{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T18:18:14Z","timestamp":1774894694401,"version":"3.50.1"},"reference-count":51,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T00:00:00Z","timestamp":1753056000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014599","name":"Mark Foundation for Cancer Research","doi-asserted-by":"publisher","award":["RG95043"],"award-info":[{"award-number":["RG95043"]}],"id":[{"id":"10.13039\/100014599","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>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.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>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.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>CoxKAN is available at GitHub and Zenodo.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf413","type":"journal-article","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T05:05:27Z","timestamp":1753074327000},"source":"Crossref","is-referenced-by-count":15,"title":["CoxKAN: Kolmogorov-Arnold networks for interpretable, high-performance survival analysis"],"prefix":"10.1093","volume":"41","author":[{"given":"William","family":"Knottenbelt","sequence":"first","affiliation":[{"name":"Department of Oncology, University of Cambridge , Cambridge, CB2 0XZ,","place":["United Kingdom"]},{"name":"Department of Physics, University of Cambridge , Cambridge, CB3 0HE,","place":["United Kingdom"]}]},{"given":"William","family":"McGough","sequence":"additional","affiliation":[{"name":"Department of Oncology, University of Cambridge , Cambridge, CB2 0XZ,","place":["United Kingdom"]},{"name":"CRUK Cambridge Centre, University of Cambridge , Cambridge, CB2 0RE,","place":["United Kingdom"]}]},{"given":"Rebecca","family":"Wray","sequence":"additional","affiliation":[{"name":"Department of Oncology, University of Cambridge , Cambridge, CB2 0XZ,","place":["United Kingdom"]},{"name":"CRUK Cambridge Centre, University of Cambridge , Cambridge, CB2 0RE,","place":["United Kingdom"]}]},{"given":"Woody Zhidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Oncology, University of Cambridge , Cambridge, CB2 0XZ,","place":["United Kingdom"]},{"name":"CRUK Cambridge Centre, University of Cambridge , Cambridge, CB2 0RE,","place":["United Kingdom"]}]},{"given":"Jiashuai","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Xi\u2019an Jiaotong University , Xi\u2019an, 710049,","place":["China"]}]},{"given":"Ines Prata","family":"Machado","sequence":"additional","affiliation":[{"name":"Department of Oncology, University of Cambridge , Cambridge, CB2 0XZ,","place":["United Kingdom"]},{"name":"CRUK Cambridge Centre, University of Cambridge , Cambridge, CB2 0RE,","place":["United Kingdom"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2365-8318","authenticated-orcid":false,"given":"Zeyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Oncology, University of Cambridge , Cambridge, CB2 0XZ,","place":["United Kingdom"]},{"name":"CRUK Cambridge Centre, University of Cambridge , Cambridge, CB2 0RE,","place":["United Kingdom"]}]},{"given":"Mireia","family":"Crispin-Ortuzar","sequence":"additional","affiliation":[{"name":"Department of Oncology, University of Cambridge , Cambridge, CB2 0XZ,","place":["United Kingdom"]},{"name":"CRUK Cambridge Centre, University of Cambridge , Cambridge, CB2 0RE,","place":["United Kingdom"]}]}],"member":"286","published-online":{"date-parts":[[2025,7,21]]},"reference":[{"key":"2025081213183582300_btaf413-B1","doi-asserted-by":"crossref","first-page":"15691","DOI":"10.1038\/s41598-024-59953-0","article-title":"Dysregulated gene subnetworks in breast invasive carcinoma reveal novel tumor suppressor genes","volume":"14","author":"Agarwal","year":"2024","journal-title":"Sci Rep"},{"key":"2025081213183582300_btaf413-B2","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1111\/1467-9876.00165","article-title":"Design and analysis of two-phase studies with binary outcome applied to WILMS tumour prognosis","volume":"48","author":"Breslow","year":"1999","journal-title":"J R Stat Soc Ser C (Appl