SurvKAN: A Fully Parametric Survival Model Based on Kolmogorov-Arnold Networks

2026-02-02

AI Summary

This work proposes SurvKAN, a fully parametric, time-continuous survival model based on Kolmogorov–Arnold Networks (KANs), which overcomes the limitations of traditional survival models—such as the Cox proportional hazards model—that rely on linear assumptions and proportional hazards constraints. Unlike existing deep learning approaches that sacrifice interpretability for flexibility, SurvKAN explicitly incorporates time as an input and directly models the log-hazard function, optimizing the full survival likelihood via end-to-end maximum likelihood estimation. By introducing the KAN architecture to survival analysis for the first time, the method dispenses with the proportional hazards assumption while achieving concordance indices and calibration performance on par with or superior to state-of-the-art methods across standard benchmarks. Moreover, it offers feature-level interpretability through learnable univariate functions, revealing risk patterns consistent with medical priors.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate prediction of time-to-event outcomes is critical for clinical decision-making, treatment planning, and resource allocation in modern healthcare. While classical survival models such as Cox remain widely adopted in standard practice, they rely on restrictive assumptions, including linear covariate relationships and proportional hazards over time, that often fail to capture real-world clinical dynamics. Recent deep learning approaches like DeepSurv and DeepHit offer improved expressivity but sacrifice interpretability, limiting clinical adoption where trust and transparency are paramount. Hybrid models incorporating Kolmogorov-Arnold Networks (KANs), such as CoxKAN, have begun to address this trade-off but remain constrained by the semi-parametric Cox framework. In this work we introduce SurvKAN, a fully parametric, time-continuous survival model based on KAN architectures that eliminates the proportional hazards constraint. SurvKAN treats time as an explicit input to a KAN that directly predicts the log-hazard function, enabling end-to-end training on the full survival likelihood. Our architecture preserves interpretability through learnable univariate functions that indicate how individual features influence risk over time. Extensive experiments on standard survival benchmarks demonstrate that SurvKAN achieves competitive or superior performance compared to classical and state-of-the-art baselines across concordance and calibration metrics. Additionally, interpretability analyses reveal clinically meaningful patterns that align with medical domain knowledge.

Problem

• survival analysis
• time-to-event prediction
• proportional hazards
• model interpretability
• clinical decision-making

Innovation

• Survival analysis
• Kolmogorov-Arnold Networks
• Fully parametric model
• Interpretability
• Time-to-event prediction