Even "de-identified," patient data can be revealed by attackers. Lucila Ohno-Machado, MD, MBA, PhD discusses the technical and policy measures that might better protect the privacy of electronic health records (EHRs) when they are used for machine learning. Hear about approaches that use multivariate models computed in a decentralized fashion for a large clinical data research network and collaboration in developing sound methods to protect patient privacy. (#36272)