CoxKAN: Kolmogorov-Arnold networks for interpretable, high-performance survival analysis
Bioinformatics · 02.08.2025 · 41 (8)
DOI: 10.1093/bioinformatics/btaf413 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 21.07.2025. Verfasst von William Knottenbelt und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oncology, University of Cambridge, Cambridge, CB2 0XZ, United Kingdom. Hauptthemen laut MEDLINE: Survival Analysis. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Mark Foundation for Cancer Research.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Oncology, University of Cambridge, Cambridge, CB2 0XZ, United Kingdom.
- Department of Physics, University of Cambridge, Cambridge, CB3 0HE, United Kingdom.
- CRUK Cambridge Centre, University of Cambridge, Cambridge, CB2 0RE, United Kingdom.
- School of Computer Science, Xi'an Jiaotong University, Xi'an, 710049, China.
ORCID-Profile: Zeyu Gao
Förderung
- Mark Foundation for Cancer Research
Zitieren
APA
Knottenbelt, W., McGough, W., Wray, R., Zhang, W. Z., Liu, J., Machado, I. P., Gao, Z., & Crispin-Ortuzar, M. (2025). CoxKAN: Kolmogorov-Arnold networks for interpretable, high-performance survival analysis. Bioinformatics, 41(8). https://doi.org/10.1093/bioinformatics/btaf413
Vancouver
Knottenbelt W, McGough W, Wray R, Zhang WZ, Liu J, Machado IP, et al. CoxKAN: Kolmogorov-Arnold networks for interpretable, high-performance survival analysis. Bioinformatics. 2025;41(8). doi:10.1093/bioinformatics/btaf413
BibTeX
@article{Knottenbelt2025,
author = {Knottenbelt, William and McGough, William and Wray, Rebecca and Zhang, Woody Zhidong and Liu, Jiashuai and Machado, Ines Prata and Gao, Zeyu and Crispin-Ortuzar, Mireia},
title = {CoxKAN: Kolmogorov-Arnold networks for interpretable, high-performance survival analysis},
journal = {Bioinformatics},
year = {2025},
volume = {41},
number = {8},
doi = {10.1093/bioinformatics/btaf413}
}
EUVIMED