Prototype-based sleep micro-structure learning for explainable and robust multimodal recognition of sleep-related conditions

Prototype-based sleep micro-structure learning for explainable and robust multimodal recognition of sleep-related conditions | 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 Prototype-based sleep micro-structure learning for explainable and robust multimodal recognition of sleep-related conditions Guido Gagliardi, Javier Garcia Ciudad, Letizia Micca, Birgitte Rahbek Kornum, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9169987/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract While sleep is fundamental to human health, sleep disturbances reduce quality of life and constitute risk factors for neurodegenerative diseases including Parkinson's and Alzheimer's. Automated sleep staging networks achieve human-level performance on multimodal physiological signals, but they operate as black boxes, limiting clinical trust and preventing the discovery and validation of sleep biomarkers linked to human health status.We propose ProtoSleepNet (PSN), the fist prototype-based sequence-to-sequence sleep staging architecture that achieves human-level sleep staging accuracy while providing interpretability through an intrinsic codebook of learned prototypes. Each prototype captures distinctive sleep microstructure patterns, visualized as physiologically meaningful features across EEG, EOG, and EMG channels. We validate PSN against state-of-the-art approaches on over 10,000 subject recordings across 10 benchmark datasets, demonstrating in-line or superior sleep staging performance, robustness to channel occlusion attacks, and interpretability through a novel explainability framework that translates abstract prototypes into clinically aligned natural-language matching rules.Finally, we show that prototype sequences (prototype-grams) from individual patients encode clinically relevant information: without any disease-specific training, prototype-grams effectively discriminate Parkinson's and Alzheimer's disease patients from healthy controls, revealing disease-specific sleep microstructure alterations aligned with known pathophysiology. Health sciences/Biomarkers Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Health sciences/Neurology Biological sciences/Neuroscience Prototype Learning Explainable AI Sleep Staging Physiological Time Series Full Text Additional Declarations No competing interests reported. Supplementary Files ProtoSleepNet5.pdf Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 14 May, 2026 Reviewers agreed at journal 19 Apr, 2026 Reviewers agreed at journal 12 Apr, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviewers invited by journal 30 Mar, 2026 Editor assigned by journal 23 Mar, 2026 Submission checks completed at journal 23 Mar, 2026 First submitted to journal 19 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-9169987","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":614677044,"identity":"bd06cb93-7588-413d-aad6-ac5491f1cb34","order_by":0,"name":"Guido Gagliardi","email":"data:image/png;base64,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","orcid":"","institution":"KU Leuven","correspondingAuthor":true,"prefix":"","firstName":"Guido","middleName":"","lastName":"Gagliardi","suffix":""},{"id":614677048,"identity":"25008214-74ca-4eb5-8236-8bd1d68880ac","order_by":1,"name":"Javier Garcia Ciudad","email":"","orcid":"","institution":"University of Copenhagen","correspondingAuthor":false,"prefix":"","firstName":"Javier","middleName":"Garcia","lastName":"Ciudad","suffix":""},{"id":614677049,"identity":"2c8cd3fa-e1df-43de-9a01-8740f64dd1eb","order_by":2,"name":"Letizia Micca","email":"","orcid":"","institution":"KU Leuven","correspondingAuthor":false,"prefix":"","firstName":"Letizia","middleName":"","lastName":"Micca","suffix":""},{"id":614677050,"identity":"42569544-462b-4cda-9f7d-b8ed7c4321bb","order_by":3,"name":"Birgitte Rahbek Kornum","email":"","orcid":"","institution":"University of Copenhagen","correspondingAuthor":false,"prefix":"","firstName":"Birgitte","middleName":"Rahbek","lastName":"Kornum","suffix":""},{"id":614677052,"identity":"5f7caf9f-d2f4-4033-b24f-78a84f33a558","order_by":4,"name":"Moran Gilat","email":"","orcid":"","institution":"KU Leuven","correspondingAuthor":false,"prefix":"","firstName":"Moran","middleName":"","lastName":"Gilat","suffix":""},{"id":614677055,"identity":"4cef6814-149f-4221-8497-19a1196fb92e","order_by":5,"name":"Antonio Luca Alfeo","email":"","orcid":"","institution":"Università degli Studi eCampus","correspondingAuthor":false,"prefix":"","firstName":"Antonio","middleName":"Luca","lastName":"Alfeo","suffix":""},{"id":614677057,"identity":"bc074d2e-12c8-4561-b200-983c4ba2d499","order_by":6,"name":"Mario G.C.A. Cimino","email":"","orcid":"","institution":"University of Pisa","correspondingAuthor":false,"prefix":"","firstName":"Mario","middleName":"G.C.A.","lastName":"Cimino","suffix":""},{"id":614677058,"identity":"26ebe1ba-2e48-4749-8446-08695e057c0c","order_by":7,"name":"Maarten