Abstract Body: With increasing availability of electronic health data from EHRs, there has been expanding interest in using this data to identify populations for targeted health interventions. With a small proportion of patients using a majority of healthcare resources, the potential benefit of predicting high cost patients is clear, though early efforts have delivered few gains. In this presentation, I present work done to evaluate how well high cost patient records contain information that may be predictive, and the nature of that information.


Adam Wilcox (Presenter)
University of Washington