Tree-Based Approaches for Interpretable Modeling in Healthcare

Abstract

Survival analysis models time-to-event data in oncology, such as cancer relapse or death, to evaluate treatment effects. Machine learning (ML) advancements, particularly ensemble methods like random survival forests (RSF), enhance predictive accuracy but often lack interpretability, posing challenges for clinical trust and regulatory compliance. This work addresses these limitations by systematically reviewing health authority criteria for AI interpretability, assessing existing methods like SurvSHAP and SurvLIME, and developing an RSF extension to handle multiple clinical events with novel metrics for performance evaluation. Future efforts focus on integrating model-specific interpretability through TreeSHAP and SurvSHAP to provide robust, time-dependent explanations, enabling the alignment of predictive power with clinical transparency in oncology care.