Predicting Clinical Outcomes Across Changing Electronic Health Record Systems
Jen Gong (MIT);Tristan Naumann (MIT);Peter Szolovits (MIT);John Guttag (MIT)
Existing machine learning methods typically assume consistency in how information is encoded. However, the way information is recorded in databases differs across institutions and over time, rendering potentially useful data obsolescent. To address this problem, we map database-specific representations of information to a common set of semantic concepts, thus allowing models to transition across different databases.