A comparison of machine learning methods to predict survival times for cancer patients: Incorporating time-varying covariates

A comparison of machine learning methods to predict survival times for cancer patients: Incorporating time-varying covariates | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article A comparison of machine learning methods to predict survival times for cancer patients: Incorporating time-varying covariates Steve Cygu, Hsien Seow, Jonathan Dushoff, Benjamin M. Bolker This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-1875351/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 25 Jan, 2023 Read the published version in Scientific Reports → Version 1 posted 9 You are reading this latest preprint version Abstract The Cox proportional hazard model is commonly used in evaluating risk factors in cancer survival data. The model assumes an additive, linear relationship between the risk factors and the log hazard. However, this assumption may be too simplistic. Further, failure to take time-varying covariates into account, if present, may lower prediction accuracy. In this retrospective, population-based, prognostic study of data from patients diagnosed with cancer from 2008 to 2015 in Ontario, Canada, we applied machine learning-based time-to-event prediction methods and compared their predictive performance in two sets of analyses: 1) yearly-cohort-based time-invariant and 2) fully time-varying covariates analysis. Machine learning-based methods — gradient boosting model (gbm), random survival forest (rsf), elastic net (enet), lasso, ridge, and deepsurv neural network (nnet) — were compared to the traditional Cox proportional hazard (coxph) model and the prior study which used the yearly-cohort-based time-invariant analysis. Using Harrell's C index as our primary measure, we found that using both machine-learning techniques and incorporating time-dependent covariates can improve predictive performance. Gradient boosting machine showed the best performance on test data in both time-invariant and time-varying covariates analysis. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 25 Jan, 2023 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Major revision 16 Sep, 2022 Reviews received at journal 25 Aug, 2022 Reviewers agreed at journal 16 Aug, 2022 Reviewers agreed at journal 16 Aug, 2022 Reviewers invited by journal 16 Aug, 2022 Editor assigned by journal 16 Aug, 2022 Editor invited by journal 28 Jul, 2022 Submission checks completed at journal 28 Jul, 2022 First submitted to journal 19 Jul, 2022 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-1875351","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":124544492,"identity":"1e81f953-6b69-4b03-acd7-073ff36e1957","order_by":0,"name":"Steve Cygu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1UlEQVRIiWNgGAWjYJACZgYDIGRvADINLEjRwnMApEWCWC1AtQwSCSA2EVr4Z6Rfky4osDPml3x+dcOPAgkG/vbuBLxaJG7klEnPMEg2k5ydU3azB+gwiTNnN+DVYiCRkybNY3DAxuB2TtoNHqAWA4lcYrXcPJN28w9xWtKPgbSYGdxgP3abKFskzrxhtgb6xViyJ4fttoyBBA9Bv/C3pz+8XfDHzrCf/fizm2/+2Mjxt/fi18IgkGMAZfGAGTz4lYOtOf4AymJ/gEvNKBgFo2AUjHAAAAGhQxmyaQBbAAAAAElFTkSuQmCC","orcid":"","institution":"McMaster University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Steve","middleName":"","lastName":"Cygu","suffix":""},{"id":124544493,"identity":"c5eccfff-17a6-4afc-b0c0-936b82f07328","order_by":1,"name":"Hsien Seow","email":"","orcid":"","institution":"McMaster University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Hsien","middleName":"","lastName":"Seow","suffix":""},{"id":124544494,"identity":"64f35113-b5d9-473d-85e9-2ae9346e7721","order_by":2,"name":"Jonathan Dushoff","email":"","orcid":"","institution":"McMaster University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jonathan","middleName":"","lastName":"Dushoff","suffix":""},{"id":124544495,"identity":"89a2d01a-e830-4340-a566-ce58da6dee39","order_by":3,"name":"Benjamin M. Bolker","email":"","orcid":"","institution":"McMaster University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Benjamin","middleName":"M.","lastName":"Bolker","suffix":""}],"badges":[],"createdAt":"2022-07-19 19:44:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-1875351/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-1875351/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-023-28393-7","type":"published","date":"2023-01-25T18:29:29+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":24608317,"identity":"4cf59fbe-553a-44ac-aa05-6fe1ad1f0b36","added_by":"auto","created_at":"2022-08-01 16:43:10","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":447292,"visible":true,"origin":"","legend":"","description":"","filename":"submission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1875351/v1_covered.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A comparison of machine learning methods to predict survival times for cancer patients: Incorporating time-varying covariates","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-1875351/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-1875351/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-1875351/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The Cox proportional hazard model is commonly used in evaluating risk factors in cancer survival data. The model assumes an additive, linear relationship between the risk factors and the log hazard. However, this assumption may be too simplistic. Further, failure to take time-varying covariates into account, if present, may lower prediction accuracy. In this retrospective, population-based, prognostic study of data from patients diagnosed with cancer from 2008 to 2015 in Ontario, Canada, we applied machine learning-based time-to-event prediction methods and compared their predictive performance in two sets of analyses: 1) yearly-cohort-based time-invariant and 2) fully time-varying covariates analysis. Machine learning-based methods — gradient boosting model (gbm), random survival forest (rsf), elastic net (enet), lasso, ridge, and deepsurv neural network (nnet) — were compared to the traditional Cox proportional hazard (coxph) model and the prior study which used the yearly-cohort-based time-invariant analysis. Using Harrell's C index as our primary measure, we found that using both machine-learning techniques and incorporating time-dependent covariates can improve predictive performance. Gradient boosting machine showed the best performance on test data in both time-invariant and time-varying covariates analysis.","manuscriptTitle":"A comparison of machine learning methods to predict survival times for cancer patients: Incorporating time-varying covariates","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-08-01 16:43:05","doi":"10.21203/rs.3.rs-1875351/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2022-09-16T05:05:40+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2022-08-25T22:24:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"4ffa55f7-b557-4af2-9643-b27a665ebd92","date":"2022-08-17T03:41:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"d2729f65-6e26-4e14-bdb7-e685c6f7aacb","date":"2022-08-16T15:49:31+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2022-08-16T15:39:23+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2022-08-16T15:29:37+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2022-07-28T05:03:50+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2022-07-28T04:59:09+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2022-07-19T19:42:48+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"84822b8f-cc64-40a6-a82a-ed823d3c0c83","owner":[],"postedDate":"August 1st, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2023-10-16T18:34:58+00:00","versionOfRecord":{"articleIdentity":"rs-1875351","link":"https://doi.org/10.1038/s41598-023-28393-7","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2023-01-25 18:29:29","publishedOnDateReadable":"January 25th, 2023"},"versionCreatedAt":"2022-08-01 16:43:05","video":"","vorDoi":"10.1038/s41598-023-28393-7","vorDoiUrl":"https://doi.org/10.1038/s41598-023-28393-7","workflowStages":[]},"version":"v1","identity":"rs-1875351","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-1875351","identity":"rs-1875351","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}