Exploring Ethics: Protecting Privacy While Sharing Biomedical Data for Machine Learning

Even though "de-identified," patient data can still sometimes be revealed by attackers. The focus of this program will include technical and policy measures that might better protect the privacy of electronic health records (EHRs) when they are used for machine learning. The approach to be discussed includes multivariate models computed in a decentralized fashion for a large clinical data research network, and how to collaborate in developing sound methods to protect patient privacy. Sharing according to patient instructions is one important way to conduct responsible machine learning. This presentation will include results from a recent study on patient-controlled electronic healthcare data sharing.