STRATA-PC: A Treatment-Aware, Outcome-Guided Deep Learning Framework for Prostate Cancer Risk Stratification

STRATA-PC: A Treatment-Aware, Outcome-Guided Deep Learning Framework for Prostate Cancer Risk Stratification | 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 Research Article STRATA-PC: A Treatment-Aware, Outcome-Guided Deep Learning Framework for Prostate Cancer Risk Stratification Arman Ghavidel, Pilar Pazos, Hyoshin J. Park, John Seems This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9490581/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Prostate cancer risk prediction remains challenged by the inability to reliably distinguish indolent from aggressive disease, leading to overtreatment or undertreatment. Conventional approaches based on prostate-specific antigen (PSA) and digital rectal examination (DRE) rely on static thresholds or baseline models, failing to capture longitudinal disease dynamics, treatment context, and calibrated risk estimation. a treatment-aware, survival-informed deep learning framework for phenotyping from irregular longitudinal clinical data. The proposed method employs a mask-aware Transformer encoder to model PSA/DRE sequences with irregular sampling, fused with static clinical features to learn a shared latent representation. This representation is optimized through a multi-task learning framework that jointly incorporates survival prediction, discrete-time hazard modeling for calibrated risk estimation, treatment supervision to encode therapeutic context, and outcome-guided deep embedded clustering using Gaussian mixtures (DEC–GMM). Applied to 4,579 men from the PLCO trial, STRATA-PC achieved strong prognostic discrimination (C-index 0.778 for overall survival and 0.853 for prostate cancer–specific mortality) with consistent calibration at 5- and 10-year horizons. Outcome-guided clustering improved latent-space separation (silhouette > 0.15) and stability across refits, while maintaining well-calibrated survival predictions. The learned latent representations consistently separated into three reproducible phenotypes that were robust to missingness patterns and aligned with treatment exposure, indicating that the framework captures meaningful variation in longitudinal disease trajectories and associated outcomes. By integrating longitudinal modeling, treatment-aware supervision, calibrated survival prediction, and mixture-based clustering within a unified framework, STRATA-PC provides a robust approach for outcome-guided phenotyping from sparse clinical time series. Artificial Intelligence and Machine Learning Prostate cancer Risk stratification Longitudinal PSA/DRE Deep learning Outcome-guided clustering Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted 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-9490581","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":627427737,"identity":"d06792bb-06d7-478e-9796-4c273d655380","order_by":0,"name":"Arman Ghavidel","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxklEQVRIiWNgGAWjYFACHiA2kODhB5JAFjOxWipsZCQbSNNyJs3G4ACxWvj71x78zNt2mMf4ePM2CYYK68QGQlokbrxLlgZpMTtzrEyC4Uw6YS0MN84YSM4EabmRYybB2HaYsBb5G2eMf4K0GM8AaflHhBaD8z1mEh/OpPEYSIC0NBChxfAGj5nFhwobHokzx4otEo6lGxPUInf+jPGNBAMJe/725o03PtRYyxLUwiCRgMRJwKEIFfAfIErZKBgFo2AUjGQAAJfxP1Gw8jcYAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0003-9798-8958","institution":"Old Dominion University","correspondingAuthor":true,"prefix":"","firstName":"Arman","middleName":"","lastName":"Ghavidel","suffix":""},{"id":627427738,"identity":"1d4d4763-9d8c-4da1-a5cc-2a24ea26400c","order_by":1,"name":"Pilar Pazos","email":"","orcid":"","institution":"Old Dominion University","correspondingAuthor":false,"prefix":"","firstName":"Pilar","middleName":"","lastName":"Pazos","suffix":""},{"id":627427739,"identity":"4a05eb92-22d8-4b29-908e-7cf21d67b151","order_by":2,"name":"Hyoshin J. Park","email":"","orcid":"","institution":"Old Dominion University","correspondingAuthor":false,"prefix":"","firstName":"Hyoshin","middleName":"J.","lastName":"Park","suffix":""},{"id":627427926,"identity":"0a68ce54-cd0b-4177-a149-0bd5a7b565eb","order_by":3,"name":"John Seems","email":"","orcid":"","institution":"Old Dominion University","correspondingAuthor":false,"prefix":"","firstName":"John","middleName":"","lastName":"Seems","suffix":""}],"badges":[],"createdAt":"2026-04-22 04:13:55","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9490581/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9490581/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107706925,"identity":"6bc35dfd-11f3-4dc9-b5a5-f9c48cc2b982","added_by":"auto","created_at":"2026-04-24 09:19:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":872913,"visible":true,"origin":"","legend":"","description":"","filename":"Preprintfinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9490581/v1_covered_ea542597-e441-4ee8-bfdc-79c53f13834e.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eSTRATA-PC: A Treatment-Aware, Outcome-Guided Deep Learning Framework for Prostate Cancer Risk Stratification\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Old Dominion University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Prostate cancer, Risk stratification, Longitudinal PSA/DRE, Deep learning, Outcome-guided clustering","lastPublishedDoi":"10.21203/rs.3.rs-9490581/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9490581/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eProstate cancer risk prediction remains challenged by the inability to reliably distinguish indolent from aggressive disease, leading to overtreatment or undertreatment. Conventional approaches based on prostate-specific antigen (PSA) and digital rectal examination (DRE) rely on static thresholds or baseline models, failing to capture longitudinal disease dynamics, treatment context, and calibrated risk estimation. a treatment-aware, survival-informed deep learning framework for phenotyping from irregular longitudinal clinical data. The proposed method employs a mask-aware Transformer encoder to model PSA/DRE sequences with irregular sampling, fused with static clinical features to learn a shared latent representation. This representation is optimized through a multi-task learning framework that jointly incorporates survival prediction, discrete-time hazard modeling for calibrated risk estimation, treatment supervision to encode therapeutic context, and outcome-guided deep embedded clustering using Gaussian mixtures (DEC\u0026ndash;GMM). Applied to 4,579 men from the PLCO trial, STRATA-PC achieved strong prognostic discrimination (C-index 0.778 for overall survival and 0.853 for prostate cancer\u0026ndash;specific mortality) with consistent calibration at 5- and 10-year horizons. Outcome-guided clustering improved latent-space separation (silhouette\u0026thinsp;\u0026gt;\u0026thinsp;0.15) and stability across refits, while maintaining well-calibrated survival predictions. The learned latent representations consistently separated into three reproducible phenotypes that were robust to missingness patterns and aligned with treatment exposure, indicating that the framework captures meaningful variation in longitudinal disease trajectories and associated outcomes. By integrating longitudinal modeling, treatment-aware supervision, calibrated survival prediction, and mixture-based clustering within a unified framework, STRATA-PC provides a robust approach for outcome-guided phenotyping from sparse clinical time series.\u003c/p\u003e","manuscriptTitle":"STRATA-PC: A Treatment-Aware, Outcome-Guided Deep Learning Framework for Prostate Cancer Risk Stratification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-23 04:21:59","doi":"10.21203/rs.3.rs-9490581/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"10cecbc6-2a3a-4c75-9099-d35eb9dcf01b","owner":[],"postedDate":"April 23rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":66778543,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-04-23T04:22:00+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-23 04:21:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9490581","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9490581","identity":"rs-9490581","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}