Stat)"},{"key":"2025081213183582300_btaf413-B3","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1109\/TMI.2020.3021387","article-title":"Pathomic fusion: an integrated framework for fusing histopathology and genomic features for cancer diagnosis and prognosis","volume":"41","author":"Chen","year":"2022","journal-title":"IEEE Trans Med Imaging"},{"key":"2025081213183582300_btaf413-B4","author":"Cheon","year":"2024"},{"key":"2025081213183582300_btaf413-B5","doi-asserted-by":"crossref","first-page":"e1006076","DOI":"10.1371\/journal.pcbi.1006076","article-title":"Cox-nnet: an artificial neural network method for prognosis prediction of high-throughput omics data","volume":"14","author":"Ching","year":"2018","journal-title":"PLoS Comput Biol"},{"key":"2025081213183582300_btaf413-B6","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1111\/j.2517-6161.1972.tb00899.x","article-title":"Regression models and life-tables","volume":"34","author":"Cox","year":"1972","journal-title":"J R Stat Soc Ser B (Methodological)"},{"key":"2025081213183582300_btaf413-B7","author":"Cranmer","year":"2023"},{"key":"2025081213183582300_btaf413-B8","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1016\/j.mayocp.2012.03.009","article-title":"Use of nonclonal serum immunoglobulin free light chains to predict overall survival in the general population","volume":"87","author":"Dispenzieri","year":"2012","journal-title":"Mayo Clin Proc"},{"key":"2025081213183582300_btaf413-B9","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1002\/sim.4780140108","article-title":"A neural network model for survival data","volume":"14","author":"Faraggi","year":"1995","journal-title":"Stat Med"},{"key":"2025081213183582300_btaf413-B10","first-page":"5021","article-title":"Gaussian processes for survival analysis","volume":"29","author":"Fernandez","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025081213183582300_btaf413-B11","first-page":"636","article-title":"The urokinase system of plasminogen activation and prognosis in 2780 breast cancer patients","volume":"60","author":"Foekens","year":"2000","journal-title":"Cancer Res"},{"key":"2025081213183582300_btaf413-B12","first-page":"898","article-title":"Development of an eight-gene prognostic model for overall survival prediction in patients with hepatocellular carcinoma","volume":"9","author":"Guo","year":"2021","journal-title":"J Clin Transl Hepatol"},{"key":"2025081213183582300_btaf413-B13","first-page":"5287","volume-title":"J Clin Oncol","author":"Harris","year":"2007"},{"key":"2025081213183582300_btaf413-B14","first-page":"25","article-title":"Random survival forests for r","volume":"7","author":"Ishwaran","year":"2007","journal-title":"R News"},{"key":"2025081213183582300_btaf413-B15","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1214\/08-AOAS169","article-title":"Random survival forests","volume":"2","author":"Ishwaran","year":"2008","journal-title":"Ann Appl Stat"},{"key":"2025081213183582300_btaf413-B16","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s12874-018-0482-1","article-title":"Deepsurv: personalized treatment recommender system using a cox proportional hazards deep neural network","volume":"18","author":"Katzman","year":"2018","journal-title":"BMC Med Res Methodol"},{"key":"2025081213183582300_btaf413-B17","doi-asserted-by":"crossref","first-page":"i389","DOI":"10.1093\/bioinformatics\/btaa462","article-title":"Improved survival analysis by learning shared genomic information from pan-cancer data","volume":"36","author":"Kim","year":"2020","journal-title":"Bioinformatics"},{"key":"2025081213183582300_btaf413-B18","author":"Kingma","year":"2015"},{"key":"2025081213183582300_btaf413-B19","doi-asserted-by":"crossref","first-page":"191","DOI":"10.7326\/0003-4819-122-3-199502010-00007","article-title":"The support prognostic model: objective estimates of survival for seriously ill hospitalized adults","volume":"122","author":"Knaus","year":"1995","journal-title":"Ann Intern Med"},{"key":"2025081213183582300_btaf413-B20","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1038\/s41374-021-00667-6","article-title":"Grading