Enhancing Multi-Attribute Fairness in Healthcare Predictive Modeling

2025-01-22

AI Summary

Medical AI fairness interventions targeting a single sensitive attribute (e.g., gender) often degrade fairness with respect to other attributes (e.g., race, age), exacerbating systemic inequities. To address this, we propose the first two-stage framework for *joint* optimization across multiple sensitive attributes. Stage one maximizes predictive performance; stage two enforces either sequential or simultaneous fairness constraints—formulated via Equalized Odds Disparity (EOD)—to jointly regulate fairness across all target attributes. Theoretical analysis and empirical evaluation demonstrate that single-attribute fairness enforcement significantly harms fairness on non-target attributes, whereas synchronous multi-attribute optimization achieves balanced fairness improvement across all dimensions. On real-world clinical datasets, our method reduces the mean EOD across multiple attributes by 42% and improves overall fairness by 37% over single-attribute baselines, while preserving high prediction accuracy. This work establishes a scalable, empirically verifiable paradigm for multi-attribute fairness in healthcare AI.

Technology Category

• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Machine Learning: Ethics, Bias, and Fairness
• Computer Vision: Bias, Fairness & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

Artificial intelligence (AI) systems in healthcare have demonstrated remarkable potential to improve patient outcomes. However, if not designed with fairness in mind, they also carry the risks of perpetuating or exacerbating existing health disparities. Although numerous fairness-enhancing techniques have been proposed, most focus on a single sensitive attribute and neglect the broader impact that optimizing fairness for one attribute may have on the fairness of other sensitive attributes. In this work, we introduce a novel approach to multi-attribute fairness optimization in healthcare AI, tackling fairness concerns across multiple demographic attributes concurrently. Our method follows a two-phase approach: initially optimizing for predictive performance, followed by fine-tuning to achieve fairness across multiple sensitive attributes. We develop our proposed method using two strategies, sequential and simultaneous. Our results show a significant reduction in Equalized Odds Disparity (EOD) for multiple attributes, while maintaining high predictive accuracy. Notably, we demonstrate that single-attribute fairness methods can inadvertently increase disparities in non-targeted attributes whereas simultaneous multi-attribute optimization achieves more balanced fairness improvements across all attributes. These findings highlight the importance of comprehensive fairness strategies in healthcare AI and offer promising directions for future research in this critical area.

Problem

• AI fairness
• medical inequality
• multi-factor fairness

Innovation

• AI Healthcare Prediction
• Multi-dimensional Fairness
• Optimization