Remote Monitoring in Dementia Care - Lightweight, Explainable AI Validated for Early Warning of Health Events in the Home

Remote Monitoring in Dementia Care - Lightweight, Explainable AI Validated for Early Warning of Health Events in the Home | 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 Remote Monitoring in Dementia Care - Lightweight, Explainable AI Validated for Early Warning of Health Events in the Home Nivedita Bijlani, Gustavo, Ramin Nilforooshan, CR&T Group, Payam Barnaghi, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6294980/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 Sensor-based remote health monitoring for people living with dementia (PLwD) enables early detection of adverse health events, reducing hospitalization risk. Identifying anomalies in real-world home activity data poses significant challenges due to noise, imprecise labels, inter-household variability, and the need for clinical explainability. We propose a lightweight, explainable AI pipeline for anomaly detection in home sensor data, aimed at early detection of health events, validated in an ongoing real-world dementia monitoring study. Our model generates noise-resilient daily representations to compute anomaly scores, compared against household-personalized thresholds to trigger alerts. Novel spatiotemporal attention maps uncover the source and timing of anomalies, offering household-specific and cohort-wide insights into atypical behavior patterns. Maximum typicality metrics provide a dynamic and continuous distinction between typical and atypical days, enabling real-time adaptation to incoming patient data. In addition, LLM-powered anomaly summaries support clinical monitoring teams by providing detailed descriptions of sensory observations. On a 65-patient internal validation cohort (18,800 person-days; Aug 2019-Apr 2022), the model achieved 84.64±2.36% sensitivity and 92.16±2.33% generalizability at a 7% maximum alert rate. In a larger 90-patient cohort (40,586 person-days; May 2022–Feb 2024), it achieved 77.04±1.35% sensitivity and 90.67±1.51% generalizability, a strong result given the inherent noise and variability of home sensor data. This AI-powered anomaly detection pipeline demonstrates high clinical utility for early in-home detection of health events in dementia care, and can be easily adapted to diverse remote monitoring settings. Artificial Intelligence and Machine Learning sensor-based remote health monitoring dementia self-supervised machine learning explainable AI Full Text Additional Declarations The authors declare no competing interests. Supplementary Files SupplementaryMaterial.pdf Supplementary Material AcknowledgementlistforUKDementiaResearchInstitute1.6.pdf Acknowledgement list for the UK DRI CR&T 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-6294980","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":433140702,"identity":"41abeb37-ba6a-42d9-9184-e22855dbae96","order_by":0,"name":"Nivedita Bijlani","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9ElEQVRIiWNgGAWjYFACHoYDEgUMDGzsDciiBwhpMQBq4UFRRUALAwNQC4NEApFazBl4Dx6wMLDL45N8/ky6co9NYgP74QfMPGdwa7Fs4EsAOiy5mE06x0zyzLO0xAaeNANmnhu4tRgc4DEAamFObJPOYZNsOHA4sYEhh4GZ5wNBLfWJbZLHnwG1/E9s4H9DlJbDiW0SDGZALQcSGyRAtuBz2GGwX44ntvHkGFs2HEg2bpN4ZnBwDh7vGxzvPfxZoqI6cX778Yc3Gw7YyfbzJz988OYYbi0MzEAkgcR3bGMgEJEgwIjsV3tCqkfBKBgFo2DkAQAC1U/0llI5FwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-9862-4732","institution":"University of Surrey","correspondingAuthor":true,"prefix":"","firstName":"Nivedita","middleName":"","lastName":"Bijlani","suffix":""},{"id":433140703,"identity":"7d0c8f38-7908-461b-81b7-908a404570a7","order_by":1,"name":"Gustavo","email":"","orcid":"https://orcid.org/0000-0002-5571-6220","institution":"Carneiro","correspondingAuthor":false,"prefix":"","firstName":"","middleName":"","lastName":"Gustavo","suffix":""},{"id":433140704,"identity":"e813f742-783c-4162-9e97-2a5c54275d06","order_by":2,"name":"Ramin Nilforooshan","email":"","orcid":"https://orcid.org/0000-0001-9801-183X","institution":"Surrey and Borders Partnership NHS Foundation Trust","correspondingAuthor":false,"prefix":"","firstName":"Ramin","middleName":"","lastName":"Nilforooshan","suffix":""},{"id":433140705,"identity":"7703aa88-c43b-4b77-9cb8-cbd0588d39cc","order_by":3,"name":"CR\u0026T Group","email":"","orcid":"","institution":"UK Dementia Research Institute","correspondingAuthor":false,"prefix":"","firstName":"CR\u0026T","middleName":"","lastName":"Group","suffix":""},{"id":433140706,"identity":"319c6827-4350-4cee-9571-f5ed2720b3a5","order_by":4,"name":"Payam Barnaghi","email":"","orcid":"https://orcid.org/0000-0001-8591-9638","institution":"UK Dementia Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Payam","middleName":"","lastName":"Barnaghi","suffix":""},{"id":433140707,"identity":"8383d18d-3166-4d9a-aa2d-edb2cdbe8ce5","order_by":5,"name":"Samaneh