of adult diffuse gliomas according to the 2021 who classification of tumors of the central nervous system","volume":"102","author":"Komori","year":"2022","journal-title":"Lab Invest"},{"key":"2025081213183582300_btaf413-B21","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1007\/s10985-021-09532-6","article-title":"Continuous and discrete-time survival prediction with neural networks","volume":"27","author":"Kvamme","year":"2021","journal-title":"Lifetime Data Anal"},{"key":"2025081213183582300_btaf413-B22","first-page":"1","article-title":"Time-to-event prediction with neural networks and cox regression","volume":"20","author":"Kvamme","year":"2019","journal-title":"J Mach Learn Res"},{"key":"2025081213183582300_btaf413-B23","author":"Langbein","year":"2024"},{"key":"2025081213183582300_btaf413-B24","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1016\/j.jtho.2021.04.004","article-title":"Time-to-event data: an overview and analysis considerations","volume":"16","author":"Le-Rademacher","year":"2021","journal-title":"J Thorac Oncol"},{"key":"2025081213183582300_btaf413-B25","author":"Lee","year":"2018"},{"key":"2025081213183582300_btaf413-B26","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. Philadelphia, Pennsylvania, USA","author":"Li","year":"2024."},{"key":"2025081213183582300_btaf413-B27","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.21037\/tlcr-23-14","article-title":"Identification of lysosomal genes associated with prognosis in lung adenocarcinoma","volume":"12","author":"Li","year":"2023","journal-title":"Transl Lung Cancer Res"},{"key":"2025081213183582300_btaf413-B28","author":"Liu","year":"2024"},{"key":"2025081213183582300_btaf413-B29","doi-asserted-by":"crossref","first-page":"145","DOI":"10.18632\/oncotarget.10426","article-title":"Non-myogenic tumors display altered expression of dystrophin (DMD) and a high frequency of genetic alterations","volume":"8","author":"Luce","year":"2017","journal-title":"Oncotarget"},{"key":"2025081213183582300_btaf413-B30","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1016\/j.jval.2019.01.005","article-title":"Measuring survival benefit in health technology assessment in the presence of nonproportional hazards","volume":"22","author":"Monnickendam","year":"2019","journal-title":"Value Health"},{"key":"2025081213183582300_btaf413-B31","first-page":"674","author":"Nagpal","year":"2021"},{"key":"2025081213183582300_btaf413-B32","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1056\/NEJMoa1402121","article-title":"Comprehensive, integrative genomic analysis of diffuse lower-grade gliomas","volume":"372","author":"Network","year":"2015","journal-title":"N Engl J Med"},{"key":"2025081213183582300_btaf413-B33","doi-asserted-by":"crossref","first-page":"eabl5165","DOI":"10.1126\/sciadv.abl5165","article-title":"Interrogating glioma-m2 macrophage interactions identifies gal-9\/tim-3 as a viable target against PTEN-null glioblastoma","volume":"8","author":"Ni","year":"2022","journal-title":"Sci Adv"},{"key":"2025081213183582300_btaf413-B34","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1093\/neuonc\/nou087","article-title":"The epidemiology of glioma in adults: a \u201cstate of the science\u201d review","volume":"16","author":"Ostrom","year":"2014","journal-title":"Neuro Oncol"},{"key":"2025081213183582300_btaf413-B35","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1016\/j.jtho.2021.01.1616","article-title":"Biomarker discovery and validation: statistical considerations","volume":"16","author":"Ou","year":"2021","journal-title":"J Thorac Oncol"},{"key":"2025081213183582300_btaf413-B36","first-page":"1190","author":"Rindt","year":"2022"},{"key":"2025081213183582300_btaf413-B37","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1038\/sj.bjc.6602298","article-title":"Expression and methylation status of tissue factor pathway inhibitor-2 gene in non-small-cell lung cancer","volume":"92","author":"Rollin","year":"2005","journal-title":"Br J