FAST-CAD: A Fairness-Aware Framework for Non-Contact Stroke Diagnosis
This work addresses fairness in medical AI for stroke diagnosis, potentially reducing healthcare disparities, though it is incremental as it builds on existing methods.
The paper tackled fairness issues in automated stroke diagnosis across demographic groups by proposing FAST-CAD, a framework combining domain-adversarial training and group distributionally robust optimization, which achieved superior diagnostic performance while maintaining fairness across 12 subgroups.
Stroke is an acute cerebrovascular disease, and timely diagnosis significantly improves patient survival. However, existing automated diagnosis methods suffer from fairness issues across demographic groups, potentially exacerbating healthcare disparities. In this work we propose FAST-CAD, a theoretically grounded framework that combines domain-adversarial training (DAT) with group distributionally robust optimization (Group-DRO) for fair and accurate non-contact stroke diagnosis. Our approach is built on domain adaptation and minimax fairness theory and provides convergence guarantees and fairness bounds. We curate a multimodal dataset covering 12 demographic subgroups defined by age, gender, and posture. FAST-CAD employs self-supervised encoders with adversarial domain discrimination to learn demographic-invariant representations, while Group-DRO optimizes worst-group risk to ensure robust performance across all subgroups. Extensive experiments show that our method achieves superior diagnostic performance while maintaining fairness across demographic groups, and our theoretical analysis supports the effectiveness of the unified DAT + Group-DRO framework. This work provides both practical advances and theoretical insights for fair medical AI systems.