Personalized Early Detection of Depression Onset Using Multivariate Mobile Passive Sensing

Personalized Early Detection of Depression Onset Using Multivariate Mobile Passive Sensing | 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 Personalized Early Detection of Depression Onset Using Multivariate Mobile Passive Sensing Hadar Fisher, Subigya Nepal, Christian A. Webb This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8960944/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 Major depressive disorder is common, recurrent, and typically detected only after full symptom onset. Passive smartphone sensing offers a scalable approach to continuous, low-burden behavioral monitoring of depression risk, but prior work applying single-variable statistical process control (SPC) methods to passive sensing data has not yielded reliable prospective detection of depressive episodes. We examined whether multivariate SPC methods applied to passive sensing data could improve prospective detection of depressive symptom onset. We analyzed data from 82 college students (31.7% developed elevated depressive symptoms) followed for up to four years using continuous passive smartphone sensing. We applied exponentially weighted moving average (EWMA) control charts to individual EMA (self-esteem, stress, social level) and passive sensing variables (activity, sleep, location visits), a multivariate EWMA procedure, and a principal component analysis-based EWMA (PCA-EWMA) integrating the full passive sensing feature space. While univariate models performed poorly (MCC = .06–.21), PCA-EWMA showed stronger performance (MCC = .39–.42; sensitivity 81–85%), with up to 76.2% of alerts occurring before future depressive symptom onset. Variable contribution analyses revealed person-specific behavioral signatures driving alerts. These findings show that coordinated behavioral changes passively detected via smartphones can signal rising depressive symptoms. Health sciences/Biomarkers Health sciences/Diseases Biological sciences/Neuroscience Biological sciences/Psychology Social science/Psychology depression passive sensing statistical process control early warning signals ecological momentary assessment digital phenotyping Full Text Additional Declarations Competing interest reported. CW has received consulting fees from King & Spalding law firm but declares no non-financial competing interests. CW’s interests were reviewed and are managed by McLean Hospital and Mass General Brigham in accordance with their conflict of interest policies. No funding from this entity was used to support the current work, and all views expressed are solely those of the authors. The other authors declare no competing financial or non-financial interests. 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-8960944","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":600432574,"identity":"1dc9baa1-4a46-4360-b8c8-803993fe9d71","order_by":0,"name":"Hadar Fisher","email":"data:image/png;base64,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","orcid":"","institution":"Harvard Medical School","correspondingAuthor":true,"prefix":"","firstName":"Hadar","middleName":"","lastName":"Fisher","suffix":""},{"id":600432575,"identity":"0e56b539-7be0-4af5-ba91-f4aeade29794","order_by":1,"name":"Subigya Nepal","email":"","orcid":"","institution":"University of Virginia","correspondingAuthor":false,"prefix":"","firstName":"Subigya","middleName":"","lastName":"Nepal","suffix":""},{"id":600432576,"identity":"0d117dfa-bb6d-4136-a98a-5ccc83dcd6a9","order_by":2,"name":"Christian A. Webb","email":"","orcid":"","institution":"Harvard Medical School","correspondingAuthor":false,"prefix":"","firstName":"Christian","middleName":"A.","lastName":"Webb","suffix":""}],"badges":[],"createdAt":"2026-02-24 20:38:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8960944/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8960944/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104402445,"identity":"12e3f93d-04e8-467a-817e-8615766c31ab","added_by":"auto","created_at":"2026-03-11 12:15:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":995271,"visible":true,"origin":"","legend":"","description":"","filename":"SPCnpjdigitalmedicineFinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8960944/v1_covered_34ebc2ea-11a1-462a-ac15-5d28d38e3d42.pdf"}],"financialInterests":"Competing interest reported. CW has received consulting fees from King \u0026 Spalding law firm but declares no non-financial competing interests. CW’s interests were reviewed and are managed by McLean Hospital and Mass General Brigham in accordance with their conflict of interest policies. No funding from this entity was used to support the current work, and all views expressed are solely those of the authors. The other authors declare no competing financial or non-financial interests.","formattedTitle":"Personalized Early Detection of Depression Onset Using Multivariate Mobile Passive Sensing","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"depression, passive sensing, statistical process control, early warning signals, ecological momentary assessment, digital phenotyping","lastPublishedDoi":"10.21203/rs.3.rs-8960944/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8960944/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Major depressive disorder is common, recurrent, and typically detected only after full symptom onset. Passive smartphone sensing offers a scalable approach to continuous, low-burden behavioral monitoring of depression risk, but prior work applying single-variable statistical process control (SPC) methods to passive sensing data has not yielded reliable prospective detection of depressive episodes. We examined whether multivariate SPC methods applied to passive sensing data could improve prospective detection of depressive symptom onset. We analyzed data from 82 college students (31.7% developed elevated depressive symptoms) followed for up to four years using continuous passive smartphone sensing. We applied exponentially weighted moving average (EWMA) control charts to individual EMA (self-esteem, stress, social level) and passive sensing variables (activity, sleep, location visits), a multivariate EWMA procedure, and a principal component analysis-based EWMA (PCA-EWMA) integrating the full passive sensing feature space. While univariate models performed poorly (MCC = .06–.21), PCA-EWMA showed stronger performance (MCC = .39–.42; sensitivity 81–85%), with up to 76.2% of alerts occurring before future depressive symptom onset. Variable contribution analyses revealed person-specific behavioral signatures driving alerts. These findings show that coordinated behavioral changes passively detected via smartphones can signal rising depressive symptoms.","manuscriptTitle":"Personalized Early Detection of Depression Onset Using Multivariate Mobile Passive Sensing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-05 14:38:01","doi":"10.21203/rs.3.rs-8960944/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":"b9bcf85a-a832-45aa-9806-a53b68886bd0","owner":[],"postedDate":"March 5th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":63894331,"name":"Health sciences/Biomarkers"},{"id":63894332,"name":"Health sciences/Diseases"},{"id":63894333,"name":"Biological sciences/Neuroscience"},{"id":63894334,"name":"Biological sciences/Psychology"},{"id":63894335,"name":"Social science/Psychology"}],"tags":[],"updatedAt":"2026-03-05T14:38:01+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-05 14:38:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8960944","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8960944","identity":"rs-8960944","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}