Causal Fairness for Survival Analysis

2026-05-11

AI Summary

This work addresses the limitations of existing fairness-aware machine learning methods, which are largely confined to static settings and fail to capture group disparities in time-to-event outcomes driven by underlying causal mechanisms. The paper proposes the first causally grounded fairness framework tailored for survival analysis, integrating causal graphical models, conditional survival function estimation, and nonparametric effect decomposition. This approach disentangles intergroup survival differences into contributions from direct, indirect, and spurious pathways, revealing how unfairness evolves over time. By moving beyond conventional statistical fairness criteria, the method enables interpretable, dynamic fairness assessment. Empirical application to ICU patient data successfully quantifies and traces the causal components underlying racial disparities in clinical prognosis.

Abstract

In the data-driven era, large-scale datasets are routinely collected and analyzed using machine learning (ML) and artificial intelligence (AI) to inform decisions in high-stakes domains such as healthcare, employment, and criminal justice, raising concerns about the fairness behavior of these systems. Existing works in fair ML cover tasks such as bias detection, fair prediction, and fair decision-making, but largely focus on static settings. At the same time, fairness in temporal contexts, particularly survival/time-to-event (TTE) analysis, remains relatively underexplored, with current approaches to fair survival analysis adopting statistical fairness definitions, which, even with unlimited data, cannot disentangle the causal mechanisms that generate disparities. To address this gap, we develop a causal framework for fairness in TTE analysis, enabling the decomposition of disparities in survival into contributions from direct, indirect, and spurious pathways. This provides a human-understandable explanation of why disparities arise and how they evolve over time. Our non-parametric approach proceeds in four steps: (1) formalizing the necessary assumptions about censoring and lack of confounding using a graphical model; (2) recovering the conditional survival function given covariates; (3) applying the Causal Reduction Theorem to reframe the problem in a form amenable to causal pathway decomposition; (4) estimating the effects efficiently. Finally, our approach is used to analyze the temporal evolution of racial disparities in outcome after admission to an intensive care unit (ICU).

Problem

• causal fairness
• survival analysis
• time-to-event analysis
• algorithmic bias
• health disparities

Innovation

• causal fairness
• survival analysis
• time-to-event analysis
• causal pathway decomposition
• non-parametric estimation