Kouchaki","email":"","orcid":"https://orcid.org/0000-0002-5870-4030","institution":"University of Surrey","correspondingAuthor":false,"prefix":"","firstName":"Samaneh","middleName":"","lastName":"Kouchaki","suffix":""}],"badges":[],"createdAt":"2025-03-24 11:41:06","currentVersionCode":1,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6294980/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6294980/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79145520,"identity":"30bd2013-0e62-4d7a-a7fb-dac9da96c94e","added_by":"auto","created_at":"2025-03-25 02:57:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6259831,"visible":true,"origin":"","legend":"","description":"","filename":"RemoteMonitoringinDementiaCareLightweightExplainableAIValidatedforEarlyWarningofHealthEventsintheHome.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6294980/v1_covered_b192826a-248b-4bd9-a3b5-7433765aacdc.pdf"},{"id":79144895,"identity":"ef2ef819-5853-4162-a632-42febcf7e547","added_by":"auto","created_at":"2025-03-25 02:48:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":10987818,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary Material\u003c/p\u003e","description":"","filename":"SupplementaryMaterial.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6294980/v1/2aaf682b1f4bd844dd6ab821.pdf"},{"id":79144894,"identity":"5149aea0-7fd8-4246-8de7-47d577d1378e","added_by":"auto","created_at":"2025-03-25 02:48:50","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":134983,"visible":true,"origin":"","legend":"\u003cp\u003eAcknowledgement list for the UK DRI CR\u0026amp;T\u003c/p\u003e","description":"","filename":"AcknowledgementlistforUKDementiaResearchInstitute1.6.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6294980/v1/de7786b8a83960a16f4b243d.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eRemote Monitoring in Dementia Care - Lightweight, Explainable AI Validated for Early Warning of Health Events in the Home\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"UK Dementia Research Institute","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":"sensor-based remote health monitoring, dementia, self-supervised machine learning, explainable AI","lastPublishedDoi":"10.21203/rs.3.rs-6294980/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6294980/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSensor-based remote health monitoring for people living with dementia (PLwD) enables early detection of adverse health events, reducing hospitalization risk. Identifying anomalies in real-world home activity data poses significant challenges due to noise, imprecise labels, inter-household variability, and the need for clinical explainability. We propose a lightweight, explainable AI pipeline for anomaly detection in home sensor data, aimed at early detection of health events, validated in an ongoing real-world dementia monitoring study. Our model generates noise-resilient daily representations to compute anomaly scores, compared against household-personalized thresholds to trigger alerts. Novel spatiotemporal attention maps uncover the source and timing of anomalies, offering household-specific and cohort-wide insights into atypical behavior patterns. Maximum typicality metrics provide a dynamic and continuous distinction between typical and atypical days, enabling real-time adaptation to incoming patient data. In addition, LLM-powered anomaly summaries support clinical monitoring teams by providing detailed descriptions of sensory observations. On a 65-patient internal validation cohort (18,800 person-days; Aug 2019-Apr 2022), the model achieved 84.64±2.36% sensitivity and 92.16±2.33% generalizability at a 7% maximum alert rate. In a larger 90-patient cohort (40,586 person-days; May 2022–Feb 2024), it achieved 77.04±1.35% sensitivity and 90.67±1.51% generalizability, a strong result given the inherent noise and variability of home sensor data. This AI-powered anomaly detection pipeline demonstrates high clinical utility for early in-home detection of health events in dementia care, and can be easily adapted to diverse remote monitoring settings.\u003c/p\u003e","manuscriptTitle":"Remote Monitoring in Dementia Care - Lightweight, Explainable AI Validated for Early Warning of Health Events in the Home","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-25 02:48:45","doi":"10.21203/rs.3.rs-6294980/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":"1fd2e2b7-6156-45b6-895d-2255b1acda38","owner":[],"postedDate":"March 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46121659,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-03-25T02:48:46+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-25 02:48:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6294980","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6294980","identity":"rs-6294980","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}