{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:27:08Z","timestamp":1777890428923,"version":"3.51.4"},"reference-count":19,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Global population aging is accelerating, and China faces a significant challenge with \u201caging before affluent.\u201d The disabled older adults population in China is projected to reach 58 million by 2050. Early identification of disability risk is essential for optimizing healthcare resource allocation and improving long-term care systems.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and validate machine learning models using comprehensive electronic medical record (EMR) data to predict four distinct levels of disability in older adults inpatients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Data from 523 patients (age \u2265 60) were retrospectively collected from two tertiary hospitals in Northeast China. Disability was categorized into four levels (A\u2013D) based on the Barthel Index (BI). Feature selection was performed using LASSO regression with 10-fold cross-validation. Six algorithms\u2014Logistic Regression (LOG), Random Forest (RF), Gradient Boosting Machine (GBM), XGBoost, AdaBoost, and Support Vector Machine (SVM)\u2014were evaluated. SHapley Additive exPlanations (SHAP) was employed to interpret model decisions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Seventeen critical predictors were identified, including age, appendicular skeletal muscle mass index (ASMI), phase angle, and various inflammatory markers. The LOG and XGBoost models demonstrated the best performance (AUC\u202f=\u202f0.83; Accuracy\u202f=\u202f0.91). Ten-fold cross-validation confirmed stable model. SHAP analysis indicated that neurological comorbidities, muscle mass indicators, and nutritional-inflammatory status were the primary drivers of disability risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>EMR-based machine learning models, particularly XGBoost, provide a robust and interpretable tool for early disability risk stratification, supporting clinical decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1823727","type":"journal-article","created":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:37:29Z","timestamp":1777613849000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessment of disability in the older adults using electronic health record\u2013based data: a machine learning approach"],"prefix":"10.3389","volume":"14","author":[{"given":"Guangpeng","family":"Chen","sequence":"first","affiliation":[{"name":"School of Public Health, Fudan University","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunyu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, Faculty of Medicine, Dalian University of Technology","place":["Dalian, China"]},{"name":"Department of International Medical, The Second Affiliated Hospital of Dalian Medical University","place":["Dalian, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Public Health, Fudan University","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"ref1","volume-title":"World Population Prospects 2024: Summary of Results","year":"2024"},{"key":"ref2","volume-title":"World Report on Disability 2021","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.1056\/NEJM198905113201906","article-title":"Activities of daily living and mortality among elderly persons in the community","volume":"322","author":"Guralnik","year":"1989","journal-title":"N Engl J Med"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e1855","DOI":"10.1016\/S2214-109X(21)00386-6","article-title":"Global, regional, and national burden of disability: estimates from the global burden of disease study 2019","volume":"9","year":"2021","journal-title":"Lancet Glob Health"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s42379-023-00138-z","article-title":"Negative population growth and population ageing in China","volume":"7","author":"Peng","year":"2023","journal-title":"China Popul Dev Stud"},{"key":"ref6","article-title":"The fifth sample survey on the living conditions of elderly people in urban and rural China: basic data bulletin","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1186\/s12877-022-03412-w","article-title":"Prevalence of self-care disability among older adults in China","volume":"22","author":"Guo","year":"2022","journal-title":"BMC Geriatr"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"S48","DOI":"10.15265\/IYS-2016-s006","article-title":"Electronic health records: then, now, and in the future","author":"Evans","year":"2016","journal-title":"Yearb Med Inform"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1628","DOI":"10.1056\/NEJMsa0900592","article-title":"Use of electronic health records in U.S. hospitals","volume":"360","author":"Jha","year":"2009","journal-title":"N Engl J Med"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1093\/eurpub\/ckv122","article-title":"The impact of electronic health records on healthcare quality: a systematic review and meta-analysis","volume":"26","author":"Campanella","year":"2016","journal-title":"Eur J Public Health"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"806","DOI":"10.1186\/s12877-024-05409-z","article-title":"Risk prediction models for disability in older adults: a systematic review and critical appraisal","volume":"24","author":"Zhou","year":"2024","journal-title":"BMC Geriatr"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1186\/s12877-021-02223-9","article-title":"A web-based dynamic nomogram for predicting instrumental activities of daily living disability in older adults: a nationally representative survey in China","volume":"21","author":"Zhang","year":"2021","journal-title":"BMC Geriatr"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1007\/s40520-022-02105-z","article-title":"Nomogram for predicting the 12-year risk of ADL disability among older adults","volume":"34","author":"Qi","year":"2022","journal-title":"Aging Clin Exp Res"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.1111\/jgs.18383","article-title":"Machine learning functional impairment classification with electronic health record data","volume":"71","author":"Pavon","year":"2023","journal-title":"J Am Geriatr Soc"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1922","DOI":"10.1111\/jgs.16057","article-title":"Machine learning-based prediction of functional disability progression in elderly patients with chronic diseases using electronic health records","volume":"67","author":"Lee","year":"2019","journal-title":"J Am Geriatr Soc"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1987","DOI":"10.1177\/08982643221118567","article-title":"Systematic comparison of traditional regression and machine learning models for functional status prediction in older adults using EHR data","volume":"34","author":"Smith","year":"2022","journal-title":"J Aging Health"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1097\/00000441-196501000-00009","article-title":"Functional evaluation: the Barthel index","volume":"14","author":"Mahoney","year":"1965","journal-title":"Md State Med J"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/j.archger.2008.07.009","article-title":"Validity and reliability of the Barthel index in geriatric inpatients","volume":"48","author":"Hirsch","year":"2009","journal-title":"Arch Gerontol Geriatr"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.ijnurstu.2018.07.008","article-title":"Applicability of the Barthel index for elderly patients with dementia in long-term care facilities","volume":"87","author":"Liu","year":"2018","journal-title":"Int J Nurs Stud"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1823727\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:37:30Z","timestamp":1777613850000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1823727\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,1]]},"references-count":19,"alternative-id":["10.3389\/fpubh.2026.1823727"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1823727","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,1]]},"article-number":"1823727"}}