skip to Main Content

Machine Learning Applied to EHR Data as a Means of Improving Biosurveillance and Diagnostic Excellence: A Pilot Project

We aim to develop and extend methods of probabilistic modeling of temporal electronic health record (EHR) data, using non-stationary Gaussian processes, hidden Markov models, and composite mixture models, to identify opportunities to conduct clinical biosurveillance and to achieve diagnostic excellence. Building off collaboration between KP DOR and the Lawrence Livermore National Laboratory, this proposal will use population-level EHR data, AI/ML methods and advanced computing to evaluate associations between health system diagnostic testing/treatment and prevalent/incident health conditions and to identify areas of potential diagnostic uncertainty.

Investigator: Liu, Vincent

Explore all studies and publications

Back To Top