Document Type

Article

Publication Date

6-2026

Abstract

This article examines how medical AI systems are incorporating SDoH data and the governance challenges that follow. The authors show that while SDoH integration can enhance clinical workflows and predictive accuracy — potentially improving outcomes for underserved populations — it also introduces acute risks of proxy discrimination, where facially neutral variables replicate protected characteristics. Surveying U.S., EU, and international frameworks, the authors argue that existing regimes lack clear ex ante guidance to distinguish beneficial from harmful uses of SDoH data. In response, they advance post-market monitoring as a pragmatic and scalable pathway: generating real-world, SDoH-stratified evidence that can support enforcement, refine standards, and ultimately align AI deployment with equity goals without foreclosing innovation.

Comments

© Competition Policy International 2026 and originally published as DoyLoo, Ryan and W. Nicholson Price II. "AI, Medicine, and Social Determinants of Health Data." TechREG Chronicle (2026). All rights reserved. Reproduced with permission. 

Download

Link to Web Version

Share

COinS