Overcoming data scarcity in life-threatening arrhythmia detection: A deep learning framework for life-saving interventions

Overcoming data scarcity in life-threatening arrhythmia detection: A deep learning framework for life-saving interventions | 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 Overcoming data scarcity in life-threatening arrhythmia detection: A deep learning framework for life-saving interventions Giuliana Monachino, Beatrice Zanchi, Michael Wand, Giulio Conte, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5465016/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 01 Jul, 2025 Read the published version in Communications Medicine → Version 1 posted You are reading this latest preprint version Abstract Life-threatening arrhythmias (LTAs) are a leading cause of death worldwide. Enhancing LTA detection in wearable monitoring systems is of great significance. We present a powerful deep-learning (DL) algorithm for detecting LTAs from single-lead ECGs, intended for application in out-of-hospital cardiac arrest (OHCA). To address the challenge of limited labeled LTA data, a transfer learning approach is proposed. A DL model is pre-trained on a massive dataset (72'952 recordings) for rhythm classification and then fine-tuned on the target dataset with LTA events (102 recordings). The resulting model achieves a sensitivity of 92.68% and a specificity of 99.48%, with a granularity of 1.28 seconds, in detecting LTAs. Additionally, a confidence estimation procedure is introduced, to enable emergency service pre-alerts in case of low-confidence detections. Our study explores the impact of transfer learning in overcoming data scarcity issues, advancing LTA detection in wearable monitoring systems, and supporting rapid, life-saving interventions in OHCA emergencies. Health sciences/Cardiology/Cardiovascular biology/Cardiovascular diseases/Arrhythmias Health sciences/Health care/Diagnosis Transfer learning Life-threatening arrhythmias Sudden cardiac arrest ECG Deep learning Data scarcity Out-of-hospital cardiac arrest Full Text Additional Declarations There is NO Competing Interest. Supplementary Files supplementarymaterials0ln.pdf Supplementary material Cite Share Download PDF Status: Published Journal Publication published 01 Jul, 2025 Read the published version in Communications Medicine → 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-5465016","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":389048252,"identity":"f04dde7e-7f17-4b40-ba4b-b4c958217257","order_by":0,"name":"Giuliana Monachino","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0003-4434-6399","institution":"University of Bern","correspondingAuthor":true,"prefix":"","firstName":"Giuliana","middleName":"","lastName":"Monachino","suffix":""},{"id":389048253,"identity":"ee5e1131-1e8a-4a61-93d4-078a69a48984","order_by":1,"name":"Beatrice Zanchi","email":"","orcid":"","institution":"University of Applied Sciences and Arts of Southern Switzerland","correspondingAuthor":false,"prefix":"","firstName":"Beatrice","middleName":"","lastName":"Zanchi","suffix":""},{"id":389048254,"identity":"b056eb24-3d6b-4367-9d9f-055d350c10fc","order_by":2,"name":"Michael Wand","email":"","orcid":"","institution":"Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI","correspondingAuthor":false,"prefix":"","firstName":"Michael","middleName":"","lastName":"Wand","suffix":""},{"id":389048255,"identity":"c42c4ca4-9dc3-4db3-950a-f1c77d6b6856","order_by":3,"name":"Giulio Conte","email":"","orcid":"","institution":"Cardiology Department, Cardiocentro Ticino Institute, Ente Ospedaliero Cantonale","correspondingAuthor":false,"prefix":"","firstName":"Giulio","middleName":"","lastName":"Conte","suffix":""},{"id":389048256,"identity":"92be0257-3041-4d71-ba5b-4b99203afafd","order_by":4,"name":"Athina Tzovara","email":"","orcid":"","institution":"University of Bern","correspondingAuthor":false,"prefix":"","firstName":"Athina","middleName":"","lastName":"Tzovara","suffix":""},{"id":389048257,"identity":"3c9744dd-d32d-4ee3-bd06-e40e79d17454","order_by":5,"name":"Francesca Faraci","email":"","orcid":"https://orcid.org/0000-0002-8720-1256","institution":"SUPSI","correspondingAuthor":false,"prefix":"","firstName":"Francesca","middleName":"","lastName":"Faraci","suffix":""}],"badges":[],"createdAt":"2024-11-16 09:35:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5465016/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5465016/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s43856-025-00982-9","type":"published","date":"2025-07-01T04:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":85827091,"identity":"baf05edf-768e-4764-be3d-86b13279d6c9","added_by":"auto","created_at":"2025-07-02 07:21:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":628337,"visible":true,"origin":"","legend":"Article File","description":"","filename":"manuscripts0ln.