Confederated Machine Learning on Horizontally and Vertically Separated Medical Data for Large-Scale Health System Intelligence
This addresses privacy and regulatory barriers in healthcare by enabling model training on separated data, though it appears incremental as an extension of federated learning.
The paper tackled the problem of training machine learning models on medical data that is fragmented horizontally, vertically, and without patient ID matching, proposing confederated learning to stratify disease risk across large-scale health systems.
Health information is generally fragmented across silos. Though it is technically feasible to unite data for analysis in a manner that underpins a rapid learning healthcare system, privacy concerns and regulatory barriers limit data centralization. Machine learning can be conducted in a federated manner on patient datasets with the same set of variables, but separated across sites of care. But federated learning cannot handle the situation where different data types for a given patient are separated vertically across different organizations and when patient ID matching across different institutions is difficult. We call methods that enable machine learning model training on data separated by two or more degrees confederated machine learning. We proposed and evaluated a confederated learning to training machine learning model to stratify the risk of several diseases among when data are horizontally separated by individual, vertically separated by data type, and separated by identity without patient ID matching.