CoxKAN: Kolmogorov-Arnold Networks for Interpretable, High-Performance Survival Analysis

TL;DR

CoxKAN introduces a novel interpretable Kolmogorov-Arnold Network for survival analysis, achieving high performance and transparency in modeling complex interactions in medical data, outperforming traditional models and deep learning approaches.

Contribution

This paper presents CoxKAN, the first application of Kolmogorov-Arnold Networks to survival analysis, combining interpretability with high predictive accuracy in medical datasets.

Findings

CoxKAN outperforms traditional Cox models by up to 4% in C-index.

CoxKAN accurately recovers interpretable hazard functions.

CoxKAN uncovers complex variable interactions and symbolic formulas.

Abstract

Motivation: Survival analysis is a branch of statistics that is crucial in medicine for modeling the time to critical events such as death or relapse, in order to improve treatment strategies and patient outcomes. Selecting survival models often involves a trade-off between performance and interpretability; deep learning models offer high performance but lack the transparency of more traditional approaches. This poses a significant issue in medicine, where practitioners are reluctant to use black-box models for critical patient decisions. Results: We introduce CoxKAN, a Cox proportional hazards Kolmogorov-Arnold Network for interpretable, high-performance survival analysis. Kolmogorov-Arnold Networks (KANs) were recently proposed as an interpretable and accurate alternative to multi-layer perceptrons. We evaluated CoxKAN on four synthetic and nine real datasets, including five cohorts with clinical data and four with genomics biomarkers. In synthetic experiments, CoxKAN accurately recovered interpretable hazard function formulae and excelled in automatic feature selection. Evaluations on real datasets showed that CoxKAN consistently outperformed the traditional Cox proportional hazards model (by up to 4% in C-index) and matched or surpassed the performance of deep learning-based models. Importantly, CoxKAN revealed complex interactions between predictor variables and uncovered symbolic formulae, which are key capabilities that other survival analysis methods lack, to provide clear insights into the impact of key biomarkers on patient risk. Availability and implementation: CoxKAN is available at GitHub and Zenodo