Algorithms to Improve Fairness in Medicare Risk Adjustment

Is use of modern algorithms associated with improved group-level fairness while maintaining overall performance in Medicare risk adjustment?In this diagnostic study including 4.4 million Medicare beneficiaries of Medicare risk adjustment algorithms, constrained regression and postprocessing both achieved fair spending targets for minoritized racial and ethnic groups without compromising overall payment system fit.These findings suggest that feasible extensions of the current risk adjustment algorithm can yield additional payments for minoritized racial and ethnic groups in Medicare.

Corresponding Author: Marissa B. Reitsma, PhD, Stanford University, 615 Crothers Way, Encina Commons, Stanford, CA 94305 (mreitsma@stanford.edu).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.