Data-Driven Identification of High-Risk Patient Groups for Falls Using SHAP-Space Profiling

Data-Driven Identification of High-Risk Patient Groups for Falls Using SHAP-Space Profiling | 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 Data-Driven Identification of High-Risk Patient Groups for Falls Using SHAP-Space Profiling Matthias Schulte-Althoff, Peter Krappen, Felix Biessmann, Sebastian Jäger, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9074928/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 Hospital falls are common and costly, yet fall risk is heterogeneous, limiting one-size-fits-all prevention. We aimed to derive interpretable, deployable fall-risk profiles from electronic health records (EHRs) to support subgroup-specific interventions. In a retrospective observational study using EHR data from a large German university hospital (2016–2022; N = 932,102), we trained an ensemble model to predict inpatient falls and computed patient-level Shapley Additive Explanations (SHAP). We then clustered fall-risk-flagged patients in SHAP space to obtain clinically interpretable risk profiles, benchmarked this approach against alternative clustering strategies, and assessed threshold trade-offs for high-risk classification. The ensemble achieved excellent discrimination (AUROC 0.95) and strong performance for the rare outcome (AUPRC 0.36) on a held-out test set. The model outperforms a guideline-features-only baseline and is competitive with prior falls prediction models in the literature. SHAP-space clustering yielded nine distinct, interpretable risk groups with specific risk factors. This allows actionable mapping to guideline domains and enabling tailored interventions based on established risk profiles. Overall, we provide an approach of how explainable, outcome-guided clustering can translate EHR-based fall prediction into tailored interventions in inpatient care. inpatient falls risk prediction electronic health records explainable AI SHAP patient stratification Full Text Additional Declarations No competing interests reported. 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-9074928","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":606400487,"identity":"f8a348ef-51a0-40da-b400-a136c9db5131","order_by":0,"name":"Matthias Schulte-Althoff","email":"","orcid":"","institution":"Charité - University Medicine Berlin","correspondingAuthor":false,"prefix":"","firstName":"Matthias","middleName":"","lastName":"Schulte-Althoff","suffix":""},{"id":606400488,"identity":"04dfd4ef-dff8-49aa-8dc0-23748a3544d5","order_by":1,"name":"Peter Krappen","email":"","orcid":"","institution":"Freie Universität Berlin","correspondingAuthor":false,"prefix":"","firstName":"Peter","middleName":"","lastName":"Krappen","suffix":""},{"id":606400489,"identity":"3628fbc3-ab6e-460a-97d4-fe9124b51a63","order_by":2,"name":"Felix Biessmann","email":"","orcid":"","institution":"Berliner Hochschule für Technik","correspondingAuthor":false,"prefix":"","firstName":"Felix","middleName":"","lastName":"Biessmann","suffix":""},{"id":606400490,"identity":"887b5de6-35bf-4555-8f96-263714725e9c","order_by":3,"name":"Sebastian Jäger","email":"","orcid":"","institution":"Berliner Hochschule für Technik","correspondingAuthor":false,"prefix":"","firstName":"Sebastian","middleName":"","lastName":"Jäger","suffix":""},{"id":606400491,"identity":"d21ddf24-5a11-47a3-9294-98e1c2ba30fe","order_by":4,"name":"Rahel Gubser","email":"","orcid":"","institution":"Charité - University Medicine Berlin","correspondingAuthor":false,"prefix":"","firstName":"Rahel","middleName":"","lastName":"Gubser","suffix":""},{"id":606400492,"identity":"d565ccd5-694a-482f-bf65-034829eee3f2","order_by":5,"name":"Armin Hauß","email":"","orcid":"","institution":"Charité - University Medicine Berlin","correspondingAuthor":false,"prefix":"","firstName":"Armin","middleName":"","lastName":"Hauß","suffix":""},{"id":606400493,"identity":"bace7b8f-8bd0-4c1c-849b-18c5d02c13ae","order_by":6,"name":"Felix Balzer","email":"","orcid":"","institution":"Charité - University Medicine Berlin","correspondingAuthor":false,"prefix":"","firstName":"Felix","middleName":"","lastName":"Balzer","suffix":""},{"id":606400495,"identity":"e21164f3-e4a9-4750-b2d6-16202870926b","order_by":7,"name":"Tim Kilgus","email":"","orcid":"","institution":"Freie Universität Berlin","correspondingAuthor":false,"prefix":"","firstName":"Tim","middleName":"","lastName":"Kilgus","suffix":""},{"id":606400497,"identity":"1f2ce489-550c-4571-8411-263e55d9f9bd","order_by":8,"name":"Daniel Fürstenau","email":"data:image/png;base64,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","orcid":"","institution":"Freie Universität Berlin","correspondingAuthor":true,"prefix":"","firstName":"Daniel","middleName":"","lastName":"Fürstenau","suffix":""}],"badges":[],"createdAt":"2026-03-09 15:39:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9074928/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9074928/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105565114,"identity":"af703a5a-060b-447f-b756-4fb55726fd67","added_by":"auto","created_at":"2026-03-27 12:52:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1011647,"visible":true,"origin":"","legend":"","description":"","filename":"FallPredict032026final.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9074928/v1_covered_5bef98a3-4dcf-4715-baa9-ccfdb6acb91b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Data-Driven Identification of High-Risk Patient Groups for Falls Using SHAP-Space Profiling","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":"inpatient falls, risk prediction, electronic health records, explainable AI, SHAP, patient stratification","lastPublishedDoi":"10.21203/rs.3.rs-9074928/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9074928/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHospital falls are common and costly, yet fall risk is heterogeneous, limiting one-size-fits-all prevention. We aimed to derive interpretable, deployable fall-risk profiles from electronic health records (EHRs) to support subgroup-specific interventions. In a retrospective observational study using EHR data from a large German university hospital (2016\u0026ndash;2022; N\u0026thinsp;=\u0026thinsp;932,102), we trained an ensemble model to predict inpatient falls and computed patient-level Shapley Additive Explanations (SHAP). We then clustered fall-risk-flagged patients in SHAP space to obtain clinically interpretable risk profiles, benchmarked this approach against alternative clustering strategies, and assessed threshold trade-offs for high-risk classification. The ensemble achieved excellent discrimination (AUROC 0.95) and strong performance for the rare outcome (AUPRC 0.36) on a held-out test set. The model outperforms a guideline-features-only baseline and is competitive with prior falls prediction models in the literature. SHAP-space clustering yielded nine distinct, interpretable risk groups with specific risk factors. This allows actionable mapping to guideline domains and enabling tailored interventions based on established risk profiles. Overall, we provide an approach of how explainable, outcome-guided clustering can translate EHR-based fall prediction into tailored interventions in inpatient care.\u003c/p\u003e","manuscriptTitle":"Data-Driven Identification of High-Risk Patient Groups for Falls Using SHAP-Space Profiling","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-17 17:47:16","doi":"10.21203/rs.3.rs-9074928/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":"12d45582-8c40-47ed-aed7-7468cbac7692","owner":[],"postedDate":"March 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-24T20:54:29+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-17 17:47:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9074928","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9074928","identity":"rs-9074928","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}