{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T15:44:28Z","timestamp":1786549468480,"version":"build-2736575974"},"posted":{"date-parts":[[2026,8,10]]},"group-title":"Health Informatics","reference-count":87,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["U24CA284167"],"award-info":[{"award-number":["U24CA284167"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["U24HG006620"],"award-info":[{"award-number":["U24HG006620"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/01xf75524","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,8,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Survival analysis is a fundamental technique in biomedical research for modeling time-to-event data. It enables the identification of prognostic factors in disease, compares survival outcomes across treatment groups, and performs targeted treatment selection. A variety of machine learning (ML) approaches to survival analysis have emerged to complement classical statistical methods, especially for high-dimensional datasets with complex, nonlinear interactions between features. However, using survival ML methods requires addressing challenges such as censoring-unaware evaluation, overfitting, selecting performance metrics, and data leakage. To address these and other difficulties in using survival ML models, we developed the\n                  <jats:monospace>mlsurv<\/jats:monospace>\n                  software package.\n                  <jats:monospace>mlsurv<\/jats:monospace>\n                  is an open-source Python package built around three major design principles: 1) methodological rigor, including evidence-based model selection, leakage-free pipelines, and multi-metric evaluation, 2) multi-scale evaluation and interpretation, including population and subpopulation evaluation, patient-level explanations, and feature analysis, and 3) automated trust and transparency, including limitation flagging and TRIPOD+AI-aligned reporting.\n                  <jats:monospace>mlsurv<\/jats:monospace>\n                  bundles ten models spanning linear, ensemble, kernel, and deep learning families within a unified software package. To our knowledge, mlsurv is the first package to span the complete survival ML workflow from automated model recommendation through TRIPOD+AI reporting and individual patient explanation. We demonstrate\n                  <jats:monospace>mlsurv<\/jats:monospace>\n                  on the Chowell immunotherapy cohort (n=1,479). We found that overall survival (OS) was more predictable than progression-free survival (PFS) (concordance of 0.73 vs 0.67). Albumin was a top feature for both endpoints but dominated OS prediction, whereas tumor mutational burden rose to co-lead PFS prediction. Survival models matched the response-trained LORIS clinical score on PFS prediction and exceeded it on OS.\n                  <jats:monospace>mlsurv<\/jats:monospace>\n                  enables biomedical researchers to conduct rigorous, multi-model survival analysis and benchmarking using minimal code with default best practices rather than implementing custom scripts and methodological safeguards from scratch.\n                <\/jats:p>","DOI":"10.64898\/2026.08.05.26359034","type":"posted-content","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T14:05:17Z","timestamp":1786370717000},"source":"Crossref","is-referenced-by-count":0,"title":["A software package for simple and rigorous survival machine learning analysis in biomedical research"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9722-3977","authenticated-orcid":false,"given":"Alyssa F.","family":"Pybus","sequence":"first","affiliation":[{"name":"Department of Machine Learning, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4322-3401","authenticated-orcid":false,"given":"Junhao","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4403-6684","authenticated-orcid":false,"suffix":"Jr","given":"Paulo Cilas","family":"Morais Lyra","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7774-1380","authenticated-orcid":false,"given":"Khai","family":"Dang","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7320-618X","authenticated-orcid":false,"given":"Isis","family":"Narvaez-Bandera","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tosin","family":"Jolaogun","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4583-5226","authenticated-orcid":false,"given":"Jeremy","family":"Goecks","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026081207450868000_2026.08.05.26359034v1.1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1972.tb00899.x"},{"key":"2026081207450868000_2026.08.05.26359034v1.2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10681-3"},{"key":"2026081207450868000_2026.08.05.26359034v1.3","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1428501"},{"key":"2026081207450868000_2026.08.05.26359034v1.4","doi-asserted-by":"publisher","DOI":"10.1145\/3214306"},{"key":"2026081207450868000_2026.08.05.26359034v1.5","doi-asserted-by":"publisher","DOI":"10.3390\/genes16060648"},{"key":"2026081207450868000_2026.08.05.26359034v1.6","doi-asserted-by":"publisher","DOI":"10.3390\/inventions9030059"},{"key":"2026081207450868000_2026.08.05.26359034v1.7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2406.08521"},{"key":"2026081207450868000_2026.08.05.26359034v1.