SOURCE-LINKED INTELLIGENCE

FRAME: separating sampling variation from representational cause in medical imaging fairness

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Subgroup performance differences are the standard evidence for fairness bias in medical imaging, and the usual response removes the demographic information that a model encodes. Here we introduce Fair-model Reference And Mechanism Evaluation (FRAME), a two-step framework for auditing such a claim. The first step derives a fair-model reference, the distribution of the difference under exact fairness at the observed subgroup sizes. In the second step, we test the remainder with two operators in representation space. One operator cannot change a within-group ranking by construction. Across 702,20

Read original source ↗ Open in workspace

recordType

paper

region

Global