{"paper_id":"21dbdfa9-f6bb-4d5c-885a-bae16b7ee9b3","body_text":"Markovian Representation Learning for Longitudinal Electronic Health Records | 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 Markovian Representation Learning for Longitudinal Electronic Health Records Samuel Lawrence, Yuchen Zhang, Mingyu Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8935515/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 Deep learning models for electronic health records are typically trained with token-level reconstruction or task-specific supervision, encouraging contextual predictability rather than explicit modeling of temporal dynamics. We propose a Markovian representation learning framework that treats longitudinal EHR data as realizations of a latent stochastic process and trains embeddings to admit low-complexity transition operators in latent space. By optimizing transition likelihood alongside information-preserving objectives, the learned representations approximate sufficient statistics of underlying clinical state, yielding compact dynamical modes with interpretable time scales. Across multiple prediction tasks and external hospital transfer settings, Markov-structured pretraining improves discrimination, temporal forecasting performance, and robustness relative to supervised and masked-event baselines. We further demonstrate that the learned transition structure supports LLM-assisted summarization and agentic cohort exploration, enabling clinician-friendly interpretation of latent progression patterns. These results suggest that explicitly modeling temporal transition structure provides a principled complement to token-centric foundation modeling for longitudinal medical data. Markov Processes Foundation Models 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-8935515\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":594967951,\"identity\":\"279ba095-fd6c-4264-abcc-2fc1c95a701b\",\"order_by\":0,\"name\":\"Samuel Lawrence\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/ElEQVRIie2QsWoCQRCGZ1nQxmi7FnKvMHIgguKz7HKgTR5gixQXFtYmLxDyDIKVtcdCqiN2ImyKPfIClleFLASDFgOWKfarZpb5mPkXIJH4j3QHTZA4v7RTAMHKWHBa4T2OQS8vrbhL6QxD7a6V33fSyMyDQ2UPGR5dgFYLtXkzz2fQM1USCrq+Csr68dYvkb3UQu0+KyOgXtEKhzxu8RL9I3Bmo3JSpWDWkUpmYCKU/bhRTMu+aQVcbyJkvb9RbPw0WkHXKVDqYvwas1QxSx6z2Kl8X+XkYWtTNS0usr4vmtDq+Wjn11+n89NsRB52zf6vkveMJxKJRILkB36AYBhVOceyAAAAAElFTkSuQmCC\",\"orcid\":\"\",\"institution\":\"Columbia University\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Samuel\",\"middleName\":\"\",\"lastName\":\"Lawrence\",\"suffix\":\"\"},{\"id\":594967962,\"identity\":\"3987dbf1-c8df-4fb4-a09f-df4f7c766ce4\",\"order_by\":1,\"name\":\"Yuchen Zhang\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Tsinghua University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Yuchen\",\"middleName\":\"\",\"lastName\":\"Zhang\",\"suffix\":\"\"},{\"id\":594968155,\"identity\":\"3048f295-5a87-4be5-95cc-2d2b46590b0c\",\"order_by\":2,\"name\":\"Mingyu Wang\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Tsinghua University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Mingyu\",\"middleName\":\"\",\"lastName\":\"Wang\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2026-02-21 20:02:46\",\"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-8935515/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-8935515/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":103505463,\"identity\":\"a3380145-ffd7-4c36-b692-4ddd06d7f16e\",\"added_by\":\"auto\",\"created_at\":\"2026-02-26 13:31:17\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":269442,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"20269HealthFM5.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8935515/v1_covered_201d35de-ebc9-4d00-a1d7-d4f7cb0a8a4d.pdf\"}],\"financialInterests\":\"The authors declare no competing interests.\",\"formattedTitle\":\"\\u003cp\\u003eMarkovian Representation Learning for Longitudinal Electronic Health Records\\u003c/p\\u003e\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":true,\"hideJournal\":true,\"highlight\":\"\",\"institution\":\"Columbia University\",\"isAcceptedByJournal\":false,\"isAuthorSuppliedPdf\":true,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":true,\"isPdf\":true,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"Markov Processes, Foundation Models\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-8935515/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-8935515/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eDeep learning models for electronic health records are typically trained with token-level reconstruction or task-specific supervision, encouraging contextual predictability rather than explicit modeling of temporal dynamics. We propose a Markovian representation learning framework that treats longitudinal EHR data as realizations of a latent stochastic process and trains embeddings to admit low-complexity transition operators in latent space. By optimizing transition likelihood alongside information-preserving objectives, the learned representations approximate sufficient statistics of underlying clinical state, yielding compact dynamical modes with interpretable time scales. Across multiple prediction tasks and external hospital transfer settings, Markov-structured pretraining improves discrimination, temporal forecasting performance, and robustness relative to supervised and masked-event baselines. We further demonstrate that the learned transition structure supports LLM-assisted summarization and agentic cohort exploration, enabling clinician-friendly interpretation of latent progression patterns. These results suggest that explicitly modeling temporal transition structure provides a principled complement to token-centric foundation modeling for longitudinal medical data.\\u003c/p\\u003e\",\"manuscriptTitle\":\"Markovian Representation Learning for Longitudinal Electronic Health Records\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2026-02-24 02:46:52\",\"doi\":\"10.21203/rs.3.rs-8935515/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"6deba287-e087-4518-8bdc-a6a22962ec24\",\"owner\":[],\"postedDate\":\"February 24th, 2026\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2026-02-24T02:46:52+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2026-02-24 02:46:52\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-8935515\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-8935515\",\"identity\":\"rs-8935515\",\"version\":[\"v1\"]},\"buildId\":\"XKTyCvWXoU3ODBz1xrDgd\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}