Identifying Undercompensated Groups Defined By Multiple Attributes in Risk Adjustment
share
Risk adjustment in health care aims to redistribute payments to insurers based on costs. However, risk adjustment formulas are known to underestimate costs for some groups of patients. This undercompensation makes these groups unprofitable to insurers and creates incentives for insurers to discriminate. We develop a machine learning method for "group importance" to identify unprofitable groups defined by multiple attributes, improving on the arbitrary nature of existing evaluations. This procedure was designed to evaluate the risk adjustment formulas used in the U.S. health insurance Marketplaces as well as Medicare, and we find a number of previously unidentified undercompensated groups. Our work provides policy makers with new information on potential targets of discrimination in the health care system and a path towards more equitable health coverage.
READ FULL TEXT