{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T09:30:33Z","timestamp":1789723833926,"version":"4.0.1"},"reference-count":47,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Aging"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Falls are one of the leading causes of injury or death among older adults. Falls occurring in individuals during hospitalization, as an adverse event, are a key concern for health care institutions. Identifying older adults at high risk of falls in clinical settings enables early interventions, thereby reducing the incidence of falls.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to develop and validate machine learning models to predict the risk of falls among hospitalized older adults.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This study retrospectively analyzed data from a tertiary general hospital in China, including 342 older adults who experienced falls and 684 randomly matched nonfallers, between January 2018 and December 2024, encompassing demographic information, comorbidities, laboratory parameters, and medication use, among other variables. The dataset was randomly split into training and testing sets in a 7:3 ratio. Predictors were selected from the training set using stepwise regression, least absolute shrinkage and selection operator, and random forest-recursive feature elimination. Seven machine learning algorithms were employed to develop predictive models in the training set, and their performance was compared in the testing set. The optimal model was interpreted using Shapley Additive Explanations (SHAP).<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The gradient boosting machine model demonstrated the best predictive performance (C-index 0.744, 95% CI 0.688\u20100.799). The 8 most important variables associated with fall risk were dizziness, epilepsy, fall history within the past 3 months, use of walking assistance, emergency admission, Morse Fall Scale scores, modified Barthel Index scores, and the number of indwelling catheters. The model was interpreted using SHAP to enhance the clinical utility of the predictive model.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The gradient boosting machine model was identified as the optimal predictive model. The SHAP method enhanced its integration into clinical workflows.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/80602","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T12:05:09Z","timestamp":1765886709000},"page":"e80602-e80602","source":"Crossref","is-referenced-by-count":5,"title":["Development and Validation of Machine Learning Models for Predicting Falls Among Hospitalized Older Adults: Retrospective Cross-Sectional Study"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4295-5396","authenticated-orcid":false,"given":"Xiyao","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7020-6022","authenticated-orcid":false,"given":"Juan","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1537-1873","authenticated-orcid":false,"given":"Dan","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1789-5763","authenticated-orcid":false,"given":"Manzhen","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6659-3549","authenticated-orcid":false,"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5409-2481","authenticated-orcid":false,"given":"Xiaoming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4037-115X","authenticated-orcid":false,"given":"Yanhua","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8064-7715","authenticated-orcid":false,"given":"Zonggui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7161-8342","authenticated-orcid":false,"given":"Xiujing","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8363-3224","authenticated-orcid":false,"given":"Zengzeng","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3828-916X","authenticated-orcid":false,"given":"Shuiyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5307-5166","authenticated-orcid":false,"given":"Yuxin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8062-7369","authenticated-orcid":false,"given":"Juan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1248-2076","authenticated-orcid":false,"given":"Xiaolin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7192-9389","authenticated-orcid":false,"given":"Junjin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5024-7253","authenticated-orcid":false,"given":"Nan","family":"Mo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,1,5]]},"reference":[{"key":"R1","unstructured":"Falls. World Health Organization. 2021. URL: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/falls [Accessed 20-12-2025]"},{"issue":"16","key":"R2","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1001\/jama.2024.1416","article-title":"Risk assessment and prevention of falls in older community-dwelling adults: a review","volume":"331","author":"Col\u00f3n-Emeric","journal-title":"JAMA"},{"issue":"1","key":"R3","doi-asserted-by":"publisher","DOI":"10.1186\/s13018-022-03222-1","article-title":"Global prevalence of falls in the older adults: a comprehensive systematic review and meta-analysis","volume":"17","author":"Salari","journal-title":"J Orthop Surg Res"},{"issue":"4","key":"R4","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1016\/j.amepre.2023.04.006","article-title":"Interpretable machine learning for fall prediction among older adults in China","volume":"65","author":"Chen","journal-title":"Am J Prev Med"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-023-04138-z","article-title":"Medications influencing the risk of fall-related injuries in older adults: case-control and case-crossover design studies","volume":"23","author":"Jung","journal-title":"BMC Geriatr"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","DOI":"10.1001\/jamahealthforum.2022.5125","article-title":"Cost of inpatient falls and cost-benefit analysis of implementation of an evidence-based fall prevention program","volume":"4","author":"Dykes","journal-title":"JAMA Health