Developing a novel Comorbidities Index for predicting 10-year mortality in Prostate Cancer patients: A computational data-driven approach

2026-05-29

AI Summary

This study addresses the limited accuracy of the conventional Charlson Comorbidity Index (CCI) in predicting 10-year non-cancer mortality risk following radical prostatectomy among contemporary prostate cancer patients, which compromises clinical decision-making. Leveraging a single-center retrospective cohort, the authors propose a novel, interpretable, and parsimonious prostate cancer–specific comorbidity index developed through a data-driven approach that integrates symbolic regression with swarm intelligence optimization techniques—including genetic algorithms, FST-PSO, SLIM, and genetic programming. By incorporating prostate cancer–relevant variables, the new index achieves a concordance index (C-index) up to 0.1 higher than both the original CCI and the Prostate Cancer–specific Charlson Index (PCCI), substantially enhancing long-term survival prediction accuracy and patient selection efficacy.

Abstract

The Charlson Comorbidities Index (CCI) is a weighted additive index widely used to estimate ten-year mortality risk, but its original weights may not reflect contemporary prognoses. This limitation is critical in Prostate Cancer (PCa), where radical treatment is recommended only for patients with a life expectancy of at least ten years. For candidates eligible for Radical Prostatectomy (RP), accurate estimation of ten-year other-cause mortality is essential to balance oncological benefit against competing risks and avoid overtreatment. We propose a data-driven framework to derive a comorbidity index tailored to PCa patients considered for RP. Using a retrospective single-institution cohort, we apply Population-Based Bio-Inspired Algorithms (PBBIAs) to recalibrate comorbidity weights and evolve alternative symbolic formulations optimized for ten-year survival discrimination. We compared six optimization strategies, including symbolic regression approaches based on Genetic Programming (GP), population-based metaheuristics, clinically validated baselines, and survival prediction models. Results show that GA, FST-PSO, and SLIM outperform both the original CCI and the PCCI, particularly when PCa-specific variables are included, improving the Concordance Index by up to 0.1. GPLearn yields compact and interpretable models with competitive performance. Overall, the proposed approach provides an updated and interpretable tool to improve patient selection for RP.

Problem

• Comorbidities Index
• Prostate Cancer
• 10-year mortality
• Radical Prostatectomy
• Patient selection

Innovation

• comorbidity index
• symbolic regression
• Genetic Programming
• data-driven optimization
• prostate cancer mortality prediction