Multi-Lead ECG Arrhythmia Detection with Hybrid Dynamic Graph Convolutional Network

Multi-Lead ECG Arrhythmia Detection with Hybrid Dynamic Graph Convolutional Network | 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 Research Article Multi-Lead ECG Arrhythmia Detection with Hybrid Dynamic Graph Convolutional Network Xudan Zheng, Yanbei Liu, Wen Wang, Qing Guo, Fang Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9428371/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 Cardiovascular disease remains a leading cause of global mortality, underscoring the critical need for accurate and efficient diagnosis of cardiac conditions. Although the electrocardiogram (ECG) is a widely used diagnostic tool, its utility is often limited by signal artifacts and phenotypic similarities among distinct pathologies. To address these limitations, we propose a novel Hybrid Dynamic Graph Convolutional Network (HDGCN) to detect multi-lead ECG arrhythmia. In our HDGCN, ECG signals are represented as graph structures, where nodes correspond to sampling points and edges encode spatiotemporal relationships. Local spatiotemporal features are extracted using a pre-trained ResNet module to capture subtle morphological variations, while an adaptive graph convolutional module with a learnable adjacency matrix dynamically models deeper inter-lead dependencies. Additionally, wavelet-based denoising is applied during preprocessing to preserve clinically relevant features, and depthwise separable convolutions are incorporated to substantially reduce computational complexity. Experimental results demonstrate that HDGCN achieves an average accuracy of 99.57%. The model exhibits robust performance in detecting complex arrhythmias, notably attaining an improvement exceeding 6% for categories such as atrial premature beats. ECG classification Dynamic Graph Convolution Multi-Scale Fusion Clinical Deployment Full Text Additional Declarations The authors declare no competing interests. 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-9428371","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":623720423,"identity":"9a231541-ce6b-478a-9f0b-d26cd43ed3fc","order_by":0,"name":"Xudan Zheng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzElEQVRIiWNgGAWjYBAC+/uPDz74UPGPh7G9gVg9B9KSDWecOSDH3HOAaC05atKcbQeM2WckEKmDseEMmzQD253E3pmPN95gqLGJJqiFmbH3sHUBz7PEmbPTii0YjqXlNhDSwsbMl3h7hgRz4sbZOWYSjA2HCWvhYeMxkOYxYE7cf/MMkVokeHiMpHkSDhszzuAhUouBBBswkA+kyTH2AP2SQIxfDCSYDz74+M8GGJWHN974UGNDWAuq9gRSlEO0kKpjFIyCUTAKRgYAALAFQjoGsYUVAAAAAElFTkSuQmCC","orcid":"","institution":"Tiangong University","correspondingAuthor":true,"prefix":"","firstName":"Xudan","middleName":"","lastName":"Zheng","suffix":""},{"id":623720424,"identity":"778102b1-e13e-4f4b-acda-f014d2ef94a7","order_by":1,"name":"Yanbei Liu","email":"","orcid":"","institution":"Tiangong University","correspondingAuthor":false,"prefix":"","firstName":"Yanbei","middleName":"","lastName":"Liu","suffix":""},{"id":623720425,"identity":"1cebcfe0-93c4-4ea6-98dc-305508a8f3b3","order_by":2,"name":"Wen Wang","email":"","orcid":"","institution":"Tiangong University","correspondingAuthor":false,"prefix":"","firstName":"Wen","middleName":"","lastName":"Wang","suffix":""},{"id":623720426,"identity":"fe121411-cb11-4c0c-ac99-6e9c1701c9df","order_by":3,"name":"Qing Guo","email":"","orcid":"","institution":"Tiangong University","correspondingAuthor":false,"prefix":"","firstName":"Qing","middleName":"","lastName":"Guo","suffix":""},{"id":623720427,"identity":"113a55ba-36ae-47f2-b489-362c975a0e0c","order_by":4,"name":"Fang Zhang","email":"","orcid":"","institution":"Tiangong University","correspondingAuthor":false,"prefix":"","firstName":"Fang","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2026-04-15 14:26:50","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-9428371/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9428371/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107480480,"identity":"995b580f-f3c3-4a5a-86d7-568b6b007f61","added_by":"auto","created_at":"2026-04-22 02:11:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":543319,"visible":true,"origin":"","legend":"","description":"","filename":"HDGCN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9428371/v1_covered_d997176c-7db3-457f-b5c4-90553acd742b.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eMulti-Lead ECG Arrhythmia Detection with Hybrid Dynamic Graph Convolutional Network\u003c/p\u003e","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":false,"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":"ECG classification, Dynamic Graph Convolution, Multi-Scale Fusion, Clinical Deployment","lastPublishedDoi":"10.21203/rs.3.rs-9428371/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9428371/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCardiovascular disease remains a leading cause of global mortality, underscoring the critical need for accurate and efficient diagnosis of cardiac conditions. Although the electrocardiogram (ECG) is a widely used diagnostic tool, its utility is often limited by signal artifacts and phenotypic similarities among distinct pathologies. To address these limitations, we propose a novel Hybrid Dynamic Graph Convolutional Network (HDGCN) to detect multi-lead ECG arrhythmia. In our HDGCN, ECG signals are represented as graph structures, where nodes correspond to sampling points and edges encode spatiotemporal relationships. Local spatiotemporal features are extracted using a pre-trained ResNet module to capture subtle morphological variations, while an adaptive graph convolutional module with a learnable adjacency matrix dynamically models deeper inter-lead dependencies. Additionally, wavelet-based denoising is applied during preprocessing to preserve clinically relevant features, and depthwise separable convolutions are incorporated to substantially reduce computational complexity. Experimental results demonstrate that HDGCN achieves an average accuracy of 99.57%. The model exhibits robust performance in detecting complex arrhythmias, notably attaining an improvement exceeding 6% for categories such as atrial premature beats.\u003c/p\u003e","manuscriptTitle":"Multi-Lead ECG Arrhythmia Detection with Hybrid Dynamic Graph Convolutional Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-16 03:17:34","doi":"10.21203/rs.3.rs-9428371/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":"a7647bde-981c-4316-8197-0781859b7b79","owner":[],"postedDate":"April 16th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-16T03:17:34+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-16 03:17:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9428371","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9428371","identity":"rs-9428371","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}