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5465016/v1_covered_55002fae-34a6-4cf9-b12b-6d05671fce30.pdf"},{"id":71594437,"identity":"a0bb0967-d11c-4142-8312-0e5e81a42d7d","added_by":"auto","created_at":"2024-12-17 03:58:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2460288,"visible":true,"origin":"","legend":"Supplementary material","description":"","filename":"supplementarymaterials0ln.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5465016/v1/5e27ce74ebb0a5910ae3ebe2.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Overcoming data scarcity in life-threatening arrhythmia detection: A deep learning framework for life-saving interventions","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Transfer learning, Life-threatening arrhythmias, Sudden cardiac arrest, ECG, Deep learning, Data scarcity, Out-of-hospital cardiac arrest","lastPublishedDoi":"10.21203/rs.3.rs-5465016/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5465016/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Life-threatening arrhythmias (LTAs) are a leading cause of death worldwide. Enhancing LTA detection in wearable monitoring systems is of great significance. We present a powerful deep-learning (DL) algorithm for detecting LTAs from single-lead ECGs, intended for application in out-of-hospital cardiac arrest (OHCA). To address the challenge of limited labeled LTA data, a transfer learning approach is proposed. A DL model is pre-trained on a massive dataset (72'952 recordings) for rhythm classification and then fine-tuned on the target dataset with LTA events (102 recordings). The resulting model achieves a sensitivity of 92.68% and a specificity of 99.48%, with a granularity of 1.28 seconds, in detecting LTAs. Additionally, a confidence estimation procedure is introduced, to enable emergency service pre-alerts in case of low-confidence detections. Our study explores the impact of transfer learning in overcoming data scarcity issues, advancing LTA detection in wearable monitoring systems, and supporting rapid, life-saving interventions in OHCA emergencies.","manuscriptTitle":"Overcoming data scarcity in life-threatening arrhythmia detection: A deep learning framework for life-saving interventions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-17 03:58:51","doi":"10.21203/rs.3.rs-5465016/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"communications-medicine","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"commsmed","sideBox":"Learn more about [Communications Medicine](http://www.nature.com/commsmed)","snPcode":"43856","submissionUrl":"https://mts-commsmed.nature.com/cgi-bin/main.plex","title":"Communications Medicine","twitterHandle":"@commsmedicine","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Communications Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"469b66e3-cb07-4762-bd64-d41d0289a251","owner":[],"postedDate":"December 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":41463515,"name":"Health sciences/Cardiology/Cardiovascular biology/Cardiovascular diseases/Arrhythmias"},{"id":41463516,"name":"Health sciences/Health care/Diagnosis"}],"tags":[],"updatedAt":"2025-07-02T07:21:28+00:00","versionOfRecord":{"articleIdentity":"rs-5465016","link":"https://doi.org/10.1038/s43856-025-00982-9","journal":{"identity":"communications-medicine","isVorOnly":false,"title":"Communications Medicine"},"publishedOn":"2025-07-01 04:00:00","publishedOnDateReadable":"July 1st, 2025"},"versionCreatedAt":"2024-12-17 03:58:51","video":"","vorDoi":"10.1038/s43856-025-00982-9","vorDoiUrl":"https://doi.org/10.1038/s43856-025-00982-9","workflowStages":[]},"version":"v1","identity":"rs-5465016","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5465016","identity":"rs-5465016","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}