Med-gte-hybrid: A contextual embedding modelfor extracting narrative information from clinical texts

Med-gte-hybrid: A contextual embedding modelfor extracting narrative information from clinical texts | 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 Med-gte-hybrid: A contextual embedding modelfor extracting narrative information from clinical texts Aditya Kumar, Simon Rauch, Mario Cypko, Oliver Amft This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5167581/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 The extraction of actionable information from unstructured clinical narrativesis a crucial step toward advancing predictive healthcare, particularly for chronicdiseases such as Chronic Kidney Disease (CKD). We present an approach toextract narrative information using a sentence transformer that generates robustembeddings for clinical text, enabling a range of downstream tasks, includingprognosis, mortality prediction, and estimation of kidney function using esti-mated glomerular filtration rate (eGFR). We selected gte-large, a high-performingsentence transformer, as the base model. Through a novel fine-tuning strategythat combines contrastive learning with denoising autoencoder-based approach,we significantly enhance the model’s ability to capture subtle patterns in clinicaltext data. The fine-tuned model, med-gte-hybrid, enables improved patient strati-fication, clustering, and prediction, outperforming current state-of-the-art modelsin key tasks. While CKD is the current focus, the approach is designed to begeneralizable across other medical domains offering the potential to improve clin-ical decision-making and personalized treatment pathways in various healthcarecontexts. Health sciences/Health care Physical sciences/Mathematics and computing/Computer science Health sciences/Medical research/Experimental models of disease Chronic kidney disease sentence transformers contrastive learning prognostic modelling mortality risk prediction eGFR prediction unstructured clinical data embedding models patient stratification information retrieval digital medicine healthcare AI Full Text Additional Declarations No competing interests reported. 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-5167581","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":362845828,"identity":"1685b8e7-89ce-497a-ba0f-7d5e0908bf1a","order_by":0,"name":"Aditya Kumar","email":"data:image/png;base64,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","orcid":"","institution":"Hahn-Schickard-Gesellschaft für angewandte Forschung","correspondingAuthor":true,"prefix":"","firstName":"Aditya","middleName":"","lastName":"Kumar","suffix":""},{"id":362845829,"identity":"70093ada-0d0b-4d59-916e-d67d46ebcef9","order_by":1,"name":"Simon Rauch","email":"","orcid":"","institution":"Hahn-Schickard-Gesellschaft für angewandte Forschung","correspondingAuthor":false,"prefix":"","firstName":"Simon","middleName":"","lastName":"Rauch","suffix":""},{"id":362845830,"identity":"220be5a1-7bac-4aff-8e6e-f2a93c1741c8","order_by":2,"name":"Mario Cypko","email":"","orcid":"","institution":"Hahn-Schickard-Gesellschaft für angewandte Forschung","correspondingAuthor":false,"prefix":"","firstName":"Mario","middleName":"","lastName":"Cypko","suffix":""},{"id":362845831,"identity":"7ec11752-1a9c-4b6d-bbc3-4a9c60474db3","order_by":3,"name":"Oliver Amft","email":"","orcid":"","institution":"Hahn-Schickard-Gesellschaft für angewandte Forschung","correspondingAuthor":false,"prefix":"","firstName":"Oliver","middleName":"","lastName":"Amft","suffix":""}],"badges":[],"createdAt":"2024-09-27 22:38:08","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-5167581/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5167581/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78319410,"identity":"41ecaefe-d3fd-4756-a097-695f24b74345","added_by":"auto","created_at":"2025-03-12 04:48:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5403120,"visible":true,"origin":"","legend":"","description":"","filename":"article.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5167581/v1_covered_7c9e4c67-fb1f-42c7-9115-da9cdd0dcac4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Med-gte-hybrid: A contextual embedding modelfor extracting narrative information from clinical texts","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"Chronic kidney disease, sentence transformers, contrastive learning, prognostic modelling, mortality risk prediction, eGFR prediction, unstructured clinical data, embedding models, patient stratification, information retrieval, digital medicine, healthcare AI","lastPublishedDoi":"10.21203/rs.3.rs-5167581/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5167581/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The extraction of actionable information from unstructured clinical narrativesis a crucial step toward advancing predictive healthcare, particularly for chronicdiseases such as Chronic Kidney Disease (CKD). We present an approach toextract narrative information using a sentence transformer that generates robustembeddings for clinical text, enabling a range of downstream tasks, includingprognosis, mortality prediction, and estimation of kidney function using esti-mated glomerular filtration rate (eGFR). We selected gte-large, a high-performingsentence transformer, as the base model. Through a novel fine-tuning strategythat combines contrastive learning with denoising autoencoder-based approach,we significantly enhance the model’s ability to capture subtle patterns in clinicaltext data. The fine-tuned model, med-gte-hybrid, enables improved patient strati-fication, clustering, and prediction, outperforming current state-of-the-art modelsin key tasks. While CKD is the current focus, the approach is designed to begeneralizable across other medical domains offering the potential to improve clin-ical decision-making and personalized treatment pathways in various healthcarecontexts.","manuscriptTitle":"Med-gte-hybrid: A contextual embedding modelfor extracting narrative information from clinical texts","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-12 04:48:44","doi":"10.21203/rs.3.rs-5167581/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":"1bc7641b-25dd-444c-9d17-a09f55017cc1","owner":[],"postedDate":"March 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":38595164,"name":"Health sciences/Health care"},{"id":38595165,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":38595166,"name":"Health sciences/Medical research/Experimental models of disease"}],"tags":[],"updatedAt":"2025-03-12T04:48:44+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-12 04:48:44","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5167581","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5167581","identity":"rs-5167581","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}