Enhanced ECG Arrhythmia Detection Accuracy by Optimizing Divergence-Based Data Fusion

Enhanced ECG Arrhythmia Detection Accuracy by Optimizing Divergence-Based Data Fusion | 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 Enhanced ECG Arrhythmia Detection Accuracy by Optimizing Divergence-Based Data Fusion Baozhuo Su, Qingli Dou, Kang Liu, Zhengxian Qu, Jerry Deng, Ting Tan, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6265131/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 AI computation in healthcare faces significant challenges when clinical datasets are limited and heterogeneous. Integrating datasets from multiple sources and different equipments is critical for effective AI computation but is complicated by their diversity, complexity, and lack of representativeness, so we often need to join multiple datasets for analysis. The currently used method is fusion after normalization. But when using this method, it can introduce redundant information, decreasing the signal-to-noise ratio and reducing classification accuracy. To tackle this issue, we propose a feature-based fusion algorithm utilizing Kernel Density Estimation (KDE) and Kullback-Leibler (KL) divergence. Our approach involves initially preprocessing and continuous estimation on the extracted features, followed by employing the gradient descent method to identify the optimal linear parameters that minimize the KL divergence between the feature distributions. Using our in-house datasets consisting of ECG signals collected from 2000 healthy and 2000 diseased individuals by different equipments and verifying our method by using the publicly available PTB-XL dataset which contains 21,837 ECG recordings from 18,885 patients. We employ a Light Gradient Boosting Machine (LGBM) model to do the binary classification. The results demonstrate that the proposed fusion method significantly enhances feature-based classification accuracy for abnormal ECG cases in the merged datasets, compared to the normalization method. This data fusion strategy provides a new approach to process heterogeneous datasets for the optimal AI computation results. Biological sciences/Biological techniques/Bioinformatics Biological sciences/Biological techniques Biological sciences/Computational biology and bioinformatics Health sciences/Health care Data Fusion Kernel Density Estimation Kullback-Leibler Divergence Machine Learning Classification LGBM Full Text Additional Declarations No competing interests reported. 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-6265131","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":432405576,"identity":"f69989d0-030f-4a1e-8eea-e71562f6e1f3","order_by":0,"name":"Baozhuo Su","email":"","orcid":"","institution":"Aerie Intelligent Technology","correspondingAuthor":false,"prefix":"","firstName":"Baozhuo","middleName":"","lastName":"Su","suffix":""},{"id":432405577,"identity":"435fc48e-0d20-4650-a4b2-9ce23ca68456","order_by":1,"name":"Qingli Dou","email":"","orcid":"","institution":"Shenzhen Bao'an District People's Hospital","correspondingAuthor":false,"prefix":"","firstName":"Qingli","middleName":"","lastName":"Dou","suffix":""},{"id":432405578,"identity":"919f75c6-7ac9-442a-9722-0603a739de38","order_by":2,"name":"Kang Liu","email":"","orcid":"","institution":"Aerie Intelligent Technology","correspondingAuthor":false,"prefix":"","firstName":"Kang","middleName":"","lastName":"Liu","suffix":""},{"id":432405579,"identity":"dbec8496-ab58-43fc-bc16-3b15a7da5005","order_by":3,"name":"Zhengxian Qu","email":"","orcid":"","institution":"Aerie Intelligent Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhengxian","middleName":"","lastName":"Qu","suffix":""},{"id":432405580,"identity":"a1cf86e2-6eee-4d28-9d03-a3fdf7e8624c","order_by":4,"name":"Jerry Deng","email":"","orcid":"","institution":"Aerie Intelligent Technology","correspondingAuthor":false,"prefix":"","firstName":"Jerry","middleName":"","lastName":"Deng","suffix":""},{"id":432405584,"identity":"2b40be4b-0ab7-423c-8317-b8d88ce08343","order_by":5,"name":"Ting