Multi-Branch Convolutional Network and LSTM-CNN for Heart Sound Classification

Multi-Branch Convolutional Network and LSTM-CNN for Heart Sound Classification | 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-Branch Convolutional Network and LSTM-CNN for Heart Sound Classification Seyed Amir Latifi, Hassan Ghassemian, Maryam Imani This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6793659/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 07 Nov, 2025 Read the published version in Physical and Engineering Sciences in Medicine → Version 1 posted 6 You are reading this latest preprint version Abstract Cardiovascular diseases represent a leading cause of mortality worldwide, necessitating accurate and early diagnosis for improved patient outcomes. Current diagnostic approaches for cardiac abnormalities often present challenges in clinical settings due to their complexity, cost, or limited accessibility. This study develops two deep learning architectures that offer fast, accurate, and cost-effective methods for automatic diagnosis of cardiac diseases, focusing specifically on addressing the critical challenge of limited labeled datasets in medical contexts. We propose two methodologies: first, a Multi-Branch Deep Convolutional Neural Network (MBDCN) that emulates human auditory processing by utilizing diverse convolutional filter sizes and power spectrum input for enhanced feature extraction; second, a Long Short-Term Memory-Convolutional Neural (LSCN) model that integrates LSTM blocks with MBDCN to improve time-domain feature extraction. The synergistic integration of multiple parallel convolutional branches with LSTM units enables superior performance in heart sound analysis. Experimental validation demonstrates that LSCN achieves multiclass classification accuracy of 89.65% and binary classification accuracy of 93.93%, significantly outperforming state-of-the-art techniques and traditional feature extraction methods such as Mel Frequency Cepstral Coefficients (MFCC) and wavelet transforms. A comprehensive 5-fold cross-validation confirms robustness of our approach across varying data partitions. These findings establish the efficacy of our proposed architectures for automated heart sound analysis, offering clinically viable and computationally efficient solutions for early detection of cardiovascular diseases in diverse healthcare environments. heart sounds cardiovascular diseases classification feature extraction Multi-Branch-CNN LSTM Full Text Cite Share Download PDF Status: Published Journal Publication published 07 Nov, 2025 Read the published version in Physical and Engineering Sciences in Medicine → Version 1 posted Reviewers agreed at journal 10 Jul, 2025 Reviewers invited by journal 09 Jul, 2025 Editor invited by journal 09 Jul, 2025 Editor assigned by journal 09 Jul, 2025 First submitted to journal 08 Jul, 2025 Editorial decision: Major revisions 03 Jul, 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-6793659","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":483250930,"identity":"6b7afea6-3d32-4f52-88fd-20e9f367475d","order_by":0,"name":"Seyed Amir Latifi","email":"","orcid":"","institution":"Tarbiat Modares University Faculty of Electrical and Computer Engineering","correspondingAuthor":false,"prefix":"","firstName":"Seyed","middleName":"Amir","lastName":"Latifi","suffix":""},{"id":483250931,"identity":"b24ee7e5-fa56-4d8b-abb4-62abeb9afa29","order_by":1,"name":"Hassan Ghassemian","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIiWNgGAWjYDACCQjFw49gA0ECMVokG0jVwmBwAFkLPiAf3fz444+KbTLG1w4fvPFzj409A/vhBwwP9+DWYnjnmJk0z5nbPGa305Ite56lJTbwpBkwJDzDo2VGghkzYxtIS46ZBM+Bw0Bf5AD9cgCflvTPH3/+u81jPDvHTPLPgf/2DPxv8GuRl8gxkOBtuM1jIJ0DdOGBA4wNEgRsMZDIKZPmOXabRwLoF2uZA8mJbRLPDA7gtWVG+uaPP2pu2/PPTj54880BO3t+/uSHD3/gswVDjg2I8WgA2tKAT3YUjIJRMApGAQgAAHQ9Ud51dpvXAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-2303-1753","institution":"Tarbiat Modares University Faculty of Electrical and Computer Engineering","correspondingAuthor":true,"prefix":"","firstName":"Hassan","middleName":"","lastName":"Ghassemian","suffix":""},{"id":483250932,"identity":"ef0d0db3-3938-4d6c-88bd-9581e6ddd3ae","order_by":2,"name":"Maryam Imani","email":"","orcid":"","institution":"Tarbiat Modares University Faculty of Electrical and Computer Engineering","correspondingAuthor":false,"prefix":"","firstName":"Maryam","middleName":"","lastName":"Imani","suffix":""}],"badges":[],"createdAt":"2025-06-01 04:22:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6793659/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6793659/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s13246-025-01664-5","type":"published","date":"2025-11-07T15:57:35+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":95564760,"identity":"18854e22-d600-4a68-91b0-36e78b21441a","added_by":"auto","created_at":"2025-11-10 16:10:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1142363,"visible":true,"origin":"","legend":"","description":"","filename":"LatifiRevision.