil, R., Barbarito, G., Lopez, I., Elezaby, A., Peterson, K., Baker, J., Ostberg, N., Bertaina, A., Negrin, R. S., Mochly-Rosen, D., Weinberg, K. I., Haileselassie, B. AMER SOC HEMATOLOGY. 2023

  View details for DOI 10.1182/blood-2023-179456

  View details for Web of Science ID 001159306708024

• Selective prediction for extracting unstructured clinical data. Journal of the American Medical Informatics Association : JAMIA Swaminathan, A., Lopez, I., Wang, W., Srivastava, U., Tran, E., Bhargava-Shah, A., Wu, J. Y., Ren, A. L., Caoili, K., Bui, B., Alkhani, L., Lee, S., Mohit, N., Seo, N., Macedo, N., Cheng, W., Liu, C., Thomas, R., Chen, J. H., Gevaert, O. 2023

  Abstract

  While there are currently approaches to handle unstructured clinical data, such as manual abstraction and structured proxy variables, these methods may be time-consuming, not scalable, and imprecise. This article aims to determine whether selective prediction, which gives a model the option to abstain from generating a prediction, can improve the accuracy and efficiency of unstructured clinical data abstraction.We trained selective classifiers (logistic regression, random forest, support vector machine) to extract 5 variables from clinical notes: depression (n = 1563), glioblastoma (GBM, n = 659), rectal adenocarcinoma (DRA, n = 601), and abdominoperineal resection (APR, n = 601) and low anterior resection (LAR, n = 601) of adenocarcinoma. We varied the cost of false positives (FP), false negatives (FN), and abstained notes and measured total misclassification cost.The depression selective classifiers abstained on anywhere from 0% to 97% of notes, and the change in total misclassification cost ranged from -58% to 9%. Selective classifiers abstained on 5%-43% of notes across the GBM and colorectal cancer models. The GBM selective classifier abstained on 43% of notes, which led to improvements in sensitivity (0.94 to 0.96), specificity (0.79 to 0.96), PPV (0.89 to 0.98), and NPV (0.88 to 0.91) when compared to a non-selective classifier and when compared to structured proxy variables.We showed that selective classifiers outperformed both non-selective classifiers and structured proxy variables for extracting data from unstructured clinical notes.Selective prediction should be considered when abstaining is preferable to making an incorrect prediction.

  View details for DOI 10.1093/jamia/ocad182

  View details for PubMedID 37769323

• Critically reading machine learning literature in neurosurgery: a reader's guide and checklist for appraising prediction models. Neurosurgical focus Emani, S., Swaminathan, A., Grobman, B., Duvall, J. B., Lopez, I., Arnaout, O., Huang, K. T. 2023; 54 (6): E3

  Abstract

  OBJECTIVE: Machine learning (ML) has become an increasingly popular tool for use in neurosurgical research. The number of publications and interest in the field have recently seen significant expansion in both quantity and complexity. However, this also places a commensurate burden on the general neurosurgical readership to appraise this literature and decide if these algorithms can be effectively translated into practice. To this end, the authors sought to review the burgeoning neurosurgical ML literature and to develop a checklist to help readers critically review and digest this work.METHODS: The authors performed a literature search of recent ML papers in the PubMed database with the terms "neurosurgery" AND "machine learning," with additional modifiers "trauma," "cancer," "pediatric," and "spine" also used to ensure a diverse selection of relevant papers within the field. Papers were reviewed for their ML methodology, including the formulation of the clinical problem, data acquisition, data preprocessing, model development, model validation, model performance, and model deployment.RESULTS: The resulting checklist consists of 14 key questions for critically appraising ML models and development techniques; these are organized according to their timing along the standard ML workflow. In addition, the authors provide an overview of the ML development process, as well as a review of key terms, models, and concepts referenced in the literature.CONCLUSIONS: ML is poised to become an increasingly important part of neurosurgical research and clinical care. The authors hope that dissemination of education on ML techniques will help neurosurgeons to critically review new research better and more effectively integrate this technology into their practices.

  View details for DOI 10.3171/2023.3.FOCUS2352

  View details for PubMedID 37283326

• Predicting premature discontinuation of medication for opioid use disorder from electronic medical records. AMIA ... Annual Symposium proceedings. AMIA Symposium Lopez, I., Fouladvand, S., Kollins, S., Chen, C. A., Bertz, J., Hernandez-Boussard, T., Lembke, A., Humphreys, K., Miner, A. S., Chen, J. H. 2023; 2023: 1067-1076

  Abstract

  Medications such as buprenorphine-naloxone are among the most effective treatments for opioid use disorder, but limited retention in treatment limits long-term outcomes. In this study, we assess the feasibility of a machine learning model to predict retention vs. attrition in medication for opioid use disorder (MOUD) treatment using electronic medical record data including concepts extracted from clinical notes. A logistic regression classifier was trained on 374 MOUD treatments with 68% resulting in potential attrition. On a held-out test set of 157 events, the full model achieved an area under the receiver operating characteristic curve (AUROC) of 0.77 (95% CI: 0.64-0.90) and AUROC of 0.74 (95% CI: 0.62-0.87) with a limited model using only structured EMR data. Risk prediction for opioid MOUD retention vs. attrition is feasible given electronic medical record data, even without necessarily incorporating concepts extracted from clinical notes.

  View details for PubMedID 38222349

  View details for PubMedCentralID PMC10785878

• Predictive Value of Clinical Complete Response after Chemoradiation for Rectal Cancer Liu, C., Boncompagni, A. A., Perrone, K., Agarwal, A., Hur, D. G., Lopez, I., Sheth, V., Morris, A. M. LIPPINCOTT WILLIAMS & WILKINS. 2022: S51-S52

  View details for DOI 10.1097/01.XCS.0000893308.54894.46

  View details for Web of Science ID 000867889300080