Identifying High-Risk Patient Clusters for Falls Using Unsupervised Machine Learning on Linked Primary and Secondary Care Electronic Health Record Data

Identifying High-Risk Patient Clusters for Falls Using Unsupervised Machine Learning on Linked Primary and Secondary Care Electronic Health Record Data | 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 Identifying High-Risk Patient Clusters for Falls Using Unsupervised Machine Learning on Linked Primary and Secondary Care Electronic Health Record Data Rachael Lear, Rachel Tao, Catalina Carenzo, Ekin Yagis, Zhuoyu Li, and 7 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8612539/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 14 You are reading this latest preprint version Abstract Falls risk is multifactorial, involving a combination of clinical and sociodemographic factors. Although guidelines acknowledge this complexity, most research has focused on individual risk factors, leaving the combined impact of comorbidities relatively understudied. This population-wide study used electronic health records (EHR) linked across primary and secondary care to identify falls risk profiles in the North West London (NWL) population and to stratify patients by their likelihood of requiring falls-related hospital care using unsupervised clustering. We conducted cluster analysis on patients from NWL General Practice records using coded falls risk factors. Cluster membership was compared against the risk of falls-related hospital encounters. Among four identified clusters, two groups of older, multimorbid patients were 11 times more likely to have a fall-related hospital encounter (RR 11.45, 95% CI 10.14–12.92 and RR 11.63, 95% CI 10.30–13.13) and had significantly longer mean length of stay compared with younger, fitter patients. Between two younger clusters, patients with higher deprivation levels were 29% more likely to have a fall-related hospital encounter (RR 1.29, 95% CI 1.12–1.49). These findings demonstrate that clustering routinely collected EHR data can identify population segments at highest risk of falls-related hospital use, supporting more targeted, multifactorial risk assessment and prevention strategies. Health sciences/Diseases Health sciences/Health care Health sciences/Medical research Health sciences/Risk factors Falls Risk Factors Population Health Machine Learning Electronic Health Records Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 25 Mar, 2026 Reviews received at journal 19 Mar, 2026 Reviews received at journal 18 Mar, 2026 Reviews received at journal 18 Mar, 2026 Reviewers agreed at journal 17 Mar, 2026 Reviewers agreed at journal 17 Mar, 2026 Reviewers agreed at journal 16 Mar, 2026 Reviewers agreed at journal 16 Mar, 2026 Reviewers agreed at journal 16 Mar, 2026 Reviewers invited by journal 16 Mar, 2026 Editor assigned by journal 16 Mar, 2026 Editor invited by journal 26 Feb, 2026 Submission checks completed at journal 09 Feb, 2026 First submitted to journal 09 Feb, 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-8612539","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":607987558,"identity":"26521b7b-2aa2-43e4-935f-5ab3c05297b1","order_by":0,"name":"Rachael Lear","email":"","orcid":"","institution":"NIHR Imperial Biomedical Research Centre","correspondingAuthor":false,"prefix":"","firstName":"Rachael","middleName":"","lastName":"Lear","suffix":""},{"id":607987561,"identity":"33a04baa-a68e-4a42-b0b6-40fb285ac94e","order_by":1,"name":"Rachel Tao","email":"","orcid":"","institution":"NIHR Imperial Biomedical Research Centre","correspondingAuthor":false,"prefix":"","firstName":"Rachel","middleName":"","lastName":"Tao","suffix":""},{"id":607987564,"identity":"117db0d0-8ac9-4a0e-8b94-efb6dc329a88","order_by":2,"name":"Catalina Carenzo","email":"","orcid":"","institution":"NIHR Imperial Biomedical Research Centre","correspondingAuthor":false,"prefix":"","firstName":"Catalina","middleName":"","lastName":"Carenzo","suffix":""},{"id":607987567,"identity":"7829650f-e56a-49ea-a9e5-c6c1c702e7cd","order_by":3,"name":"Ekin Yagis","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvklEQVRIiWNgGAWjYLCCBAYbHjiTWC1ppGphYDiM0E0Q8EskP37x4M95Gf4G5ocfGNvSCGuRnJFmZpHYdptH4gCbsQRjWw5hLQY3EswMEhtu8xgwMJgxMLZVENZifyP9m0HCn3NALezfiNNiIJFj/CCB7QBQCw/IFiIcJnHmTRlDYlsyj8RhnmKJhHNEeJ+/PX3zxx9/7Oz529s3fvhQlkxYC4NAApsEmMHMQGxE8h9g/kCUwlEwCkbBKBi5AABE5jSGyhAPewAAAABJRU5ErkJggg==","orcid":"","institution":"NIHR Imperial Biomedical Research Centre","correspondingAuthor":true,"prefix":"","firstName":"Ekin","middleName":"","lastName":"Yagis","suffix":""},{"id":607987570,"identity":"a6efb807-ed3b-4e47-94dc-3fca93ab88aa","order_by":4,"name":"Zhuoyu Li","email":"","orcid":"","institution":"NIHR Imperial Biomedical Research Centre","correspondingAuthor":false,"prefix":"","firstName":"Zhuoyu","middleName":"","lastName":"Li","suffix":""},{"id":607987575,"identity":"5696e15c-6ee2-471a-814a-5a963dcb743b","order_by":5,"name":"Maria Tipper","email":"","orcid":"","institution":"Imperial College Healthcare NHS Trust","correspondingAuthor":false,"prefix":"","firstName":"Maria","middleName":"","lastName":"Tipper","suffix":""},{"id":607987578,"identity":"97ae5e0f-dd4f-4674-a71d-5d8b284dcc28","order_by":6,"name":"Agnes Motsi","email":"","orcid":"","institution":"Imperial College Healthcare NHS Trust","correspondingAuthor":false,"prefix":"","firstName":"Agnes","middleName":"","lastName":"Motsi","suffix":""},{"id":607987580,"identity":"9e5a342f-f96e-4037-a98e-fef9ad9d6ab3","order_by":7,"name":"Sharon O’Malley","email":"","orcid":"","institution":"Imperial College Healthcare NHS Trust","correspondingAuthor":false,"prefix":"","firstName":"Sharon","middleName":"","lastName":"O’Malley","suffix":""},{"id":607987581,"identity":"f3bf80a1-3ce7-40be-b27e-0627122f5e25","order_by":8,"name":"Yusuf