About
Jeremy Weiss, PhD, MD
Tenure Track Investigator, Computational Health Research Branch, LHNCBCMy research focuses on advancing machine learning methods in clinical data science to improve clinical prediction in internal medicine and critical care settings, with applications in opioid abuse, spesis, and COVID-19.
Contact Information
Building 38A, 8600 Rockville Pike MSC 6075 Bethesda, MD 20894
Tel: 301-496-8409
Research Interests
I lead the Care Health and Reasoning Machines lab to advance machine learning methods in clinical data science. Our lab focuses on improving clinical prediction in internal medicine and critical care settings, with applications in opioid abuse, sepsis, and COVID-19. We develop longitudinal models to analyze electronic health records as their collection mechanisms necessitate advanced analytics for appropriate use and interpretation.
Our lab advances improving and validating risk scores, individualizing treatment recommendations, and promoting analytics-based medicine. My work on survival models from observational, longitudinal data have been included in leading machine learning and medical informatics publications from Neural Information Processing Systems (NeurIPS), the Association for the Advancement of Artificial Intelligence, the American Medical Informatics Association, and the Journal of the American Medical Association. I also review manuscripts across machine learning and clinical venues with top reviewer awards at NeurIPS and the Annals of Internal Medicine.
Google Scholar publication list
Publications Zhang W, Weiss JC. Longitudinal fairness with censorship. Association for the Advancement of Artificial Intelligence (AAAI), 2022.Zhou H, Cheng C, Shields KJ, Kochhar G, Cheema T, Lipton ZC, Weiss JC. Learning clinical concepts for predicting risk of progression to severe COVID-19. To appear in American Medical Informatics Association (AMIA) Annual Symposium, 2022.
Kim J, Weiss JC, Ravikumar P. Context-sensitive spelling correction of clinical text via conditional independence. Conference of Health, Inference, and Learning (CHIL), Proceedings of Machine Learning Research (PMLR), 2022.
Lo-Ciganic WH, et al. Developing and validating a machine-learning algorithm to predict opioid overdose among Medicaid beneficiaries in two US states: a prognostic modeling study. Lancet Digital Health, 2022.
Reinhart A, et al. ”An open repository of real-time COVID-19 indicators.” Proceedings of the National Academy of Sciences (PNAS) of the United States of America, 118.51, 2021.
Weiss JC. TL-Lite: Temporal visualization and learning for clinical forecasting. In Machine Learning for Health, Proceedings of Machine Learning Research (PMLR), 2020.