Cancer"},{"key":"2025081213183582300_btaf413-B38","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/1471-2288-13-33","article-title":"External validation of a cox prognostic model: principles and methods","volume":"13","author":"Royston","year":"2013","journal-title":"BMC Med Res Methodol"},{"key":"2025081213183582300_btaf413-B39","doi-asserted-by":"crossref","first-page":"3203","DOI":"10.1038\/s41598-021-82332-y","article-title":"Detecting survival-associated biomarkers from heterogeneous populations","volume":"11","author":"Saegusa","year":"2021","journal-title":"Sci Rep"},{"key":"2025081213183582300_btaf413-B40","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.trecan.2024.02.003","article-title":"Kmt2c and kmt2d aberrations in breast cancer","volume":"10","author":"Tinsley","year":"2024","journal-title":"Trends Cancer"},{"key":"2025081213183582300_btaf413-B41","author":"Vaca-Rubio","year":"2024"},{"key":"2025081213183582300_btaf413-B42","author":"Vaswani","year":"2017"},{"key":"2025081213183582300_btaf413-B43","doi-asserted-by":"crossref","first-page":"954840","DOI":"10.3389\/fgene.2022.954840","article-title":"m7g-associated subtypes, tumor microenvironment, and validation of prognostic signature in lung adenocarcinoma","volume":"13","author":"Wang","year":"2022","journal-title":"Front Genet"},{"key":"2025081213183582300_btaf413-B44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3214306","article-title":"Machine learning for survival analysis: a survey","volume":"51","author":"Wang","year":"2019","journal-title":"ACM Comput Surv"},{"key":"2025081213183582300_btaf413-B45","author":"Watanabe","year":"2023"},{"key":"2025081213183582300_btaf413-B46","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1593\/neo.05307","article-title":"Patients with high-grade gliomas harboring deletions of chromosomes 9p and 10q benefit from temozolomide treatment","volume":"7","author":"Wemmert","year":"2005","journal-title":"Neoplasia"},{"key":"2025081213183582300_btaf413-B47","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/s10462-023-10681-3","article-title":"Deep learning for survival analysis: a review","volume":"57","author":"Wiegrebe","year":"2024","journal-title":"Artif Intell Rev"},{"key":"2025081213183582300_btaf413-B48","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.lungcan.2011.09.005","article-title":"Tfpi-2 methylation predicts poor prognosis in non-small cell lung cancer","volume":"76","author":"Wu","year":"2012","journal-title":"Lung Cancer"},{"key":"2025081213183582300_btaf413-B49","doi-asserted-by":"crossref","first-page":"8072796","DOI":"10.1155\/2021\/8072796","article-title":"Bioinformatic analysis of immune significance of ryr2 mutation in breast cancer","volume":"2021","author":"Xu","year":"2021","journal-title":"Biomed Res Int"},{"key":"2025081213183582300_btaf413-B50","article-title":"Learning patient-specific cancer survival distributions as a sequence of dependent regressors","author":"Yu","year":"2011","journal-title":"Advances in Neural Information Processing Systems 24"},{"key":"2025081213183582300_btaf413-B51","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1186\/s12967-021-02979-z","article-title":"Identification of prognostic values defined by copy number variation, mRNA and protein expression of lancl2 and EGFR in glioblastoma patients","volume":"19","author":"Zhao","year":"2021","journal-title":"J Transl Med"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf413\/63808076\/btaf413.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/8\/btaf413\/63808076\/btaf413.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/8\/btaf413\/63808076\/btaf413.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T17:18:50Z","timestamp":1755019130000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf413\/8209483"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,7,21]]},"references-count":51,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf413","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,8]]},"published":{"date-parts":[[2025,7,21]]},"article-number":"btaf413"}}