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2026.106538"},{"key":"2026081207450868000_2026.08.05.26359034v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-026-01557-x"},{"key":"2026081207450868000_2026.08.05.26359034v1.10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2510.12399"},{"key":"2026081207450868000_2026.08.05.26359034v1.11","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01317"},{"issue":"212","key":"2026081207450868000_2026.08.05.26359034v1.12","first-page":"1","article-title":"scikit-survival: A Library for Time-to-Event Analysis Built on Top of scikit-learn","volume":"21","year":"2020","journal-title":"J Mach Learn Res"},{"key":"2026081207450868000_2026.08.05.26359034v1.13","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"2026081207450868000_2026.08.05.26359034v1.14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1201.0490"},{"key":"2026081207450868000_2026.08.05.26359034v1.15","doi-asserted-by":"publisher","DOI":"10.1007\/s10985-021-09532-6"},{"key":"2026081207450868000_2026.08.05.26359034v1.16","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-018-0482-1"},{"key":"2026081207450868000_2026.08.05.26359034v1.17","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"2026081207450868000_2026.08.05.26359034v1.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100804"},{"key":"2026081207450868000_2026.08.05.26359034v1.19","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"2026081207450868000_2026.08.05.26359034v1.20","doi-asserted-by":"publisher","DOI":"10.1093\/gigascience\/giac071"},{"key":"2026081207450868000_2026.08.05.26359034v1.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.111176"},{"key":"2026081207450868000_2026.08.05.26359034v1.22","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-025-02694-z"},{"key":"2026081207450868000_2026.08.05.26359034v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-021-01070-8"},{"key":"2026081207450868000_2026.08.05.26359034v1.24","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v039.i10"},{"key":"2026081207450868000_2026.08.05.26359034v1.25","doi-asserted-by":"publisher","DOI":"10.1002\/9781118032985"},{"key":"2026081207450868000_2026.08.05.26359034v1.26","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOAS169"},{"key":"2026081207450868000_2026.08.05.26359034v1.27","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxj011"},{"key":"2026081207450868000_2026.08.05.26359034v1.28","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2022.2067548"},{"key":"2026081207450868000_2026.08.05.26359034v1.29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23525-7_15"},{"key":"2026081207450868000_2026.08.05.26359034v1.30","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-018-0482-1"},{"key":"2026081207450868000_2026.08.05.26359034v1.31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11842"},{"key":"2026081207450868000_2026.08.05.26359034v1.32","doi-asserted-by":"publisher","DOI":"10.1001\/jama.1982.03320430047030"},{"key":"2026081207450868000_2026.08.05.26359034v1.33","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/81.3.515"},{"key":"2026081207450868000_2026.08.05.26359034v1.34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19425-7"},{"key":"2026081207450868000_2026.08.05.26359034v1.35","doi-asserted-by":"publisher","DOI":"10.1002\/sim.7992"},{"key":"2026081207450868000_2026.08.05.26359034v1.36","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-137"},{"key":"2026081207450868000_2026.08.05.26359034v1.37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2016.02.031"},{"key":"2026081207450868000_2026.08.05.26359034v1.38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.01703"},{"key":"2026081207450868000_2026.08.05.26359034v1.39","doi-asserted-by":"publisher","DOI":"10.1201\/9780429246593"},{"key":"2026081207450868000_2026.08.05.26359034v1.40","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6370"},{"issue":"3","key":"2026081207450868000_2026.08.05.26359034v1.41","first-page":"163","article-title":"Evaluation of survival data and two new rank order statistics arising in its consideration","volume":"50","year":"1966","journal-title":"Cancer Chemother Rep"},{"key":"2026081207450868000_2026.08.05.26359034v1.42","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-13-152"},{"key":"2026081207450868000_2026.08.05.26359034v1.43","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2014.55.2208"},{"key":"2026081207450868000_2026.08.05.26359034v1.44","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4154"},{"key":"2026081207450868000_2026.08.05.26359034v1.45","doi-asserted-by":"publisher","DOI":"10.1002\/sim.2427"},{"key":"2026081207450868000_2026.08.05.26359034v1.46","doi-asserted-by":"publisher","DOI":"10.1198\/016214507000000149"},{"key":"2026081207450868000_2026.08.05.26359034v1.47","doi-asserted-by":"publisher","DOI":"10.1097\/EDE.0b013e3181c30fb2"},{"key":"2026081207450868000_2026.08.05.26359034v1.48","