Forum"},{"issue":"5","key":"R7","doi-asserted-by":"publisher","DOI":"10.1093\/ageing\/afac077","article-title":"Interventions to reduce falls in hospitals: a systematic review and meta-analysis","volume":"51","author":"Morris","journal-title":"Age Ageing"},{"issue":"8","key":"R8","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1136\/bmjqs-2024-017993","article-title":"Under-reporting of falls in hospitals: a multisite study in South Korea","volume":"34","author":"Cho","journal-title":"BMJ Qual Saf"},{"issue":"27","key":"R9","doi-asserted-by":"publisher","first-page":"875","DOI":"10.15585\/mmwr.mm6927a5","article-title":"Trends in nonfatal falls and fall-related injuries among adults aged \u226565 years - United States, 2012-2018","volume":"69","author":"Moreland","journal-title":"MMWR Morb Mortal Wkly Rep"},{"issue":"4","key":"R10","doi-asserted-by":"publisher","first-page":"345","DOI":"10.15441\/ceem.22.354","article-title":"Development and validation of interpretable machine learning models for inpatient fall events and electronic medical record integration","volume":"9","author":"Shim","journal-title":"Clin Exp Emerg Med"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2020.104272","article-title":"Identification of important factors in an inpatient fall risk prediction model to improve the quality of care using EHR and electronic administrative data: a machine-learning approach","volume":"143","author":"Lindberg","journal-title":"Int J Med Inform"},{"issue":"8","key":"R12","doi-asserted-by":"publisher","first-page":"e1152","DOI":"10.1097\/PTS.0000000000000462","article-title":"Validation of a falls risk screening tool derived from InterRAI acute care assessment","volume":"17","author":"Peel","journal-title":"J Patient Saf"},{"issue":"2","key":"R13","doi-asserted-by":"publisher","first-page":"216","DOI":"10.2340\/16501977-2290","article-title":"External validation of approaches to prediction of falls during hospital rehabilitation stays and development of a new simpler tool","volume":"50","author":"Vratsistas-Curto","journal-title":"J Rehabil Med"},{"issue":"7","key":"R14","doi-asserted-by":"publisher","DOI":"10.2196\/37913","article-title":"Impact of a clinical text-based fall prediction model on preventing extended hospital stays for elderly inpatients: model development and performance evaluation","volume":"10","author":"Kawazoe","journal-title":"JMIR Med Inform"},{"issue":"7","key":"R15","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1016\/j.jamda.2023.03.006","article-title":"Development and internal validation of a prediction model for falls using electronic health records in a hospital setting","volume":"24","author":"Dormosh","journal-title":"J Am Med Dir Assoc"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.937216","article-title":"A model for predicting fall risks of hospitalized elderly in Taiwan-a machine learning approach based on both electronic health records and comprehensive geriatric assessment","volume":"9","author":"Chu","journal-title":"Front Med (Lausanne)"},{"issue":"17-18","key":"R17","doi-asserted-by":"publisher","first-page":"6474","DOI":"10.1111\/jocn.16680","article-title":"Development and evaluation of a simple predictive model for falls in acute care setting","volume":"32","author":"Satoh","journal-title":"J Clin Nurs"},{"issue":"4","key":"R18","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1038\/nmeth.4642","article-title":"Statistics versus machine learning","volume":"15","author":"Bzdok","journal-title":"Nat Methods"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.2196\/54934","article-title":"The applications of artificial intelligence for assessing fall risk: systematic review","volume":"26","author":"Gonz\u00e1lez-Castro","journal-title":"J Med Internet Res"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.2196\/54872","article-title":"Development and validation of an explainable machine learning model for predicting myocardial injury after noncardiac surgery in two centers in China: retrospective study","volume":"7","author":"Liu","journal-title":"JMIR Aging"},{"issue":"7","key":"R21","doi-asserted-by":"publisher","first-page":"3599","DOI":"10.1109\/JBHI.2023.3267039","article-title":"Ambient monitoring of gait and machine learning models for dynamic and short-term falls risk assessment in people with dementia","volume":"27","author":"Adeli","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","DOI":"10.1002\/jcsm.13713","article-title":"Predicting in-hospital fall risk using machine learning with real-time location system and electronic medical records","volume":"16","author":"Kim","journal-title":"J Cachexia Sarcopenia Muscle"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1425713","article-title":"Fall risk prediction using temporal gait features and machine learning approaches","volume":"7","author":"Lim","journal-title":"Front Artif Intell"},{"key":"R24","unstructured":"Rothman KJ Greenland S Lash TL . Modern Epidemiology. 3rd ed. Wolters Kluwer Health\/Lippincott Williams & Wilkins; 2008. URL: https:\/\/books.google.com\/books\/about\/Modern_Epidemiology.html?id=Z3vjT9ALxHUC [Accessed 20-12-2025] ISBN: 9780781755641"},{"issue":"9","key":"R25","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1093\/oxfordjournals.aje.a116396","article-title":"Selection of controls in case-control studies. I. Principles","volume":"135","author":"Wacholder","journal-title":"Am J Epidemiol"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","article-title":"MissForest--non-parametric missing value imputation for mixed-type data","volume":"28","author":"Stekhoven","journal-title":"Bioinformatics"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-025-06289-6","article-title":"Prediction of postpartum depression in women: development and validation of multiple machine learning models","volume":"23","author":"Qi","journal-title":"J Transl Med"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2024.09.059","article-title":"Machine learning algorithms to predict mild cognitive