Heart Failure Detection in Electrocardiograms Using Artificial Intelligence

Heart Failure Detection in Electrocardiograms Using Artificial Intelligence | 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 Heart Failure Detection in Electrocardiograms Using Artificial Intelligence Arian Ranjbar, Elias Stenhede, Jesper Ravn, Henrik Schirmer This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5716430/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract The diagnosis of heart failure (HF) is resource-intensive, requiring specialized personnel and equipment, which often leads to severe underdiagnosis. This study proposes the use of a machine learning model to detect HF in Electrocardiograms (ECGs), a commonly used tool in most healthcare settings. HF is known to have limited validity in diagnosis codes, limiting the viability of direct application of supervised learning. However, we hypothesize that validating diagnosis with measured levels of circulating N-terminal proB-type natriuretic peptide (NT-proBNP), ameliorates the impact of label noise in a large dataset. We demonstrate the success of the labelling strategy by developing a neural network and prospectively validating it in a cohort comprising 43109 patients. The model significantly outperformed NT-proBNP in diagnostic accuracy (p = 7.5e-7), and is capable of detecting both HF with reduced ejection fraction (AUC=0.91) and preserved ejection fraction (AUC=0.68-0.89 depending on definition). To highlight the impact of underdiagnosis in evaluating the model, we conducted a small-scale retrospective clinical evaluation of the test set, including patients with ejection fraction >50% with no HF diagnosis and normal levels of NT-proBNP. In this subgroup, 24 out of the 30 patients with the highest model-predicted risk satisfied the diagnostic criteria for HFpEF. These combined findings demonstrate the model’s capability in finding HF independent of ejection fraction, and a potential for accessible diagnostics through AI-enhanced ECG analysis. Health sciences/Diseases/Cardiovascular diseases/Heart failure Health sciences/Health care/Diagnosis/Electrodiagnosis Health sciences/Biomarkers/Diagnostic markers Full Text Additional Declarations Yes there is potential Competing Interest. Henrik Schirmer has previously received lecture fees from Amgen, Boehringer Ingelheim, Bristol-Myers Sqibb, Novartis, NovoNordisk and Sanofi-Aventis. The authors declare no other competing interests. Supplementary Files Supplementary.pdf Supplementary tables for the clinical evaluation Cite Share Download PDF Status: Under Review 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-5716430","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":397488636,"identity":"6ce3bd7a-1aa9-4288-9311-09934531fda9","order_by":0,"name":"Arian Ranjbar","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABHElEQVRIie2QQUvDMBTHX/DQy7O9LkzWr5BSmMiQfZWWgl4HXioIphR28gNMFD9DTwVvHQF3SetVCchkH6Gn4cVUiwepdUfB/EhICP8fL+8BGAx/EsLbi9Q71lsAFPrAHRW5k/KFzpA5fOb7cG5EUs/gxT0k5bI+v8tH9sp6FTMQBw7sL9cdyqAK0+ECzrx7XkW0zJVPBTKxAIGU2xHrKiMJHyIEJCsko0muwkwgfCxW4HjQYbiSpG9amWrF3ya36jIT1rpXYZLMmyqhVsY04SpgAliv4mllgiyIsqI6OeIPyrtuekF2ijRFv6uXkbQ2CuPgOHsqxTO/UK79uNrUGE+mjnXldU2s/V4zu+L7y96P+RaH/5YwGAyG/8o79VJl1D2W8R4AAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-0422-2255","institution":"Akershus University Hospital","correspondingAuthor":true,"prefix":"","firstName":"Arian","middleName":"","lastName":"Ranjbar","suffix":""},{"id":397488637,"identity":"3d6382f2-fcd5-4862-b70f-c99b5fc89d8e","order_by":1,"name":"Elias Stenhede","email":"","orcid":"https://orcid.org/0009-0005-2654-4553","institution":"Akershus University Hospital","correspondingAuthor":false,"prefix":"","firstName":"Elias","middleName":"","lastName":"Stenhede","suffix":""},{"id":397488638,"identity":"0f5fd3a6-9f7b-443f-b1fd-560f1d791287","order_by":2,"name":"Jesper Ravn","email":"","orcid":"","institution":"Akershus University Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jesper","middleName":"","lastName":"Ravn","suffix":""},{"id":397488639,"identity":"62509766-2625-4f5f-b158-1421a1e8847a","order_by":3,"name":"Henrik Schirmer","email":"","orcid":"https://orcid.org/0000-0002-9348-3149","institution":"Akershus