Mitigating Disparities in Prostate Cancer Survival Prediction Through Fairness‐Aware Machine Learning Models

TL;DR

This paper introduces fairness-aware machine learning models to reduce racial disparities in predicting prostate cancer survival outcomes.

Contribution

The study benchmarks two fairness-aware deep learning survival models to mitigate racial disparities in survival prediction.

Findings

Fairness-aware models improved cross-group concordance indices for Black and Hispanic patients compared to the baseline model.

Minimal performance loss was observed for White patients when using fairness-aware models.

Abstract

Prediction models can contribute to disparities in care by performing unequally across demographic groups. While fairness‐aware methods have been explored for binary outcomes, applications to survival analysis remain limited. This study compares two fairness‐aware deep learning survival models to mitigate racial disparities in predicting survival after radical prostatectomy for prostate cancer.

We used the National Cancer Database to train deep Cox proportional hazards models for overall survival. Two fairness‐aware approaches, Fair Deep Cox Proportional Hazards Model (Fair DCPH) and Group Distributionally Robust Optimization Deep Cox Proportional Hazards Model (GroupDRO DCPH), were compared against a standard Deep Cox model (Baseline). Model fairness was assessed via cross‐group and within‐group concordance indices (C‐index).

Among 418,968 included patients, 78.5% were White, with smaller proportions of Black (13.2%), Hispanic (4.5%), Asian (1.9%), and Other (2.0%) patients. The baseline DCPH model achieved a cross‐group C‐index of 0.699 for White patients but showed reduced performance for Black (0.678) and Hispanic (0.689) patients. Fairness‐aware models improved cross‐group C‐indices; for Black patients, cross‐group C‐index increased to 0.692 (Fair DCPH) and 0.696 (GroupDRO DCPH); for Hispanic patients, to 0.693 and 0.697, respectively. Cross‐group C‐index also improved in the Asian subgroup, where the C‐index rose from 0.696 (Baseline DCPH) to 0.702 (Fair DCPH) and 0.707 (GroupDRO DCPH), with minimal performance loss observed for White patients.

We benchmark two fairness‐aware survival models that address racial disparities in post‐prostatectomy survival prediction. These methods can be extended to other time‐to‐event models to ensure equitable care supported by fair prediction models.

Figures