impairment in older adults in China: a cross-sectional study","volume":"368","author":"Song","journal-title":"J Affect Disord"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1186\/s13007-022-00871-5","article-title":"Predictive modeling of Persian walnut (Juglans regia L.) in vitro proliferation media using machine learning approaches: a comparative study of ANN, KNN and GEP models","volume":"18","author":"Sadat-Hosseini","journal-title":"Plant Methods"},{"issue":"11","key":"R30","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1016\/j.soard.2023.05.025","article-title":"Predicting readmission after bariatric surgery using machine learning","volume":"19","author":"Butler","journal-title":"Surg Obes Relat Dis"},{"issue":"1","key":"R31","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","article-title":"Assessing the performance of prediction models: a framework for traditional and novel measures","volume":"21","author":"Steyerberg","journal-title":"Epidemiology"},{"issue":"1","key":"R32","doi-asserted-by":"publisher","DOI":"10.1186\/s12933-024-02439-0","article-title":"Construction of machine learning diagnostic models for cardiovascular pan-disease based on blood routine and biochemical detection data","volume":"23","author":"Wang","journal-title":"Cardiovasc Diabetol"},{"key":"R33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejim.2022.05.004","article-title":"Low serum albumin: a neglected predictor in patients with cardiovascular disease","volume":"102","author":"Manolis","journal-title":"Eur J Intern Med"},{"issue":"1","key":"R34","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/0277-9536(89)90309-2","article-title":"A prospective study to identify the fall-prone patient","volume":"28","author":"Morse","journal-title":"Soc Sci Med"},{"issue":"8","key":"R35","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1016\/0895-4356(89)90065-6","article-title":"Improving the sensitivity of the Barthel Index for stroke rehabilitation","volume":"42","author":"Shah","journal-title":"J Clin Epidemiol"},{"issue":"8","key":"R36","doi-asserted-by":"publisher","DOI":"10.3390\/nu15081991","article-title":"Nutritional status and its detection in patients with inflammatory bowel diseases","volume":"15","author":"Jab\u0142o\u0144ska","journal-title":"Nutrients"},{"issue":"7","key":"R37","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1111\/j.1365-2702.2005.01121.x","article-title":"Pain: a review of three commonly used pain rating scales","volume":"14","author":"Williamson","journal-title":"J Clin Nurs"},{"issue":"1","key":"R38","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-025-21284-8","article-title":"Constructing a fall risk prediction model for hospitalized patients using machine learning","volume":"25","author":"Kang","journal-title":"BMC Public Health"},{"key":"R39","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108561","article-title":"Machine learning-based predictive models for perioperative major adverse cardiovascular events in patients with stable coronary artery disease undergoing noncardiac surgery","volume":"260","author":"Shen","journal-title":"Comput Methods Programs Biomed"},{"key":"R40","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2024.1369200","article-title":"Falls in hospitalized older adults and the use of fall risk-increasing drugs and anticholinergic medications in Colombia: a case\u2012control study","volume":"15","author":"Machado-Duque","journal-title":"Front Pharmacol"},{"issue":"1","key":"R41","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-025-05814-y","article-title":"A fall risk prediction model based on the CHARLS database for older individuals in China","volume":"25","author":"Liang","journal-title":"BMC Geriatr"},{"issue":"1","key":"R42","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-025-05688-0","article-title":"Risk prediction models for falls in hospitalized older patients: a systematic review and meta-analysis","volume":"25","author":"Mao","journal-title":"BMC Geriatr"},{"key":"R43","doi-asserted-by":"publisher","DOI":"10.2196\/46791","article-title":"A machine learning-based Preclinical Osteoporosis Screening Tool (POST): model development and validation study","volume":"6","author":"Yang","journal-title":"JMIR Aging"},{"issue":"10","key":"R44","doi-asserted-by":"publisher","DOI":"10.1093\/ageing\/afaf285","article-title":"A novel electronic-health-record based, machine-learning model to predict 1-year risk of fall hospitalisation in older adults: a Hong Kong territory-wide cohort and modelling study","volume":"54","author":"Yang","journal-title":"Age Ageing"},{"issue":"1","key":"R45","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-022-02879-x","article-title":"Association between daily activities and fall in older adults: an analysis of longitudinal ageing study in India (2017-18)","volume":"22","author":"Nagarkar","journal-title":"BMC Geriatr"},{"key":"R46","doi-asserted-by":"publisher","DOI":"10.1016\/j.maturitas.2020.10.021","article-title":"Risk factors for recurrent falls in older adults: a systematic review with meta-analysis","volume":"144","author":"Jehu","journal-title":"Maturitas"},{"issue":"6","key":"R47","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.1249\/MSS.0000000000001942","article-title":"Physical activity, injurious falls, and physical function in aging: an umbrella review","volume":"51","author":"Dipietro","journal-title":"Med Sci Sports Exerc"}],"container-title":["JMIR Aging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aging.jmir.org\/2026\/1\/e80602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T19:41:45Z","timestamp":1786650105000},"score":1,"resource":{"primary":{"URL":"https:\/\/aging.jmir.org\/2026\/1\/e80602"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,5]]},"references-count":47,"URL":"https:\/\/doi.org\/10.2196\/80602","relation":{},"ISSN":["2561-7605"],"issn-type":[{"value":"2561-7605","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,5]]},"article-number":"v9i16e80602"}}