Diagnosis and risk factor mining for valvular heart disease with atrial fibrillation via ensemble machine learning

Diagnosis and risk factor mining for valvular heart disease with atrial fibrillation via ensemble machine learning | 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 Diagnosis and risk factor mining for valvular heart disease with atrial fibrillation via ensemble machine learning Zhengjie Wang, Nuoyangfan Lei, Yiweng Zhang, Qi Tong, Yiren Sun, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4002924/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 Diagnosis and risk assessment of atrial fibrillation (AF) remain challenging. As the gold standard, a 12-lead electrocardiogram (ECG) has the limitations of missing diagnosis and high cost of 24-hour Holter ECG. Existing risk scores for AF are also limited by low accuracy. Although electronic health records (EHR) have rich information of patients and machine learning (ML) has been proven useful in medical applications, it is still an open issue how to utilize ML and EHR to analyze AF in patients with valvular heart disease. We collected the EHR of 2077 patients with valvular heart disease (707 cases of AF), and investigated logistic regression (LR), standard ML, and ensemble ML models combined with Smotenn and Shapley algorithms. In addition, we explored the factors related to the occurrence of AF from two aspects: population-individual level feature analysis and cut-off value estimation. The sensitivity of Stacking and Blending ensemble ML models is 0.851 (0.842-0.860) and 0.876 (0.868-0.883), respectively, significantly higher than that of other models (P value <0.001). According to the Shapley algorithm, the occurrence of AF was strongly correlated with the left atrial diameter (LAD), peak mitral e-wave velocity (Emv), stroke volume (SV), and right atrial diameter (RAD). Finally, three continuous features (LAD=43mm, Emv=1.2m/s, SV=44mL) were identified as potential AF risk cut-off values. The ensemble ML models show high potential to build knowledge-based AF diagnosis systems that can assist doctors in making a precise diagnosis of AF and give early warning to patients. Biological sciences/Computational biology and bioinformatics Health sciences/Diseases/Cardiovascular diseases/Arrhythmias/Atrial fibrillation Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryMaterial1.png SupplementaryMaterial2.docx SupplementaryMaterial3.pdf SupplementaryMaterial4.docx 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-4002924","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":280345625,"identity":"12d2aea2-6b88-476f-a488-8c0f02bac447","order_by":0,"name":"Zhengjie Wang","email":"","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Zhengjie","middleName":"","lastName":"Wang","suffix":""},{"id":280345626,"identity":"7628df99-3ceb-4b84-ba4d-87c94a0fa321","order_by":1,"name":"Nuoyangfan Lei","email":"","orcid":"","institution":"Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Nuoyangfan","middleName":"","lastName":"Lei","suffix":""},{"id":280345627,"identity":"03694f2c-fdf4-49f4-8a71-94190ea036e7","order_by":2,"name":"Yiweng Zhang","email":"","orcid":"","institution":"Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Yiweng","middleName":"","lastName":"Zhang","suffix":""},{"id":280345628,"identity":"c6436a8c-00f3-4499-beea-f50c59c557a5","order_by":3,"name":"Qi Tong","email":"","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Qi","middleName":"","lastName":"Tong","suffix":""},{"id":280345629,"identity":"629e3dba-e245-498a-8da9-1972d3af6b89","order_by":4,"name":"Yiren Sun","email":"","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Yiren","middleName":"","lastName":"Sun","suffix":""},{"id":280345630,"identity":"651eecfd-9c30-477f-a78f-6eee374c3422","order_by":5,"name":"Jie Cai","email":"","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Jie","middleName":"","lastName":"Cai","suffix":""},{"id":280345631,"identity":"6657dea8-e3d6-414f-aedb-1818340ebe68","order_by":6,"name":"Qiyue Xu","email":"","orcid":"","institution":"Mudanjiang Medical University","correspondingAuthor":false,"prefix":"","firstName":"Qiyue","middleName":"","lastName":"Xu","suffix":""},{"id":280345632,"identity":"93bdef63-72ff-4e99-b7dd-c8037efd5219","order_by":7,"name":"Oumar Mahamoud","email":"","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Oumar","middleName":"","lastName":"Mahamoud","suffix":""},{"id":280345633,"identity":"2b6fd2d7-fc21-4070-b2ae-82c66ed90c04","order_by":8,"name":"Xuemei Liu","email":"","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Xuemei","middleName":"","lastName":"Liu","suffix":""},{"id":280345634,"identity":"1eba8ee1-19e4-4773-86e1-69add304b98d","order_by":9,"name":"Qijun Zhao","email":"","orcid":"","institution":"Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Qijun","middleName":"","lastName":"Zhao","suffix":""},{"id":280345635,"identity":"1240591d-e40e-45c2-9557-66ddc7b7d6de","order_by":10,"name":"Yongjun Qian","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIiWNgGAWjYDACZijN2MDA+ADCTCBeC7MBcVqQAJsEUVr4jjM/e8xTcceueUbuscofNYcZ+NlzDBh+7sCtRfIwm7kxz5lnyY0z8tJu8xw7zCDZ88aAsfcMbi0GhxnMpHnbDiczzsgxu83YcJjB4EaOATNjGz4t7N/gWgp/ArXYE9bCA7bFDqSFgRdkiwQBLZKHecok55w5nMDY88ZYmudYOo/EmWcFB3vxaOE7f3ybxJuKw/aG7TmGH3/UWMvxtydvfPATjxaGAwwMTDwMDIkbGyB8Hqggfi2MPxgY7OXxqhoFo2AUjIIRDQBJplB+g4y0JQAAAABJRU5ErkJggg==","orcid":"","institution":"West