{"paper_id":"41a7969f-b5a0-4e39-aeca-3c85e91b3d4a","body_text":"Multimodal Transformer for Heart Disease Classification Using Multiple Heart Sound Spectral Analyses and Clinical Metadata | 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 Multimodal Transformer for Heart Disease Classification Using Multiple Heart Sound Spectral Analyses and Clinical Metadata Shintaro Fujisawa, Yusuke Fukazawa This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6076597/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 This study proposes a multimodal fusion framework for heart disease classification that combines multiple spectral analyses of heart sounds with clinical metadata. Our framework integrates four complementary spectral analysis methods (Stockwell transform, bispectrum, mel-spectrogram, and power spectrum) using Vision Transformers. This spectral fusion is further enhanced by incorporating clinical metadata processed through Bio\\_ClinicalBERT, enabling the capture of diagnostic insights from specialist physicians. Our framework achieved superior performance, with the model that fused both spectral features and clinical data reaching an accuracy of 0.881. This fusion model outperformed the individual spectral models, which had an accuracy of 0.831, by 6\\%. Additionally, incorporating clinical metadata resulted in a 2.6\\% improvement in accuracy compared to the model that fused only the four spectral features, which had an accuracy of 0.855. Through SHAP analysis, we discovered that our model excels at detecting right-heart abnormalities, which are often difficult to identify through traditional auscultation. Furthermore, we identified the Stockwell transform and mel-spectrogram as particularly influential features. The Stockwell transform's ability to localize both time and frequency information allowed our model to capture transient patterns crucial for detecting subtle heart sound abnormalities. Similarly, the mel-spectrogram, designed to mimic human auditory perception, excelled in highlighting frequency-related features commonly recognized by clinicians. Bioinformatics Clinical metadata Heart disease classification Multimodal learning Spectral analysis Transformers 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-6076597\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":418896027,\"identity\":\"86a7d024-4d14-4af7-8866-4b2da5152cf5\",\"order_by\":0,\"name\":\"Shintaro Fujisawa\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Sophia University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Shintaro\",\"middleName\":\"\",\"lastName\":\"Fujisawa\",\"suffix\":\"\"},{\"id\":418896028,\"identity\":\"d36a8aae-05e4-4fbd-9e3f-491504576f86\",\"order_by\":1,\"name\":\"Yusuke Fukazawa\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA60lEQVRIiWNgGAWjYBAC9gY2CIMfiJkZDCAcA3xaeA5AtUg2kKzF4ABICzGARyIt8eOPmsPyxucPH3tcUGDHwN9+gKG4AL+WwxISxw4bbruRlm48wyCZQeJMAoPxDDxa7CXSGyQM2G4zbrvBYybNYwB02w0GBmMevLakN/9I+HfbfnP/GZCWegZ5wlrSjkkcbLuduIEhB6TlMIMBQS08z9IsG/v+J88A+YXH4DiP4ZnEBrx+4WFPM77541uabX8/MMR4/lTLyR0/fMwYX4ghA3AMAZ3E2GZMpA4GNhiD+TGxWkbBKBgFo2BEAABibUbeb4VkFQAAAABJRU5ErkJggg==\",\"orcid\":\"https://orcid.org/0000-0001-9834-9339\",\"institution\":\"Sophia University\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Yusuke\",\"middleName\":\"\",\"lastName\":\"Fukazawa\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-02-21 06:25:53\",\"currentVersionCode\":1,\"declarations\":{\"humanSubjects\":true,\"vertebrateSubjects\":false,\"conflictsOfInterestStatement\":false,\"humanSubjectEthicalGuidelines\":true,\"humanSubjectConsent\":true,\"humanSubjectClinicalTrial\":true,\"humanSubjectCaseReport\":false,\"vertebrateSubjectEthicalGuidelines\":false},\"doi\":\"10.21203/rs.3.rs-6076597/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-6076597/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":76999953,\"identity\":\"0de60185-d46f-49c3-a48c-48503ba18396\",\"added_by\":\"auto\",\"created_at\":\"2025-02-24 07:26:19\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":1424906,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"20241207HealthInformationScienceandSystems.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-6076597/v1_covered_70445a20-b0b0-4157-9416-7fe754fcbf25.pdf\"}],\"financialInterests\":\"The authors declare no competing interests.\",\"formattedTitle\":\"\\u003cp\\u003eMultimodal Transformer for Heart Disease Classification Using Multiple Heart Sound Spectral Analyses and Clinical Metadata\\u003c/p\\u003e\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":true,\"hideJournal\":true,\"highlight\":\"\",\"institution\":\"Graduate Degree Program of Applied Data Sciences, Sophia University,\",\"isAcceptedByJournal\":false,\"isAuthorSuppliedPdf\":true,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":true,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"Clinical metadata, Heart disease classification, Multimodal learning, Spectral analysis, Transformers\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-6076597/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-6076597/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eThis study proposes a multimodal fusion framework for heart disease classification that combines multiple spectral analyses of heart sounds with clinical metadata. Our framework integrates four complementary spectral analysis methods (Stockwell transform, bispectrum, mel-spectrogram, and power spectrum) using Vision Transformers. This spectral fusion is further enhanced by incorporating clinical metadata processed through Bio\\\\_ClinicalBERT, enabling the capture of diagnostic insights from specialist physicians. Our framework achieved superior performance, with the model that fused both spectral features and clinical data reaching an accuracy of 0.881. This fusion model outperformed the individual spectral models, which had an accuracy of 0.831, by 6\\\\%. Additionally, incorporating clinical metadata resulted in a 2.6\\\\% improvement in accuracy compared to the model that fused only the four spectral features, which had an accuracy of 0.855. Through SHAP analysis, we discovered that our model excels at detecting right-heart abnormalities, which are often difficult to identify through traditional auscultation. Furthermore, we identified the Stockwell transform and mel-spectrogram as particularly influential features. The Stockwell transform's ability to localize both time and frequency information allowed our model to capture transient patterns crucial for detecting subtle heart sound abnormalities. Similarly, the mel-spectrogram, designed to mimic human auditory perception, excelled in highlighting frequency-related features commonly recognized by clinicians.\\u003c/p\\u003e\",\"manuscriptTitle\":\"Multimodal Transformer for Heart Disease Classification Using Multiple Heart Sound Spectral Analyses and Clinical Metadata\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-02-24 07:18:11\",\"doi\":\"10.21203/rs.3.rs-6076597/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"f423af2f-c44f-4eb9-bf08-55b2e1128515\",\"owner\":[],\"postedDate\":\"February 24th, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[{\"id\":44662594,\"name\":\"Bioinformatics\"}],\"tags\":[],\"updatedAt\":\"2025-02-24T07:18:11+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2025-02-24 07:18:11\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-6076597\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-6076597\",\"identity\":\"rs-6076597\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}