Grand Rounds

The inaugural ENACT Grand Rounds seminar on March 24, 2025, will feature Shyam Visweswaran, MD, PhD, Professor and Vice Chair of Clinical Informatics in the Department of Biomedical Informatics at the University of Pittsburgh, and Olga V. Kravchenko, MS, PhD, Assistant Professor in the Department of Family Medicine at the University of Pittsburgh. Dr. Visweswaran and Dr. Kravchenko will present ENACT’s pioneering postpartum hemorrhage (PPH) study, which exemplifies ENACT’s ability to generate insights from multi-site data, showcasing a stepwise journey from initial hypotheses to advanced predictive modeling. By analyzing data from 22 ENACT sites and over 1.2 million unique delivery hospitalizations (2005–2022), researchers uncovered troubling trends in PPH incidence and comorbidity burdens. Using ENACT enclaves and synthetic datasets, the team developed a machine learning (XGBoost) model incorporating 15 risk factors to predict PPH, demonstrating improved performance when combining data across multiple sites. Attendees will learn how ENACT’s secure, collaborative tools can be applied to solve complex healthcare challenges, advancing clinical decision-making.

Precision Phenotyping in ENACT for Curated Cohorts of Unexplained Chronic Conditions With advances in AI and increasing computational capabilities, electronic phenotyping is evolving into precision phenotyping -- where multi-modal frameworks define phenotypes in a more personalized manner using electronic health record (EHR) data. The ENACT network supports this shift by providing interoperable informatics infrastructure for distributed learning and algorithm deployment. This presentation explores how precision phenotyping algorithms within ENACT can be applied to curate highly specific research cohorts for complex, unexplained chronic conditions. By integrating algorithmic precision and collaborative infrastructure, this approach offers new avenues for targeted clinical studies and advances in translational research. Presenter: Hossein Estiri, PhD, is an Associate Professor of Medicine at Harvard Medical School and an Investigator at Massachusetts General Hospital, where he leads the Clinical Augmented Intelligence Group (CLAI). He also serves as the Head of AI Research at the Center for AI and Biomedical Informatics of the Learning Healthcare System (CAIBILS) at Mass General Brigham. Dr. Estiri’s research is at the intersection of biomedical informatics, machine learning, and population health, with a particular focus on modeling complex phenotypes from electronic health records (EHRs). His work aims to advance precision medicine by developing computational frameworks that uncover nuanced patterns in clinical data, enabling more accurate phenotyping and improved cohort discovery for translational research and clinical trials.