Incorporating Race in Clinical Algorithms—A Response
By
James A. Diao
Emma Pierson
October 1, 2026
Clinical Scorecard: Incorporating Race in Clinical Algorithms—A Response
At a Glance
Category Detail
Condition Clinical Algorithm Design
Key Mechanisms Incorporation of patient preferences, accuracy, equity, and outcomes in algorithm design.
Target Population Patients affected by health disparities.
Care Setting Clinical research and algorithm development.
Key Highlights
Patient preferences are a key consideration in algorithm design. Concerns exist regarding the incorporation of race into clinical algorithms. Race-neutral approaches are favored when performance is comparable. Comparative assessment of race-aware versus race-neutral algorithms is necessary. Race often serves as a proxy for unmeasured factors in algorithms.
Guideline-Based Recommendations
Diagnosis
Evaluate the methodological rigor in developing clinical algorithms.
Management
Consider systemic measures beyond computational modifications for race removal.
Monitoring & Follow-up
Assess the consequences of algorithm modifications on health disparities.
Risks
Different race-removal approaches may improve or worsen health disparities.
Patient & Prescribing Data
Patients with varying racial backgrounds affected by health disparities.
Incorporating novel measurements may improve algorithm accuracy without relying on race.
Clinical Best Practices
Focus on patient attitudes regarding the use of race in clinical algorithms. Conduct rigorous comparisons of race-aware and race-neutral algorithms. Implement systemic efforts to improve measurement and reduce disparities.
Related Resources & Content