Sleep EEG foundation models reveal within-stage microstructure that improves health screening beyond traditional stages

Sleep EEG foundation models reveal within-stage microstructure that improves health screening beyond traditional stages | 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 Sleep EEG foundation models reveal within-stage microstructure that improves health screening beyond traditional stages William Grey Coon, Mattson Ogg This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9044150/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Sleep is a rich longitudinal biosignal reflecting integrated brain and systemic physiology, yet polysomnography reduces to a lossy clinical interface of coarse, human-defined stages. We asked whether self-supervised foundation models learn sleep EEG structure beyond traditional staging and encode enriched health information. Using 11,261 overnight recordings, we trained transformers on unlabeled sleep data and probed representations across diagnostic, demographic and functional outcomes. Self-supervised models outperformed matched from-scratch models and exceeded five-stage–supervised pretraining for several endpoints (BMI, age, mood and cognition), while remaining comparable for apnea severity and sex. In nested controls, EEG-derived self-supervised model scores retained incremental predictive value beyond demographic covariates and stage-derived sleep-report summaries, indicating that gains are not explained by model architecture or coarse sleep architecture alone. Embedding analyses show that the models recover the stage scaffold without labels yet resolve within-stage microstructure—especially within N2—that improves health prediction and supports scalable EEG-only digital biomarkers. Health sciences/Biomarkers Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Health sciences/Health care Health sciences/Medical research Biological sciences/Neuroscience Full Text Additional Declarations No competing interests reported. Supplementary Files 20260306REVnpjDMSleep2.0SupplementJHUAPLCoonOgg.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 15 Apr, 2026 Reviews received at journal 13 Apr, 2026 Reviews received at journal 09 Apr, 2026 Reviewers agreed at journal 16 Mar, 2026 Reviewers agreed at journal 15 Mar, 2026 Reviews received at journal 13 Mar, 2026 Reviewers agreed at journal 12 Mar, 2026 Reviewers invited by journal 11 Mar, 2026 Editor assigned by journal 06 Mar, 2026 Submission checks completed at journal 06 Mar, 2026 First submitted to journal 05 Mar, 2026 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-9044150","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":602456884,"identity":"6e5b4352-a7e0-4f72-bb51-2a5978179f15","order_by":0,"name":"William Grey Coon","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3ElEQVRIiWNgGAWjYDACZubGA2AGe0MaiJIBYgMCWhgbIFp4DoC18BDWwgDTIpHARpwWg+MgLTU2cuaSD5495qm5w8PA3rxNAq+WwyAtx9KMLWcnpBvzHHvGw8BzrAyvFjOQFsaGw4kbbiekSfOwHeZhkMgxI1LLzQNALf+AWuTfEKvlBkOaNG8byBYe/FrsQVoSgH4xOJOQJjm37xkPG09asQU+LZL9hw8++AAMMYPjZ9Ik3ny7I8fPfnjjDXxawCABTPKAqAMMbASVIwD7AbCWUTAKRsEoGAXoAACcrkqeG0MqHwAAAABJRU5ErkJggg==","orcid":"","institution":"Johns Hopkins University Applied Physics Laboratory","correspondingAuthor":true,"prefix":"","firstName":"William","middleName":"Grey","lastName":"Coon","suffix":""},{"id":602456885,"identity":"452107df-1f1e-4499-b306-832fd0d4b00b","order_by":1,"name":"Mattson Ogg","email":"","orcid":"","institution":"Johns Hopkins University Applied Physics Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Mattson","middleName":"","lastName":"Ogg","suffix":""}],"badges":[],"createdAt":"2026-03-05 21:23:37","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9044150/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9044150/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104242785,"identity":"5c4b905b-2f03-475f-8ba1-b05900fd1a0e","added_by":"auto","created_at":"2026-03-09 14:42:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1537525,"visible":true,"origin":"","legend":"","description":"","filename":"20260306REVnpjDMSleep2.0MainTextJHUAPLCoonOgg.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9044150/v1_covered_3460660c-9c4b-419a-9e3f-0e91f9f58237.pdf"},{"id":104242768,"identity":"cfb01d30-eb4a-466f-b2a7-8b3a5b90a95a","added_by":"auto","created_at":"2026-03-09 14:42:15","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":7082213,"visible":true,"origin":"","legend":"","description":"","filename":"20260306REVnpjDMSleep2.0SupplementJHUAPLCoonOgg.docx","url":"https://assets-eu.researchsquare.com/files/rs-9044150/v1/4d26a7a08b9f1bbba1aea358.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Sleep EEG foundation models reveal within-stage microstructure that improves health screening beyond traditional stages","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9044150/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9044150/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSleep is a rich longitudinal biosignal reflecting integrated brain and systemic physiology, yet polysomnography reduces to a lossy clinical interface of coarse, human-defined stages. We asked whether self-supervised foundation models learn sleep EEG structure beyond traditional staging and encode enriched health information. Using 11,261 overnight recordings, we trained transformers on unlabeled sleep data and probed representations across diagnostic, demographic and functional outcomes. Self-supervised models outperformed matched from-scratch models and exceeded five-stage\u0026ndash;supervised pretraining for several endpoints (BMI, age, mood and cognition), while remaining comparable for apnea severity and sex. In nested controls, EEG-derived self-supervised model scores retained incremental predictive value beyond demographic covariates and stage-derived sleep-report summaries, indicating that gains are not explained by model architecture or coarse sleep architecture alone. Embedding analyses show that the models recover the stage scaffold without labels yet resolve within-stage microstructure\u0026mdash;especially within N2\u0026mdash;that improves health prediction and supports scalable EEG-only digital biomarkers.\u003c/p\u003e","manuscriptTitle":"Sleep EEG foundation models reveal within-stage microstructure that improves health screening beyond traditional stages","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-09 14:41:09","doi":"10.21203/rs.3.rs-9044150/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-15T05:56:57+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-13T20:38:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-09T08:01:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"228671487404891462864095226023908378423","date":"2026-03-16T13:18:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"237488320736652303303980295101137832806","date":"2026-03-15T21:54:41+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-13T15:02:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"326980250624312116559823451633757092896","date":"2026-03-12T08:16:33+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-11T23:17:34+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-06T17:18:27+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-06T11:48:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Medicine","date":"2026-03-05T21:17:07+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8e219611-2e36-4dc4-8e87-4cefa26db8f8","owner":[],"postedDate":"March 9th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":64111798,"name":"Health sciences/Biomarkers"},{"id":64111799,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":64111800,"name":"Physical sciences/Engineering"},{"id":64111801,"name":"Health sciences/Health care"},{"id":64111802,"name":"Health sciences/Medical research"},{"id":64111803,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2026-05-05T22:08:07+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-09 14:41:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9044150","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9044150","identity":"rs-9044150","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}