A domain-agnostic continual multi-task learning model for generalized glucose level and hypoglycemia event prediction

A domain-agnostic continual multi-task learning model for generalized glucose level and hypoglycemia event prediction | 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 domain-agnostic continual multi-task learning model for generalized glucose level and hypoglycemia event prediction Minjoo Hwang, Vega Pradana Rachim, Junyoung Yoo, Yein Lee, Sung-Min Park This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6576039/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Oct, 2025 Read the published version in npj Digital Medicine → Version 1 posted 10 You are reading this latest preprint version Abstract Continuous prediction of blood glucose levels and hypoglycemia events is critical for managing type 1 diabetes mellitus (T1DM), particularly under intensive insulin therapy. Existing models focus on a single task, limiting their practicality and adaptability in automated insulin delivery (AID) systems. To address, a domain-agnostic continual multi-task learning (DA-CMTL) model is proposed to perform both tasks within a unified framework. Trained on simulated datasets via Sim2Real transfer and adapted using elastic weight consolidation, DA-CMTL supports generalization across domains. On public datasets (DiaTrend, OhioT1DM, and ShanghaiT1DM), DA-CMTL achieved a root mean squared error of 14.19 mg/dL, mean absolute error of 10.09 mg/dL, and sensitivity/specificity of 89.28%/94.09% for early hypoglycemia detection. Real-world validation using type 2 diabetes-induced rats demonstrated a reduction in time below range from 3.01–2.58%, supporting reliable integration as a safety layer in AID systems. These results highlight DA-CMTL’s robustness, scalability, and potential to improve safety in AID. Health sciences/Health care/Disease prevention/Preventive medicine Health sciences/Endocrinology/Endocrine system and metabolic diseases/Diabetes/Type 1 diabetes mellitus Full Text Additional Declarations Competing interest reported. V.P.R. and S.M.P. are Curestream employees and share holders. M.H., J.Y. and Y.L. have no conflicts of interest to disclose for publication of this paper. Cite Share Download PDF Status: Published Journal Publication published 16 Oct, 2025 Read the published version in npj Digital Medicine → Version 1 posted Reviewers agreed at journal 29 May, 2025 Reviewers agreed at journal 28 May, 2025 Reviewers agreed at journal 28 May, 2025 Reviewers agreed at journal 27 May, 2025 Reviewers agreed at journal 27 May, 2025 Reviewers agreed at journal 27 May, 2025 Reviewers invited by journal 27 May, 2025 Editor assigned by journal 26 May, 2025 Submission checks completed at journal 26 May, 2025 First submitted to journal 02 May, 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-6576039","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":463848738,"identity":"ca2d3845-f6ec-40dc-8112-f1cb2b5db85b","order_by":0,"name":"Minjoo Hwang","email":"","orcid":"","institution":"Graduate School of Artificial Intelligence, Pohang University of Science and Technology (POSTECH)","correspondingAuthor":false,"prefix":"","firstName":"Minjoo","middleName":"","lastName":"Hwang","suffix":""},{"id":463848741,"identity":"3683c351-e3fa-4755-8696-12dd7fc3f5ba","order_by":1,"name":"Vega Pradana Rachim","email":"","orcid":"","institution":"Department of Convergence IT Engineering, Pohang University of Science and Technology (POSTECH)","correspondingAuthor":false,"prefix":"","firstName":"Vega","middleName":"Pradana","lastName":"Rachim","suffix":""},{"id":463848742,"identity":"b2766839-fded-4336-b5a8-ba14f12c50ab","order_by":2,"name":"Junyoung Yoo","email":"","orcid":"","institution":"Department of Convergence IT Engineering, Pohang University of Science and Technology (POSTECH)","correspondingAuthor":false,"prefix":"","firstName":"Junyoung","middleName":"","lastName":"Yoo","suffix":""},{"id":463848744,"identity":"b1e831bb-0806-4371-99d8-7858986cab72","order_by":3,"name":"Yein Lee","email":"","orcid":"","institution":"Department of Convergence IT Engineering, Pohang University of Science and Technology (POSTECH)","correspondingAuthor":false,"prefix":"","firstName":"Yein","middleName":"","lastName":"Lee","suffix":""},{"id":463848746,"identity":"e533d242-7d8a-4627-a7cb-9795cb38dc81","order_by":4,"name":"Sung-Min Park","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCklEQVRIiWNgGAWjYNACAxDBxvgAwuNBiBHSwgyiJIjUAgZsbBJEaZGfkXv41Y2CO3n8s4+lVRdU1NXxs589wPCjhsHYvAGHk27kpVnnGDwrljiXduz2jDOHJSR78hIYe44xmMkcwKFFIsfMOMfgcGLDGfa227xtByQMbvAYMPA2MNhI4HQYVMt8oJZi3rY6CXugFsa/eLQw3MgxfgzSsuEM2zFm3jZmCQMJHgNmoC1muLQYnHljxgzUUmx4hi1ZGugXyRlngFyZYxLGOB3WnmP8OefP4Ty5M2yGn4Ehxs/ffsbw4ZsaG8MZuBwGjA+QcQkgFjNM6AA4fnAD5g8YWkbBKBgFo2AUIAMABBJUcxNVhv8AAAAASUVORK5CYII=","orcid":"","institution":"Department of Convergence IT Engineering, Pohang