Work

Context is all you need: A causal framework for governing bias in clinical AI

Year: 2026

Type: article

Abstract: Clinical AI systems can produce different recommendations when a patient's race, income, housing status, or gender identity changes, but a differential alone does not establish unjustified bias. What separates a clinically justified differential from an unjustified one is not its size or direction but its origin: whether the feature acts through a clinically justified pathway, or marks how patients of that group have been treated. That distinction is causal, and a model trained only to detect statistical association records that a feature carries information but never why. Existing evidence does not establish reliable recovery of this adjudication inside that model; we therefore argue for explicit causal and normative supervision, whether supplied by an external layer, built into training, or both. We set out a six-criterion rubric, four approaches to implementing it, and a two-sided evaluation reporting preserved clinical sensitivity alongside reduced bias.

Source: PLOS Digital Health

DOI: 10.1371/journal.pdig.0001819

Authors: Alon Gorenshtein, Mahmud Omar, Yiftach Barash, Girish N. Nadkarni, Eyal Klang

Institutions: Harvard University, Mount Sinai Health System, Mount Sinai Medical Center, Icahn School of Medicine at Mount Sinai

Language: English

Topic: Ethics and Social Impacts of AI

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDGs: Good health and well-being, Reduced inequalities

Open Access status: gold

Estimated APC paid: $3,043