Equitable Survival Prediction: A Fairness-Aware Survival Modeling (FASM) Approach

2025-10-23

AI Summary

In healthcare survival analysis, clinical data biases often induce discriminatory risk ranking across demographic groups—e.g., high-risk Black patients ranked below low-risk White patients—exacerbating health inequities. To address this, we propose FASM, the first survival modeling framework that jointly optimizes intra-group and inter-group risk ranking fairness. FASM introduces time-dynamic fairness constraints and hierarchical fair regularization, coupled with a time-aware evaluation protocol. Experiments on the SEER breast cancer dataset demonstrate that FASM maintains strong predictive performance (C-index ≈ 0.72) while significantly improving inter-group ranking fairness—reducing Kendall-τ disparity by 42%—with stable fairness over a 10-year follow-up period and most pronounced gains at mid-term horizons. This work overcomes a key limitation of prior fair survival models, which neglect inter-group ranking bias, and establishes a novel paradigm for trustworthy, equitable medical AI.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

As machine learning models become increasingly integrated into healthcare, structural inequities and social biases embedded in clinical data can be perpetuated or even amplified by data-driven models. In survival analysis, censoring and time dynamics can further add complexity to fair model development. Additionally, algorithmic fairness approaches often overlook disparities in cross-group rankings, e.g., high-risk Black patients may be ranked below lower-risk White patients who do not experience the event of mortality. Such misranking can reinforce biological essentialism and undermine equitable care. We propose a Fairness-Aware Survival Modeling (FASM), designed to mitigate algorithmic bias regarding both intra-group and cross-group risk rankings over time. Using breast cancer prognosis as a representative case and applying FASM to SEER breast cancer data, we show that FASM substantially improves fairness while preserving discrimination performance comparable to fairness-unaware survival models. Time-stratified evaluations show that FASM maintains stable fairness over a 10-year horizon, with the greatest improvements observed during the mid-term of follow-up. Our approach enables the development of survival models that prioritize both accuracy and equity in clinical decision-making, advancing fairness as a core principle in clinical care.

Problem

• Mitigating algorithmic bias in survival analysis models
• Addressing disparities in cross-group risk ranking fairness
• Ensuring equitable prediction accuracy over long-term horizons

Innovation

• Fairness-aware survival modeling for bias mitigation
• Addresses intra-group and cross-group risk ranking disparities
• Maintains discrimination performance while improving equity