CIPHER: Causal Intervention Pathways for Healthcare Equity and Robustness

2026-07-01

AI Summary

This study addresses significant performance disparities in existing deep learning–based medical diagnostic models across sensitive subgroups, such as race and gender. Leveraging structural causal models, the authors identify and systematically intervene on four causal pathways through which sensitive attributes influence predictions in medical imaging. They propose CIPHER, a novel framework that enhances model fairness and robustness by synthesizing anatomically faithful, editable counterfactual images using a diffusion model combined with classifier-free guidance and null-text inversion. Evaluated on chest X-ray and dermoscopy datasets, CIPHER reduces the worst-group performance gap by 35.8% on average compared to disease-conditioned synthesis baselines while simultaneously improving overall diagnostic accuracy.

Abstract

Deep learning models for medical diagnosis frequently exhibit substantial performance disparities across sensitive subgroups (e.g., race, sex), even when average accuracy is high. While generative data augmentation offers a route to mitigate this, existing strategies are suboptimal; they typically address only one or two dependency channels between sensitive attributes and image features. We formalize the medical image formation process via a structural causal model, revealing that sensitive attributes actually influence image content through four distinct pathways-a structural complexity neglected by prior works. Based on this insight, we introduce CIPHER (Causal Intervention Pathways for Healthcare Equity and Robustness), a framework designed to systematically intervene on all four causal paths. To achieve this, CIPHER utilizes a diffusion backbone equipped with classifier-free guidance and null-text inversion. This technical design enables the faithful reconstruction of patient-specific anatomy while allowing for the precise, editable synthesis of counterfactuals required to break sensitive dependency chains. We tested CIPHER using chest X-ray and dermoscopy benchmarks across both standard and shifted data distributions. By employing a multi-pathway intervention strategy, our model reduced worst-group disparities by an average of 35.8% compared to disease-conditioned synthesis baselines, while also improving total diagnostic accuracy

Problem

• healthcare equity
• algorithmic fairness
• medical image analysis
• causal pathways
• performance disparity

Innovation

• causal intervention
• healthcare equity
• diffusion models
• counterfactual synthesis
• structural causal model