The Clinical Excellence Research Center is exploring applications of machine learning to electronic health record data and to administrative claims data. These efforts use machine learning to provide powerful insights like the identification of patients likely to incur high medical costs in future time periods.
Projects and Outcomes
CERC conducted a population-based study of newly high-cost patients using the Danish national database. We used machine learning to predict future high-cost patients by identifying those whose costs will "bloom" within 12 months. Our analysis found that we improved positive predictive power by more than 30%, compared with standard risk-stratification tools.
Publications and News
- – Nature Digital Medicine
Machine learning and atherosclerotic cardiovascular disease risk prediction in a multi-ethnic population
Machine learning (ML) algorithms present an opportunity to develop improved and more generalizable risk prediction models. By leveraging large-scale data—from electronic health records (EHRs), for instance—such algorithms can determine combinations of variables that reliably predict an outcome.
- – Nature Medicine
Estimate the hidden deployment cost of predictive models to improve patient care
Although examples of algorithms designed to improve healthcare delivery abound, for many, clinical integration will not be achieved. The deployment cost of machine learning models is an underappreciated barrier to success. Experts propose three criteria that, assessed early, could help estimate the deployment cost.