University of Science and Technology (POSTECH)","correspondingAuthor":true,"prefix":"","firstName":"Sung-Min","middleName":"","lastName":"Park","suffix":""}],"badges":[],"createdAt":"2025-05-02 06:53:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6576039/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6576039/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41746-025-01994-4","type":"published","date":"2025-10-16T15:57:34+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93956720,"identity":"1cbda9c4-ab38-40c8-88ac-495865876d96","added_by":"auto","created_at":"2025-10-20 16:11:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1239598,"visible":true,"origin":"","legend":"","description":"","filename":"npjdigitalmedicinemanuscriptv1.1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6576039/v1_covered_2e2bfa58-f3e0-42b1-bcec-cfcc8cfb5700.pdf"}],"financialInterests":"Competing interest reported. V.P.R. and S.M.P. are Curestream employees and share holders. \nM.H., J.Y. and Y.L. have no conflicts of interest to disclose for publication of this paper.","formattedTitle":"A domain-agnostic continual multi-task learning model for generalized glucose level and hypoglycemia event prediction","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":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6576039/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6576039/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eContinuous prediction of blood glucose levels and hypoglycemia events is critical for managing type 1 diabetes mellitus (T1DM), particularly under intensive insulin therapy. Existing models focus on a single task, limiting their practicality and adaptability in automated insulin delivery (AID) systems. To address, a domain-agnostic continual multi-task learning (DA-CMTL) model is proposed to perform both tasks within a unified framework. Trained on simulated datasets via Sim2Real transfer and adapted using elastic weight consolidation, DA-CMTL supports generalization across domains. On public datasets (DiaTrend, OhioT1DM, and ShanghaiT1DM), DA-CMTL achieved a root mean squared error of 14.19 mg/dL, mean absolute error of 10.09 mg/dL, and sensitivity/specificity of 89.28%/94.09% for early hypoglycemia detection. Real-world validation using type 2 diabetes-induced rats demonstrated a reduction in time below range from 3.01\u0026ndash;2.58%, supporting reliable integration as a safety layer in AID systems. These results highlight DA-CMTL\u0026rsquo;s robustness, scalability, and potential to improve safety in AID.\u003c/p\u003e","manuscriptTitle":"A domain-agnostic continual multi-task learning model for generalized glucose level and hypoglycemia event prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-30 17:56:54","doi":"10.21203/rs.3.rs-6576039/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"860898469324573857858197882054052955","date":"2025-05-29T22:21:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"170578264014385207948266192555363809595","date":"2025-05-28T13:56:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"60648205902096210497333504524830069934","date":"2025-05-28T04:58:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"179537374418562820524251077187914968918","date":"2025-05-27T22:58:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"185002489958082185758753722019800844260","date":"2025-05-27T22:26:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"172752647491407570158132976456876886786","date":"2025-05-27T22:18:28+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-27T22:17:01+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-27T00:31:28+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-26T10:13:48+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Medicine","date":"2025-05-02T06:50:45+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"5ffbc06b-62e6-4736-a401-1b97f525cbc1","owner":[],"postedDate":"May 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":49254092,"name":"Health sciences/Health care/Disease prevention/Preventive medicine"},{"id":49254093,"name":"Health sciences/Endocrinology/Endocrine system and metabolic diseases/Diabetes/Type 1 diabetes mellitus"}],"tags":[],"updatedAt":"2025-10-20T16:08:46+00:00","versionOfRecord":{"articleIdentity":"rs-6576039","link":"https://doi.org/10.1038/s41746-025-01994-4","journal":{"identity":"npj-digital-medicine","isVorOnly":false,"title":"npj Digital Medicine"},"publishedOn":"2025-10-16 15:57:34","publishedOnDateReadable":"October 16th, 2025"},"versionCreatedAt":"2025-05-30 17:56:54","video":"","vorDoi":"10.1038/s41746-025-01994-4","vorDoiUrl":"https://doi.org/10.1038/s41746-025-01994-4","workflowStages":[]},"version":"v1","identity":"rs-6576039","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6576039","identity":"rs-6576039","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}