Beyond Predictive Fairness: Quantifying Attribution Consistency Across Demographic Groups in Diabetic Retinopathy Screening

arXiv:2608.18759v1 Announce Type: cross Abstract: Fairness in medical imaging is commonly evaluated through subgroup performance metrics, yet it remains unclear whether models rely on consistent visual evidence across demographic groups. This work introduces the Explanation Consistency Score (ECS), a fairness-aware metric based on Jensen-Shannon divergence that quantifies the similarity of attribution maps across subgroups. Using diabetic retinopathy screening as a case study, ECS is evaluated globally and within disease severity. Experiments reveal that while predictive performance differs across ethnic groups, explanation consistency remains relatively high and shows no significant association with performance disparities. These findings suggest that predictive fairness and explanation consistency capture complementary dimensions of model behavior, motivating fairness evaluations that extend beyond predictive performance.

Related

• DuetFair: Coupling Inter- and Intra-Subgroup Robustness for Fair Medical Image Segmentation
• Knowing When Not to Predict: Self Supervised Learning and Abstention for Safer DR Screening
• Evaluating the Impact of Medical Image Reconstruction on Downstream AI Fairness and Performance
• Ethical Framework for Responsible Foundational Models in Medical Imaging

Source: arXiv cs.AI | 2026-08-20