Abdullahi","email":"","orcid":"","institution":"NIHR Imperial Biomedical Research Centre","correspondingAuthor":false,"prefix":"","firstName":"Yusuf","middleName":"","lastName":"Abdullahi","suffix":""},{"id":607987582,"identity":"53f06900-0354-411f-b7d8-51c1ed2251fb","order_by":9,"name":"Ben Glampson","email":"","orcid":"","institution":"NIHR Imperial Biomedical Research Centre","correspondingAuthor":false,"prefix":"","firstName":"Ben","middleName":"","lastName":"Glampson","suffix":""},{"id":607987583,"identity":"02c2a6ea-ae30-45bb-a65f-14996cbc5efd","order_by":10,"name":"Colin Mitchell","email":"","orcid":"","institution":"Imperial College Healthcare NHS Trust","correspondingAuthor":false,"prefix":"","firstName":"Colin","middleName":"","lastName":"Mitchell","suffix":""},{"id":607987584,"identity":"81b03c80-afd1-451b-8b37-b1a69da67571","order_by":11,"name":"Erik K Mayer","email":"","orcid":"","institution":"Imperial College London","correspondingAuthor":false,"prefix":"","firstName":"Erik","middleName":"K","lastName":"Mayer","suffix":""}],"badges":[],"createdAt":"2026-01-15 16:53:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8612539/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8612539/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105033881,"identity":"fe3f064e-3abb-404f-9cb6-dc5db5530dfe","added_by":"auto","created_at":"2026-03-20 07:22:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":597640,"visible":true,"origin":"","legend":"","description":"","filename":"WSICFallsforsubmissionstoScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8612539/v1_covered_e369948d-3f01-47fa-825e-0dffe49035b9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Identifying High-Risk Patient Clusters for Falls Using Unsupervised Machine Learning on Linked Primary and Secondary Care Electronic Health Record Data","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Falls, Risk Factors, Population Health, Machine Learning, Electronic Health Records","lastPublishedDoi":"10.21203/rs.3.rs-8612539/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8612539/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFalls risk is multifactorial, involving a combination of clinical and sociodemographic factors. Although guidelines acknowledge this complexity, most research has focused on individual risk factors, leaving the combined impact of comorbidities relatively understudied. This population-wide study used electronic health records (EHR) linked across primary and secondary care to identify falls risk profiles in the North West London (NWL) population and to stratify patients by their likelihood of requiring falls-related hospital care using unsupervised clustering. We conducted cluster analysis on patients from NWL General Practice records using coded falls risk factors. Cluster membership was compared against the risk of falls-related hospital encounters. Among four identified clusters, two groups of older, multimorbid patients were 11 times more likely to have a fall-related hospital encounter (RR 11.45, 95% CI 10.14\u0026ndash;12.92 and RR 11.63, 95% CI 10.30\u0026ndash;13.13) and had significantly longer mean length of stay compared with younger, fitter patients. Between two younger clusters, patients with higher deprivation levels were 29% more likely to have a fall-related hospital encounter (RR 1.29, 95% CI 1.12\u0026ndash;1.49). These findings demonstrate that clustering routinely collected EHR data can identify population segments at highest risk of falls-related hospital use, supporting more targeted, multifactorial risk assessment and prevention strategies.\u003c/p\u003e","manuscriptTitle":"Identifying High-Risk Patient Clusters for Falls Using Unsupervised Machine Learning on Linked Primary and Secondary Care Electronic Health Record Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-18 08:49:50","doi":"10.21203/rs.3.rs-8612539/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-25T08:45:01+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-19T05:47:18+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-18T16:28:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-18T05:02:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"193805629528002143126220214242820472207","date":"2026-03-18T03:44:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"19581665526592865087260044748367309544","date":"2026-03-17T04:15:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"154228232755004910332906501062971334585","date":"2026-03-17T03:52:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"338417574708145305898859561305462557531","date":"2026-03-17T03:45:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"39870973843047088775048978448620221148","date":"2026-03-17T03:42:31+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-17T03:41:01+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-17T03:38:00+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-02-26T06:41:33+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-09T09:59:29+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-02-09T09:31:11+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"bf07f671-e2cc-48e3-940f-b59cf9d85a66","owner":[],"postedDate":"March 18th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":64693516,"name":"Health sciences/Diseases"},{"id":64693517,"name":"Health sciences/Health care"},{"id":64693519,"name":"Health sciences/Medical research"},{"id":64693521,"name":"Health sciences/Risk factors"}],"tags":[],"updatedAt":"2026-03-25T08:56:44+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-18 08:49:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8612539","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8612539","identity":"rs-8612539","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}