Enhancing Type 2 Diabetes Prediction through Transfer Learning: A Framework for Utilizing Unpaired Clinical and Genetic Data

Enhancing Type 2 Diabetes Prediction through Transfer Learning: A Framework for Utilizing Unpaired Clinical and Genetic Data | 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 Enhancing Type 2 Diabetes Prediction through Transfer Learning: A Framework for Utilizing Unpaired Clinical and Genetic Data YounSung Jung, EunHee Kang, SeanKyo Han, TaeJin Ahn, NanHee Kim, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6208543/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 29 Jul, 2025 Read the published version in Scientific Reports → Version 1 posted 13 You are reading this latest preprint version Abstract The prevalence of type 2 diabetes mellitus (T2DM) in Korea has risen in recent years, yet many cases remain undiagnosed. Advanced artificial intelligence (AI) models using multi-modal data have shown promise in disease prediction, but two major challenges persist: the scarcity of samples containing all desired data modalities and class imbalance in T2DM datasets. We propose a novel transfer learning framework to predict T2DM onset within five years, using two Korean cohorts (KoGES and SNUH). To utilize unpaired multi-modal data, our approach transfers knowledge between clinical and genetic domains, leveraging unpaired clinical data alongside paired data. We also address class imbalance by applying a positively weighted binary cross-entropy (BCE) loss and a weighted random sampler (WRS). The transfer learning framework improved T2DM prediction performance. Using WRS and weighted BCE loss increased the model’s balanced accuracy and AUC (achieving test AUC 0.8441). Furthermore, combining transfer learning with intermediate data fusion yielded even higher performance (test AUC 0.8715). These enhancements were achieved despite limited paired multi-modal samples. Our framework effectively handles scarce paired data and class imbalance, leading to improved T2DM risk prediction. This approach can be adapted to other medical prediction tasks and integrated with additional data modalities, potentially aiding earlier diagnosis and better disease management in clinical settings. Health sciences/Endocrinology/Endocrine system and metabolic diseases/Diabetes/Type 2 diabetes mellitus Biological sciences/Computational biology and bioinformatics Biological sciences/Genetics Full Text Additional Declarations No competing interests reported. Supplementary Files Supplementarytables.docx Cite Share Download PDF Status: Published Journal Publication published 29 Jul, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 07 Apr, 2025 Reviews received at journal 07 Apr, 2025 Reviews received at journal 03 Apr, 2025 Reviewers agreed at journal 01 Apr, 2025 Reviewers agreed at journal 31 Mar, 2025 Reviews received at journal 28 Mar, 2025 Reviewers agreed at journal 28 Mar, 2025 Reviewers agreed at journal 23 Mar, 2025 Reviewers invited by journal 20 Mar, 2025 Editor assigned by journal 20 Mar, 2025 Editor invited by journal 20 Mar, 2025 Submission checks completed at journal 20 Mar, 2025 First submitted to journal 12 Mar, 2025 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-6208543","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":432702390,"identity":"92a9ffdd-10f7-4c0e-b7aa-26ce9d28217c","order_by":0,"name":"YounSung Jung","email":"","orcid":"","institution":"Handong Global University","correspondingAuthor":false,"prefix":"","firstName":"YounSung","middleName":"","lastName":"Jung","suffix":""},{"id":432702391,"identity":"86fd5de2-2981-4005-accb-d4ab2ebad423","order_by":1,"name":"EunHee Kang","email":"","orcid":"","institution":"Handong Global University","correspondingAuthor":false,"prefix":"","firstName":"EunHee","middleName":"","lastName":"Kang","suffix":""},{"id":432702392,"identity":"949923ae-a46a-43c3-844b-46efbca0398a","order_by":2,"name":"SeanKyo Han","email":"","orcid":"","institution":"Handong Global University","correspondingAuthor":false,"prefix":"","firstName":"SeanKyo","middleName":"","lastName":"Han","suffix":""},{"id":432702393,"identity":"1e8d6e62-c1a8-46b2-bb25-a3f7836c4ec5","order_by":3,"name":"TaeJin Ahn","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+klEQVRIiWNgGAWjYJACgwQQwcB8DEgxQ4R48CjnQWhhSyNeC8QqBh4z4rTYsx8+UPBwB4O8uXTPtwc/d1jLmfMvYHzwtg2PLTxpCQaJZxgMd845u92w90y6seWMB8yGc/FpYcgxMEhsY2DccCN3mwRv2+HEDTcOsEnz4tPC//4DSIv9hhs5zyT/QrSw/8arRSKHAaQFqDIHZDhQy/kGNma8Wm48AzlMInnDjTQzadm2dGODG4zNknPO4dbC3p/8zPBnm43thhvJzyTftlnLGZw/fPDDmzLcWoCAzYCBQQKJL5HYgFc9EDA/QOXzHyCkYxSMglEwCkYYAAAp+VLWIK+PmwAAAABJRU5ErkJggg==","orcid":"","institution":"Handong Global University","correspondingAuthor":true,"prefix":"","firstName":"TaeJin","middleName":"","lastName":"Ahn","suffix":""},{"id":432702394,"identity":"bfbca9ee-d931-48f3-8ab0-c87fc5b1ef88","order_by":4,"name":"NanHee Kim","email":"","orcid":"","institution":"Korea University Ansan Hospital","correspondingAuthor":false,"prefix":"","firstName":"NanHee","middleName":"","lastName":"Kim","suffix":""},{"id":432702395,"identity":"202d9d3a-cad9-4362-b24f-ba9c147efb02","order_by":5,"name":"SoYoung Park","email":"","orcid":"","institution":"Korea University Ansan Hospital","correspondingAuthor":false,"prefix":"","firstName":"SoYoung","middleName":"","lastName":"Park","suffix":""},{"id":432702396,"identity":"62c35a90-891d-4555-acde-62cee2d15370","order_by":6,"name":"MinHee