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6428"},{"key":"2026081207450868000_2026.08.05.26359034v1.49","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0258(19990915\/30)18:17\/18<2529::AID-SIM274>3.0.CO;2-5"},{"key":"2026081207450868000_2026.08.05.26359034v1.50","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq134"},{"key":"2026081207450868000_2026.08.05.26359034v1.51","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2026081207450868000_2026.08.05.26359034v1.52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.07874"},{"key":"2026081207450868000_2026.08.05.26359034v1.53","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOAS148"},{"key":"2026081207450868000_2026.08.05.26359034v1.54","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0138-9"},{"key":"2026081207450868000_2026.08.05.26359034v1.55","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2015.04.005"},{"key":"2026081207450868000_2026.08.05.26359034v1.56","doi-asserted-by":"publisher","DOI":"10.1002\/sim.2929"},{"key":"2026081207450868000_2026.08.05.26359034v1.57","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4085"},{"key":"2026081207450868000_2026.08.05.26359034v1.58","doi-asserted-by":"publisher","DOI":"10.1038\/s43018-024-00772-7"},{"key":"2026081207450868000_2026.08.05.26359034v1.59","doi-asserted-by":"publisher","DOI":"10.1038\/nature10983"},{"key":"2026081207450868000_2026.08.05.26359034v1.60","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.1994.12.10.2086"},{"key":"2026081207450868000_2026.08.05.26359034v1.61","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-13-33"},{"key":"2026081207450868000_2026.08.05.26359034v1.62","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-122-3-199502010-00007"},{"key":"2026081207450868000_2026.08.05.26359034v1.63","doi-asserted-by":"publisher","DOI":"10.1016\/j.mayocp.2012.03.009"},{"key":"2026081207450868000_2026.08.05.26359034v1.64","doi-asserted-by":"publisher","DOI":"10.1038\/nature11412"},{"key":"2026081207450868000_2026.08.05.26359034v1.65","doi-asserted-by":"publisher","DOI":"10.1126\/science.aao4572"},{"key":"2026081207450868000_2026.08.05.26359034v1.66","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.00825"},{"key":"2026081207450868000_2026.08.05.26359034v1.67","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2023.03.006"},{"key":"2026081207450868000_2026.08.05.26359034v1.68","doi-asserted-by":"publisher","DOI":"10.1016\/j.anai.2021.03.003"},{"key":"2026081207450868000_2026.08.05.26359034v1.69","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.21.00174"},{"key":"2026081207450868000_2026.08.05.26359034v1.70","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1200694"},{"key":"2026081207450868000_2026.08.05.26359034v1.71","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMc1905518"},{"key":"2026081207450868000_2026.08.05.26359034v1.72","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2201445"},{"key":"2026081207450868000_2026.08.05.26359034v1.73","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1703481"},{"key":"2026081207450868000_2026.08.05.26359034v1.74","doi-asserted-by":"publisher","DOI":"10.1002\/ijc.35347"},{"key":"2026081207450868000_2026.08.05.26359034v1.75","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.2535"},{"key":"2026081207450868000_2026.08.05.26359034v1.76","doi-asserted-by":"publisher","DOI":"10.1038\/s41416-021-01413-x"},{"key":"2026081207450868000_2026.08.05.26359034v1.77","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-019-0116-x"},{"key":"2026081207450868000_2026.08.05.26359034v1.78","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2407417"},{"key":"2026081207450868000_2026.08.05.26359034v1.79","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1801005"},{"key":"2026081207450868000_2026.08.05.26359034v1.80","doi-asserted-by":"publisher","DOI":"10.1016\/j.annonc.2024.07.727"},{"key":"2026081207450868000_2026.08.05.26359034v1.81","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03398-5"},{"key":"2026081207450868000_2026.08.05.26359034v1.82","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-20061-6"},{"key":"2026081207450868000_2026.08.05.26359034v1.83","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkag469"},{"key":"2026081207450868000_2026.08.05.26359034v1.84","doi-asserted-by":"publisher","DOI":"10.1101\/gr.4086505"},{"key":"2026081207450868000_2026.08.05.26359034v1.85","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2010-11-8-r86"},{"key":"2026081207450868000_2026.08.05.26359034v1.86","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-025-00462-9"},{"key":"2026081207450868000_2026.08.05.26359034v1.87","doi-asserted-by":"publisher","DOI":"10.3803\/EnM.2025.2675"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.08.05.26359034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T14:45:15Z","timestamp":1786545915000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.08.05.26359034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,10]]},"references-count":87,"URL":"https:\/\/doi.org\/10.64898\/2026.08.05.26359034","relation":{},"subject":[],"published":{"date-parts":[[2026,8,10]]},"subtype":"preprint"}}