Using Physician Behavioral Big Data for High Precision Fraud Prediction and Detections

Using existing data from a variety of public sources, this project will involve constructing a database to identify physician behavioral factors (illegal behavior, patient complaints and malpractice, disciplinary actions, conspicuous consumption, and life stressors) that predict engagement in health care fraud. Data sources include federal databases on fraud, as well as state and local court records, state medical records, and online review web sites. The project will use retrospective matched design that includes a sample of physicians assigned to one of two groups: those who have and have not been excluded from participation in federal health care programs, such as Medicare, due to fraud, from 2015-2019.

"Note: This project contains a research and/or development component, as defined in applicable law," and complies with Part 200 Uniform Requirements - 2 CFR 200.210(a)(14). CA/NCF