Automatic Classification and Acoustic Auscultation of Heart, Lung, and Bowel Sounds Using Artificial Intelligence

Automatic Classification and Acoustic Auscultation of Heart, Lung, and Bowel Sounds 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 Automatic Classification and Acoustic Auscultation of Heart, Lung, and Bowel Sounds Using Artificial Intelligence Yen-Sheng Lin, Ansh Kapadia, Eric B. Ortigoza This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7061625/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 Auscultation of heart, lung, and bowel sounds remains a fundamental diagnostic technique in clinical practice despite significant technological advancements in medical imaging. However, the accuracy of auscultation-based diagnoses is highly dependent on clinician experience and expertise, leading to potential diagnostic inconsistencies. The objective of this study is to present a novel artificial intelligence (AI) framework for the automatic classification and acoustic differentiation of heart, lung, and bowel sounds, addressing the need for objective, reproducible diagnostic support tools. Our approach leverages recent advances in supervised machine learning and signal processing to extract distinctive acoustic signatures from publicly available, digitized heart, lung, and bowel sounds. By analyzing spectral, temporal, and morphological features across diverse asymptomatic populations, the algorithm achieves excellent classification of predictive accuracy (65.00–91.67%) and validation accuracy (83.87–94.62%) from six AI models. The clinical implications of this algorithm show promise beyond diagnostic support to applications in medical education, telemedicine, and continuous patient monitoring. This work contributes to emerging AI-assisted auscultation by providing a comprehensive framework for multi-organ sound classification with the potential to improve differential diagnostic accuracy and standardization in clinical settings. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Health sciences/Health care Physical sciences/Mathematics and computing Health sciences/Medical research Artificial Intelligence Acoustic Auscultation Automated Algorithm 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-7061625","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":491954405,"identity":"03abb89f-9733-43e9-9606-12b1f1d08384","order_by":0,"name":"Yen-Sheng Lin","email":"data:image/png;base64,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","orcid":"","institution":"The University of Texas Southwestern Medical Center","correspondingAuthor":true,"prefix":"","firstName":"Yen-Sheng","middleName":"","lastName":"Lin","suffix":""},{"id":491954406,"identity":"c4396250-b881-4b58-a85f-01014eea643d","order_by":1,"name":"Ansh Kapadia","email":"","orcid":"","institution":"University of North Texas","correspondingAuthor":false,"prefix":"","firstName":"Ansh","middleName":"","lastName":"Kapadia","suffix":""},{"id":491954407,"identity":"b3823bb1-7a1e-4585-a7c7-e03e05c7b4a6","order_by":2,"name":"Eric B. Ortigoza","email":"","orcid":"","institution":"The University of Texas Southwestern Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Eric","middleName":"B.","lastName":"Ortigoza","suffix":""}],"badges":[],"createdAt":"2025-07-07 05:53:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7061625/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7061625/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106172797,"identity":"79fb29e8-b0bd-4494-8f62-14219cb6fc8e","added_by":"auto","created_at":"2026-04-05 07:24:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":696671,"visible":true,"origin":"","legend":"","description":"","filename":"AutomaticClassificationandAcousticDifferentiationofHLB07072025final1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7061625/v1_covered_73487e22-f4e1-4315-b081-3b8351793007.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Automatic Classification and Acoustic Auscultation of Heart, Lung, and Bowel Sounds Using Artificial Intelligence","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":"Artificial Intelligence, Acoustic Auscultation, Automated Algorithm","lastPublishedDoi":"10.21203/rs.3.rs-7061625/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7061625/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAuscultation of heart, lung, and bowel sounds remains a fundamental diagnostic technique in clinical practice despite significant technological advancements in medical imaging. However, the accuracy of auscultation-based diagnoses is highly dependent on clinician experience and expertise, leading to potential diagnostic inconsistencies. The objective of this study is to present a novel artificial intelligence (AI) framework for the automatic classification and acoustic differentiation of heart, lung, and bowel sounds, addressing the need for objective, reproducible diagnostic support tools. Our approach leverages recent advances in supervised machine learning and signal processing to extract distinctive acoustic signatures from publicly available, digitized heart, lung, and bowel sounds. By analyzing spectral, temporal, and morphological features across diverse asymptomatic populations, the algorithm achieves excellent classification of predictive accuracy (65.00\u0026ndash;91.67%) and validation accuracy (83.87\u0026ndash;94.62%) from six AI models. The clinical implications of this algorithm show promise beyond diagnostic support to applications in medical education, telemedicine, and continuous patient monitoring. This work contributes to emerging AI-assisted auscultation by providing a comprehensive framework for multi-organ sound classification with the potential to improve differential diagnostic accuracy and standardization in clinical settings.\u003c/p\u003e","manuscriptTitle":"Automatic Classification and Acoustic Auscultation of Heart, Lung, and Bowel Sounds Using Artificial Intelligence","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-29 18:27:26","doi":"10.21203/rs.3.rs-7061625/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":"ab4e7946-cb4d-461d-80c8-5f0d2d9f41f6","owner":[],"postedDate":"July 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":52229386,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":52229387,"name":"Physical sciences/Engineering"},{"id":52229388,"name":"Health sciences/Health care"},{"id":52229389,"name":"Physical sciences/Mathematics and computing"},{"id":52229390,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-04-05T07:24:13+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-29 18:27:26","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7061625","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7061625","identity":"rs-7061625","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}