De Vos","email":"","orcid":"","institution":"KU Leuven","correspondingAuthor":false,"prefix":"","firstName":"Maarten","middleName":"","lastName":"De Vos","suffix":""}],"badges":[],"createdAt":"2026-03-19 13:24:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9169987/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9169987/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106093173,"identity":"437e4645-5ddc-46c5-bdd6-06633cc341fd","added_by":"auto","created_at":"2026-04-03 11:35:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":603914,"visible":true,"origin":"","legend":"","description":"","filename":"ProtoSleepNet4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9169987/v1_covered_7fba65f6-14c8-4b41-911e-a120297e6756.pdf"},{"id":105937489,"identity":"fd8fb9c8-351c-4b2f-84d5-04df144c2bc1","added_by":"auto","created_at":"2026-04-01 15:14:23","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":517842,"visible":true,"origin":"","legend":"","description":"","filename":"ProtoSleepNet5.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9169987/v1/de65f99e60be1e7ef01194cc.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prototype-based sleep micro-structure learning for explainable and robust multimodal recognition of sleep-related conditions","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Prototype Learning, Explainable AI, Sleep Staging, Physiological Time Series","lastPublishedDoi":"10.21203/rs.3.rs-9169987/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9169987/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"While sleep is fundamental to human health, sleep disturbances reduce quality of life and constitute risk factors for neurodegenerative diseases including Parkinson's and Alzheimer's. Automated sleep staging networks achieve human-level performance on multimodal physiological signals, but they operate as black boxes, limiting clinical trust and preventing the discovery and validation of sleep biomarkers linked to human health status.We propose ProtoSleepNet (PSN), the fist prototype-based sequence-to-sequence sleep staging architecture that achieves human-level sleep staging accuracy while providing interpretability through an intrinsic codebook of learned prototypes. Each prototype captures distinctive sleep microstructure patterns, visualized as physiologically meaningful features across EEG, EOG, and EMG channels. We validate PSN against state-of-the-art approaches on over 10,000 subject recordings across 10 benchmark datasets, demonstrating in-line or superior sleep staging performance, robustness to channel occlusion attacks, and interpretability through a novel explainability framework that translates abstract prototypes into clinically aligned natural-language matching rules.Finally, we show that prototype sequences (prototype-grams) from individual patients encode clinically relevant information: without any disease-specific training, prototype-grams effectively discriminate Parkinson's and Alzheimer's disease patients from healthy controls, revealing disease-specific sleep microstructure alterations aligned with known pathophysiology.","manuscriptTitle":"Prototype-based sleep micro-structure learning for explainable and robust multimodal recognition of sleep-related conditions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-01 15:14:19","doi":"10.21203/rs.3.rs-9169987/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"324488928612839528593989211818166368022","date":"2026-05-14T16:57:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"59831551657797398896436550558298125390","date":"2026-04-20T02:23:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"191441926542779309482632539853020095497","date":"2026-04-12T20:46:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"153877852081645322892240366827834813482","date":"2026-04-09T16:29:26+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-30T10:15:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-24T00:05:03+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-23T04:10:15+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Medicine","date":"2026-03-19T13:16:40+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":"2a6d033d-44d6-47de-a836-c53bbd4452ad","owner":[],"postedDate":"April 1st, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"324488928612839528593989211818166368022","date":"2026-05-14T16:57:02+00:00","index":25,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":65406108,"name":"Health sciences/Biomarkers"},{"id":65406109,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":65406110,"name":"Physical sciences/Engineering"},{"id":65406111,"name":"Health sciences/Neurology"},{"id":65406112,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2026-04-01T15:14:19+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-01 15:14:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9169987","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9169987","identity":"rs-9169987","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}