Developing Probabilistic Ensemble Machine Learning Models for Home-Based Sleep Apnea Screening using Overnight SpO2 Data at Varying Data Granularity

Developing Probabilistic Ensemble Machine Learning Models for Home-Based Sleep Apnea Screening using Overnight SpO2 Data at Varying Data Granularity | 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 Developing Probabilistic Ensemble Machine Learning Models for Home-Based Sleep Apnea Screening using Overnight SpO2 Data at Varying Data Granularity Zilu Liang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4358408/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract Purpose This study aims to develop sleep apnea screening models using a large clinical sleep dataset of SpO2 data, with the goal of achieving better performance and generalizability compared to existing models. Methods We utilized SpO2 recordings from the Sleep Heart Health Study database (N = 5667). Probabilistic ensemble machine learning was employed to predict sleep apnea status at three AHI cutoff points: ≥5, ≥ 15, and ≥ 30 events/hour. To investigate the impact of data granularity, SpO2 data were resampled to 1/30, 1/60, and 1/300 Hz. Model performance was evaluated across various decision boundaries ranging from 0.05 to 0.95. Results Our models demonstrated good to excellent performance, with AUC values of 0.82, 0.85, and 0.90 for cutoffs ≥ 5, ≥15, and ≥ 30, respectively. Sensitivity ranged from good to excellent (0.76, 0.84, 0.89), while specificity ranged from good to excellent (0.87, 0.86, 0.90). Positive predictive values (PPV) ranged from fair to excellent (0.97, 0.83, 0.66), and negative predictive values (NPV) ranged from low to excellent (0.43, 0.87, 0.98). Both decision boundaries and data granularity had a significant impact on model performance, with optimal decision boundaries aligning with the prevalence of positive cases in the cohort. Lower data granularity resulted in decreased model performance. Conclusion Our models demonstrated superior performance across all three AHI cutoff thresholds compared to existing large sleep apnea screening models, even when considering varying SpO2 data granularity. The use of probabilistic ensemble machine learning shows promises for developing generalizable sleep apnea screening models with overnight SpO2 data. Biomedical Engineering Sleep apnea SpO2 oximeter machine learning probabilistic learning ensemble learning decision boundary Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions 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-4358408","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":298538396,"identity":"01d43ed1-0e90-44ec-92bd-af0f4775d3f9","order_by":0,"name":"Zilu Liang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIiWNgGAWjYBACPmYIzcPHwHwYLmqATwsbTAsbA1sykVoQDB5j4hzGxs787OEXhjoZNomcz8Y8NXUM/O0HGIoL8DqMzdxYhoGNh00id3Myz7HDDBJnEhiMZ+DVwmAmLcHAA9ZymIftAAPDDQYGYx68Wti/AbVIALXkPD7M86+OQZ6wFh4zyQ8MBiAtzMm8bcwMBkRoKZNmMEjgYeN5Zmw4t+8wj+GZxAa8fuHnP75N8kdFnT0/e/JjiTff6uTkjh8+ZowvxECAmQcp6oBOYmwjGEOMP9DNeExIyygYBaNgFIwoAADutTSGtrEJmwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-2328-5016","institution":"Kyoto University of Advanced Science","correspondingAuthor":true,"prefix":"","firstName":"Zilu","middleName":"","lastName":"Liang","suffix":""}],"badges":[],"createdAt":"2024-05-02 10:07:15","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-4358408/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-4358408/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":56204780,"identity":"f8404d8d-566b-49cf-a6c0-ad9520d22e93","added_by":"auto","created_at":"2024-05-09 20:48:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":744603,"visible":true,"origin":"","legend":"","description":"","filename":"probabilisticEnsemblev3.1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4358408/v2_covered_c520358e-24e4-4437-815d-1b96898d76af.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Developing Probabilistic Ensemble Machine Learning Models for Home-Based Sleep Apnea Screening using Overnight SpO2 Data at Varying Data Granularity","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Kyoto University of Advanced Science","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"Sleep apnea, SpO2, oximeter, machine learning, probabilistic learning, ensemble learning, decision boundary","lastPublishedDoi":"10.21203/rs.3.rs-4358408/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4358408/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003ePurpose\u003c/h2\u003e \u003cp\u003eThis study aims to develop sleep apnea screening models using a large clinical sleep dataset of SpO2 data, with the goal of achieving better performance and generalizability compared to existing models.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eWe utilized SpO2 recordings from the Sleep Heart Health Study database (N\u0026thinsp;=\u0026thinsp;5667). Probabilistic ensemble machine learning was employed to predict sleep apnea status at three AHI cutoff points: \u0026ge;5, \u0026ge;\u0026thinsp;15, and \u0026ge;\u0026thinsp;30 events/hour. To investigate the impact of data granularity, SpO2 data were resampled to 1/30, 1/60, and 1/300 Hz. Model performance was evaluated across various decision boundaries ranging from 0.05 to 0.95.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eOur models demonstrated good to excellent performance, with AUC values of 0.82, 0.85, and 0.90 for cutoffs\u0026thinsp;\u0026ge;\u0026thinsp;5, \u0026ge;15, and \u0026ge;\u0026thinsp;30, respectively. Sensitivity ranged from good to excellent (0.76, 0.84, 0.89), while specificity ranged from good to excellent (0.87, 0.86, 0.90). Positive predictive values (PPV) ranged from fair to excellent (0.97, 0.83, 0.66), and negative predictive values (NPV) ranged from low to excellent (0.43, 0.87, 0.98). Both decision boundaries and data granularity had a significant impact on model performance, with optimal decision boundaries aligning with the prevalence of positive cases in the cohort. Lower data granularity resulted in decreased model performance.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eOur models demonstrated superior performance across all three AHI cutoff thresholds compared to existing large sleep apnea screening models, even when considering varying SpO2 data granularity. The use of probabilistic ensemble machine learning shows promises for developing generalizable sleep apnea screening models with overnight SpO2 data.\u003c/p\u003e","manuscriptTitle":"Developing Probabilistic Ensemble Machine Learning Models for Home-Based Sleep Apnea Screening using Overnight SpO2 Data at Varying Data Granularity","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2024-05-09 20:40:21","doi":"10.21203/rs.3.rs-4358408/v2","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}},{"code":1,"date":"2024-05-03 20:52:43","doi":"10.21203/rs.3.rs-4358408/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":"49fb115d-0d7f-44a5-80d9-7e12f890855d","owner":[],"postedDate":"May 9th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":31499719,"name":"Biomedical Engineering"}],"tags":[],"updatedAt":"2024-05-03T20:52:43+00:00","versionOfRecord":[],"versionCreatedAt":"2024-05-09 20:40:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-4358408","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4358408","identity":"rs-4358408","version":["v2"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}