Kim","email":"","orcid":"","institution":"Korea University Ansan Hospital","correspondingAuthor":false,"prefix":"","firstName":"MinHee","middleName":"","lastName":"Kim","suffix":""}],"badges":[],"createdAt":"2025-03-12 04:53:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6208543/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6208543/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-05532-w","type":"published","date":"2025-07-29T16:13:36+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":88268387,"identity":"14bf4267-a7e6-4fdd-bd77-5b9f30781066","added_by":"auto","created_at":"2025-08-04 16:51:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2254435,"visible":true,"origin":"","legend":"","description":"","filename":"revisedmanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6208543/v1_covered_cd12dbce-3114-4967-95bb-8591011def13.pdf"},{"id":79071532,"identity":"1e97a1da-098e-4299-bbf7-db9c60e99a48","added_by":"auto","created_at":"2025-03-24 06:15:09","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":36378,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementarytables.docx","url":"https://assets-eu.researchsquare.com/files/rs-6208543/v1/c2715ab0c4ba3128864ebe7a.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing Type 2 Diabetes Prediction through Transfer Learning: A Framework for Utilizing Unpaired Clinical and Genetic Data","fulltext":[],"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":true,"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-6208543/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6208543/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The prevalence of type 2 diabetes mellitus (T2DM) in Korea has risen in recent years, yet many cases remain undiagnosed. Advanced artificial intelligence (AI) models using multi-modal data have shown promise in disease prediction, but two major challenges persist: the scarcity of samples containing all desired data modalities and class imbalance in T2DM datasets. We propose a novel transfer learning framework to predict T2DM onset within five years, using two Korean cohorts (KoGES and SNUH). To utilize unpaired multi-modal data, our approach transfers knowledge between clinical and genetic domains, leveraging unpaired clinical data alongside paired data. We also address class imbalance by applying a positively weighted binary cross-entropy (BCE) loss and a weighted random sampler (WRS). The transfer learning framework improved T2DM prediction performance. Using WRS and weighted BCE loss increased the model’s balanced accuracy and AUC (achieving test AUC 0.8441). Furthermore, combining transfer learning with intermediate data fusion yielded even higher performance (test AUC 0.8715). These enhancements were achieved despite limited paired multi-modal samples. Our framework effectively handles scarce paired data and class imbalance, leading to improved T2DM risk prediction. This approach can be adapted to other medical prediction tasks and integrated with additional data modalities, potentially aiding earlier diagnosis and better disease management in clinical settings.","manuscriptTitle":"Enhancing Type 2 Diabetes Prediction through Transfer Learning: A Framework for Utilizing Unpaired Clinical and Genetic Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-24 06:07:05","doi":"10.21203/rs.3.rs-6208543/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-07T13:08:42+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-07T05:41:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-03T06:57:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"109592380103747090223586476758065180824","date":"2025-04-01T10:13:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"43452185635503459580311561734646633313","date":"2025-04-01T01:20:10+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-28T13:04:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"98557361160041165609361484683091738172","date":"2025-03-28T06:29:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"185026286997675688292586288037334298488","date":"2025-03-23T10:04:55+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-21T00:33:55+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-21T00:26:58+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-03-20T12:43:09+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-20T05:01:22+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-03-12T04:42:02+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":"7d7040b1-790f-4fd2-8407-2a65b0348153","owner":[],"postedDate":"March 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":46081883,"name":"Health sciences/Endocrinology/Endocrine system and metabolic diseases/Diabetes/Type 2 diabetes mellitus"},{"id":46081884,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":46081885,"name":"Biological sciences/Genetics"}],"tags":[],"updatedAt":"2025-08-04T16:45:17+00:00","versionOfRecord":{"articleIdentity":"rs-6208543","link":"https://doi.org/10.1038/s41598-025-05532-w","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-07-29 16:13:36","publishedOnDateReadable":"July 29th, 2025"},"versionCreatedAt":"2025-03-24 06:07:05","video":"","vorDoi":"10.1038/s41598-025-05532-w","vorDoiUrl":"https://doi.org/10.1038/s41598-025-05532-w","workflowStages":[]},"version":"v1","identity":"rs-6208543","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6208543","identity":"rs-6208543","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}