AI Reports · Stanford HAI · 2026-10-30 · Policy position
The Complexities of Race Adjustment in Health Algorithms | Stanford HAI
This policy brief examines the complexities of accounting for race in clinical algorithms that evaluate chronic kidney disease and their implications for health inequities. Using Stanford Health Care data on more than half a million patients from 2019 to 2023, it finds that a new algorithm no longer adjusting for race lowered kidney health estimates for Black or African American patients, placing them in more severe stages, with no meaningful change in nephrology referrals and visits. It concludes that technical fixes alone are insufficient to address deep-seated health inequities.