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6793659/v1_covered_3877f3b5-14dd-41ab-b1ec-fa61c9c153c3.pdf"}],"financialInterests":"","formattedTitle":"Multi-Branch Convolutional Network and LSTM-CNN for Heart Sound Classification","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":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"physical-and-engineering-sciences-in-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"apes","sideBox":"Learn more about [Physical and Engineering Sciences in Medicine](http://link.springer.com/journal/13246)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/apes/default.aspx","title":"Physical and Engineering Sciences in Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"heart sounds, cardiovascular diseases classification, feature extraction, Multi-Branch-CNN, LSTM","lastPublishedDoi":"10.21203/rs.3.rs-6793659/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6793659/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCardiovascular diseases represent a leading cause of mortality worldwide, necessitating accurate and early diagnosis for improved patient outcomes. Current diagnostic approaches for cardiac abnormalities often present challenges in clinical settings due to their complexity, cost, or limited accessibility. This study develops two deep learning architectures that offer fast, accurate, and cost-effective methods for automatic diagnosis of cardiac diseases, focusing specifically on addressing the critical challenge of limited labeled datasets in medical contexts. We propose two methodologies: first, a Multi-Branch Deep Convolutional Neural Network (MBDCN) that emulates human auditory processing by utilizing diverse convolutional filter sizes and power spectrum input for enhanced feature extraction; second, a Long Short-Term Memory-Convolutional Neural (LSCN) model that integrates LSTM blocks with MBDCN to improve time-domain feature extraction. The synergistic integration of multiple parallel convolutional branches with LSTM units enables superior performance in heart sound analysis. Experimental validation demonstrates that LSCN achieves multiclass classification accuracy of 89.65% and binary classification accuracy of 93.93%, significantly outperforming state-of-the-art techniques and traditional feature extraction methods such as Mel Frequency Cepstral Coefficients (MFCC) and wavelet transforms. A comprehensive 5-fold cross-validation confirms robustness of our approach across varying data partitions. These findings establish the efficacy of our proposed architectures for automated heart sound analysis, offering clinically viable and computationally efficient solutions for early detection of cardiovascular diseases in diverse healthcare environments.\u003c/p\u003e","manuscriptTitle":"Multi-Branch Convolutional Network and LSTM-CNN for Heart Sound Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-14 07:09:45","doi":"10.21203/rs.3.rs-6793659/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2025-07-10T13:03:27+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-10T03:57:45+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"Physical and Engineering Sciences in Medicine","date":"2025-07-10T03:18:08+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-09T14:12:00+00:00","index":"","fulltext":""},{"type":"submitted","content":"Physical and Engineering Sciences in Medicine","date":"2025-07-09T00:00:16+00:00","index":"","fulltext":""},{"type":"decision","content":"Major revisions","date":"2025-07-03T04:19:03+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"physical-and-engineering-sciences-in-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"apes","sideBox":"Learn more about [Physical and Engineering Sciences in Medicine](http://link.springer.com/journal/13246)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/apes/default.aspx","title":"Physical and Engineering Sciences in Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"492e4ec4-8d71-4fc2-bd10-943dd091c114","owner":[],"postedDate":"July 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-11-10T16:09:33+00:00","versionOfRecord":{"articleIdentity":"rs-6793659","link":"https://doi.org/10.1007/s13246-025-01664-5","journal":{"identity":"physical-and-engineering-sciences-in-medicine","isVorOnly":false,"title":"Physical and Engineering Sciences in Medicine"},"publishedOn":"2025-11-07 15:57:35","publishedOnDateReadable":"November 7th, 2025"},"versionCreatedAt":"2025-07-14 07:09:45","video":"","vorDoi":"10.1007/s13246-025-01664-5","vorDoiUrl":"https://doi.org/10.1007/s13246-025-01664-5","workflowStages":[]},"version":"v1","identity":"rs-6793659","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6793659","identity":"rs-6793659","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}