Tan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYFACxgYGhgogzczAcADENyCkgYcNpOUMTEsCUVpAFrXBuMRosZdvbnv4dZ6dnHk788HDhT9s5M0ZmB8+uoHfYe3GstuSjWUOsyUcnpGQZrizgc3YOAe/ljZpyW3MiTOYeQwO8yQcTjA4wMMmTVjLnPr6Gcz8H4Ba/hOnRfJjw+EECWYeBqCWA0RoOZbYJs1w7LjhDGY2oMPSkg03HCbgF/bm488kf9RUy0vwH378mcfGTt7gePPDx/i0gADQSShcAspBgPEHEYpGwSgYBaNgBAMAbh9DoLTOjBAAAAAASUVORK5CYII=","orcid":"","institution":"Aerie Intelligent Technology","correspondingAuthor":true,"prefix":"","firstName":"Ting","middleName":"","lastName":"Tan","suffix":""},{"id":432405585,"identity":"b0b52041-06e9-4ecc-b339-d04b1d2af8ff","order_by":6,"name":"Yanan Gu","email":"","orcid":"","institution":"Shenzhen Bao'an District People's Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yanan","middleName":"","lastName":"Gu","suffix":""}],"badges":[],"createdAt":"2025-03-20 01:23:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6265131/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6265131/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95527793,"identity":"aa7ce339-651b-41af-bc17-6fbc7af0c413","added_by":"auto","created_at":"2025-11-10 10:14:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":8517859,"visible":true,"origin":"","legend":"","description":"","filename":"npj.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6265131/v1_covered_db7c9cc9-51c8-43f2-9636-41d0f35fa0b5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhanced ECG Arrhythmia Detection Accuracy by Optimizing Divergence-Based Data Fusion","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Data Fusion, Kernel Density Estimation, Kullback-Leibler Divergence, Machine Learning, Classification, LGBM","lastPublishedDoi":"10.21203/rs.3.rs-6265131/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6265131/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"AI computation in healthcare faces significant challenges when clinical datasets are limited and heterogeneous. Integrating datasets from multiple sources and different equipments is critical for effective AI computation but is complicated by their diversity, complexity, and lack of representativeness, so we often need to join multiple datasets for analysis. The currently used method is fusion after normalization. But when using this method, it can introduce redundant information, decreasing the signal-to-noise ratio and reducing classification accuracy. To tackle this issue, we propose a feature-based fusion algorithm utilizing Kernel Density Estimation (KDE) and Kullback-Leibler (KL) divergence. Our approach involves initially preprocessing and continuous estimation on the extracted features, followed by employing the gradient descent method to identify the optimal linear parameters that minimize the KL divergence between the feature distributions. Using our in-house datasets consisting of ECG signals collected from 2000 healthy and 2000 diseased individuals by different equipments and verifying our method by using the publicly available PTB-XL dataset which contains 21,837 ECG recordings from 18,885 patients. We employ a Light Gradient Boosting Machine (LGBM) model to do the binary classification. The results demonstrate that the proposed fusion method significantly enhances feature-based classification accuracy for abnormal ECG cases in the merged datasets, compared to the normalization method. This data fusion strategy provides a new approach to process heterogeneous datasets for the optimal AI computation results.","manuscriptTitle":"Enhanced ECG Arrhythmia Detection Accuracy by Optimizing Divergence-Based Data Fusion","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-31 04:55:35","doi":"10.21203/rs.3.rs-6265131/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":"4acbe4c0-31df-43ed-b3a2-fd1d042c88ed","owner":[],"postedDate":"March 31st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46057519,"name":"Biological sciences/Biological techniques/Bioinformatics"},{"id":46057520,"name":"Biological sciences/Biological techniques"},{"id":46057521,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":46057522,"name":"Health sciences/Health care"}],"tags":[],"updatedAt":"2025-11-08T20:08:22+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-31 04:55:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6265131","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6265131","identity":"rs-6265131","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}