Federated Learning for Electronic Health Records

In data-driven medical research, multi-center studies have long been preferred over single-center ones due to a single institute sometimes not having enough data obtain sufficient statistical power for certain hypothesis testings as well predictive and subgroup studies. The wide adoption of electronic health records (EHRs) has made multi-institutional collaboration much more feasible. However, concerns infrastructures, regulations, privacy, standardization present challenge sharing across healthcare institutions. Federated Learning (FL), which allows multiple sites collaboratively train global model without directly data, become promising paradigm break the isolation. this study, we surveyed existing works on FL applications in EHRs evaluated performance current state-of-the-art algorithms two EHR machine learning tasks significant clinical importance real world dataset.