News & Events

The integration and analysis of electronic health record (EHR) data across institutions present both significant challenges and transformative opportunities for biomedical research. This talk outlines the development and application of federated data networks such as I2B2 and SHRINE, which enable real-time, privacy-preserving queries across distributed EHR systems. These platforms support large-scale cohort discovery and have been instrumental in initiatives like the EnACT network and the COVID-19-focused 4CE consortium. In contrast, centralized repositories like the NIH’s N3C and Epic’s Cosmos database offer comprehensive datasets conducive to machine learning but may obscure site-specific variability. 

The All of Us Research Program, a flagship initiative of the NIH, aims to build one of the most comprehensive and diverse biomedical data resources in the world by enrolling over one million participants across the United States. Dr. Jordan Smoller, a lead investigator in the program, outlines its structure, scope, and transformative potential for advancing precision medicine. With over 850,000 participants enrolled and more than 630,000 contributing data, the program integrates electronic health records (EHRs), genomic data, physical measurements, surveys, and wearable device data. 

As machine learning (ML) becomes increasingly integrated into healthcare, ensuring ethical, fair, and robust deployment is critical. Dr. Marzyeh Ghassemi and the Healthy ML Lab at MIT investigate the challenges and opportunities of applying ML in clinical settings, with a focus on fairness, privacy, and real-world impact. Through case studies in medical imaging and clinical prediction, her work highlights how models trained on large datasets can exhibit significant disparities in performance across demographic subgroups, including age, race, gender, and insurance status.