University Hospital","correspondingAuthor":false,"prefix":"","firstName":"Henrik","middleName":"","lastName":"Schirmer","suffix":""}],"badges":[],"createdAt":"2024-12-26 13:35:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5716430/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5716430/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":73442322,"identity":"ab258997-4181-4304-ac66-ecc7c5fb7b46","added_by":"auto","created_at":"2025-01-10 04:02:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":382707,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Heartfailuredetectioninelectrocardiogramusingartificialintelligence.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5716430/v1_covered_fdfe9c75-ca19-4f87-8a95-6d997a97d647.pdf"},{"id":73441589,"identity":"c0ec654b-1854-4426-a36a-475cf214f903","added_by":"auto","created_at":"2025-01-10 03:46:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":117461,"visible":true,"origin":"","legend":"Supplementary tables for the clinical evaluation","description":"","filename":"Supplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5716430/v1/dcb924044a0468010899a111.pdf"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nHenrik Schirmer has previously received lecture fees from Amgen, Boehringer Ingelheim, Bristol-Myers Sqibb, Novartis, NovoNordisk and Sanofi-Aventis. The authors declare no other competing interests.","formattedTitle":"Heart Failure Detection in Electrocardiograms Using Artificial Intelligence","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-5716430/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5716430/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The diagnosis of heart failure (HF) is resource-intensive, requiring specialized personnel and equipment, which often leads to severe underdiagnosis. This study proposes the use of a machine learning model to detect HF in Electrocardiograms (ECGs), a commonly used tool in most healthcare settings. HF is known to have limited validity in diagnosis codes, limiting the viability of direct application of supervised learning. However, we hypothesize that validating diagnosis with measured levels of circulating N-terminal proB-type natriuretic peptide (NT-proBNP), ameliorates the impact of label noise in a large dataset. We demonstrate the success of the labelling strategy by developing a neural network and prospectively validating it in a cohort comprising 43109 patients. The model significantly outperformed NT-proBNP in diagnostic accuracy (p = 7.5e-7), and is capable of detecting both HF with reduced ejection fraction (AUC=0.91) and preserved ejection fraction (AUC=0.68-0.89 depending on definition). To highlight the impact of underdiagnosis in evaluating the model, we conducted a small-scale retrospective clinical evaluation of the test set, including patients with ejection fraction \u003e50% with no HF diagnosis and normal levels of NT-proBNP. In this subgroup, 24 out of the 30 patients with the highest model-predicted risk satisfied the diagnostic criteria for HFpEF. These combined findings demonstrate the model’s capability in finding HF independent of ejection fraction, and a potential for accessible diagnostics through AI-enhanced ECG analysis.","manuscriptTitle":"Heart Failure Detection in Electrocardiograms Using Artificial Intelligence","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-10 03:45:56","doi":"10.21203/rs.3.rs-5716430/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"758f6745-1e5a-4d3a-a2a4-f6c7bf0e1a8a","owner":[],"postedDate":"January 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":42350091,"name":"Health sciences/Diseases/Cardiovascular diseases/Heart failure"},{"id":42350092,"name":"Health sciences/Health care/Diagnosis/Electrodiagnosis"},{"id":42350093,"name":"Health sciences/Biomarkers/Diagnostic markers"}],"tags":[],"updatedAt":"2025-09-22T18:53:22+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-10 03:45:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5716430","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5716430","identity":"rs-5716430","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}