China Hospital of Sichuan University","correspondingAuthor":true,"prefix":"","firstName":"Yongjun","middleName":"","lastName":"Qian","suffix":""}],"badges":[],"createdAt":"2024-03-01 10:46:52","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4002924/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4002924/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":57193653,"identity":"ae130587-b04a-458f-95d6-c15c910e6524","added_by":"auto","created_at":"2024-05-27 08:06:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1862237,"visible":true,"origin":"","legend":"","description":"","filename":"TemplateforsubmissionstoScientificReports5.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4002924/v1_covered_1db4d728-9fa7-445d-83cb-727875106d42.pdf"},{"id":52984961,"identity":"e4f1cd96-e929-43cf-b5a9-24d89e4742f3","added_by":"auto","created_at":"2024-03-19 11:01:04","extension":"png","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":92945,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterial1.png","url":"https://assets-eu.researchsquare.com/files/rs-4002924/v1/1df9a778f7e75cf1a1b0f7b4.png"},{"id":52984960,"identity":"8949132f-82a9-45b9-9c9e-db10309d0bad","added_by":"auto","created_at":"2024-03-19 11:01:04","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":11906,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterial2.docx","url":"https://assets-eu.researchsquare.com/files/rs-4002924/v1/5304e7fa6e81d28b9bda059f.docx"},{"id":52984962,"identity":"73347de8-be91-456f-9a81-53ecef514c1d","added_by":"auto","created_at":"2024-03-19 11:01:04","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":121785,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterial3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4002924/v1/9b66daae6470bedd291d869c.pdf"},{"id":52984963,"identity":"33b2a832-02ca-4812-a94a-1ea19da1fd0b","added_by":"auto","created_at":"2024-03-19 11:01:04","extension":"docx","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":11112,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterial4.docx","url":"https://assets-eu.researchsquare.com/files/rs-4002924/v1/469297c16e3f0e7f7778e8f0.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Diagnosis and risk factor mining for valvular heart disease with atrial fibrillation via ensemble machine learning","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":"","lastPublishedDoi":"10.21203/rs.3.rs-4002924/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4002924/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Diagnosis and risk assessment of atrial fibrillation (AF) remain challenging. As the gold standard, a 12-lead electrocardiogram (ECG) has the limitations of missing diagnosis and high cost of 24-hour Holter ECG. Existing risk scores for AF are also limited by low accuracy. Although electronic health records (EHR) have rich information of patients and machine learning (ML) has been proven useful in medical applications, it is still an open issue how to utilize ML and EHR to analyze AF in patients with valvular heart disease. We collected the EHR of 2077 patients with valvular heart disease (707 cases of AF), and investigated logistic regression (LR), standard ML, and ensemble ML models combined with Smotenn and Shapley algorithms. In addition, we explored the factors related to the occurrence of AF from two aspects: population-individual level feature analysis and cut-off value estimation. The sensitivity of Stacking and Blending ensemble ML models is 0.851 (0.842-0.860) and 0.876 (0.868-0.883), respectively, significantly higher than that of other models (P value \u003c0.001). According to the Shapley algorithm, the occurrence of AF was strongly correlated with the left atrial diameter (LAD), peak mitral e-wave velocity (Emv), stroke volume (SV), and right atrial diameter (RAD). Finally, three continuous features (LAD=43mm, Emv=1.2m/s, SV=44mL) were identified as potential AF risk cut-off values. The ensemble ML models show high potential to build knowledge-based AF diagnosis systems that can assist doctors in making a precise diagnosis of AF and give early warning to patients.","manuscriptTitle":"Diagnosis and risk factor mining for valvular heart disease with atrial fibrillation via ensemble machine learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-19 11:00:59","doi":"10.21203/rs.3.rs-4002924/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":"60f6d6ac-6690-457e-b257-1a954078b7ad","owner":[],"postedDate":"March 19th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":29524912,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":29524913,"name":"Health sciences/Diseases/Cardiovascular diseases/Arrhythmias/Atrial fibrillation"}],"tags":[],"updatedAt":"2024-05-27T08:06:33+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-19 11:00:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4002924","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4002924","identity":"rs-4002924","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}