{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T05:03:58Z","timestamp":1789707838781,"version":"4.0.1"},"reference-count":50,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018684","name":"National Health Commission of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018684","id-type":"DOI","asserted-by":"publisher"}]}],"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 aging has made disability among older adults a major public health challenge. Existing prediction models often lack external validation and actionable risk stratification. This study aims to develop and externally validate an explainable, three-tier machine learning framework for disability risk prediction and stratification among older adults.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      The training set and internal validation set were derived from the longitudinal development cohort of the China Health and Retirement Longitudinal Study (CHARLS,\n                      <jats:italic>n<\/jats:italic>\n                      = 3,599). An independent cross-sectional survey (\n                      <jats:italic>n<\/jats:italic>\n                      = 2,066) was used for external validation of the model. Individuals 65 years of age and older were included. Disability was defined by basic activities of daily living (BADL). After feature selection, five candidate machine learning techniques were evaluated to identify the optimal model. The SHapley Additive exPlanations (SHAP) was used to interpret the optimal model. Ultimately, a three-tier risk stratification method was developed and verified using Decision Curve Analysis (DCA) and the Cochran-Armitage trend test.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      LASSO regression identified seven critical predictors. The Extreme Gradient Boosting (XGBoost) achieved the optimal balance, achieving the optimal balance of predictive performance in the internal testing set (AUC = 0.737) and external validation cohort (AUC = 0.782). SHAP analysis revealed age, age-adjusted Charlson Comorbidity Index (ACCI), and lower limb mobility as the paramount global predictors. The established risk stratification thresholds (33.17 and 65.23%) successfully categorized older adults into three levels. This three-tier system exhibited a significant gradient increase in actual disability incidence within the external set (\n                      <jats:italic>P<\/jats:italic>\n                      <jats:sub>trend<\/jats:sub>\n                      &amp;lt; 0.001) and a broad positive net clinical benefit in DCA.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The XGBoost model showed satisfactory and consistent performance in external validation. SHAP provided clinically meaningful insights, emphasizing age, lower-limb mobility, psychological status, and comorbidity burden. The validated three-tier system bridges the translational gap between complex predicted probabilities and practical clinical decisions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1904998","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T04:36:10Z","timestamp":1789706170000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and external validation of a machine learning model for three-tier disability risk stratification in older adults"],"prefix":"10.3389","volume":"14","author":[{"given":"Yitong","family":"Mao","sequence":"first","affiliation":[{"name":"Nursing Department, The Second Affiliated Hospital of Zhejiang University School of Medicine (SAHZU), Hangzhou","place":["Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiting","family":"Guo","sequence":"additional","affiliation":[{"name":"Nursing Department, The Second Affiliated Hospital of Zhejiang University School of Medicine (SAHZU), Hangzhou","place":["Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Wang","sequence":"additional","affiliation":[{"name":"Nursing Department, The Second Affiliated Hospital of Zhejiang University School of Medicine (SAHZU), Hangzhou","place":["Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Yang","sequence":"additional","affiliation":[{"name":"Nursing Department, The Second Affiliated Hospital of Zhejiang University School of Medicine (SAHZU), Hangzhou","place":["Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Chen","sequence":"additional","affiliation":[{"name":"Nursing Department, The Second Affiliated Hospital of Zhejiang University School of Medicine (SAHZU), Hangzhou","place":["Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Lu","sequence":"additional","affiliation":[{"name":"Nursing Department, The Second Affiliated Hospital of Zhejiang University School of Medicine (SAHZU), Hangzhou","place":["Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nursing Department, The Second Affiliated Hospital of Zhejiang University School of Medicine (SAHZU), Hangzhou","place":["Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingfen","family":"Jin","sequence":"additional","affiliation":[{"name":"Nursing Department, The Second Affiliated Hospital of Zhejiang University School of Medicine (SAHZU), Hangzhou","place":["Zhejiang, China"]},{"name":"Key Laboratory of the Diagnosis and Treatment of Severe Trauma and Burn of Zhejiang Province","place":["Hangzhou, Zhejiang, China"]},{"name":"Zhejiang Provincial Clinical Research Center for Emergency and Critical Disease","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1146\/annurev.pu.17.050196.000325","article-title":"Disability as a public health outcome in the aging population","volume":"17","author":"Guralnik","year":"1996","journal-title":"Annu Rev Public Health."},{"key":"B2","doi-asserted-by":"publisher","first-page":"S308","DOI":"10.1111\/j.1532-5415.2010.02914.x","article-title":"Assessment of function and disability in longitudinal studies","volume":"58","author":"Gill","year":"2010","journal-title":"J Am Geriatr Soc."},{"key":"B3","doi-asserted-by":"publisher","first-page":"S163","DOI":"10.1093\/geront\/gnw037","article-title":"The world report on ageing and health","volume":"56","author":"Beard","year":"2016","journal-title":"Gerontologist"},{"key":"B4","doi-asserted-by":"publisher","first-page":"100424","DOI":"10.1016\/j.ssmph.2019.100424","article-title":"Social participation patterns and their associations with health and well-being for older adults","volume":"8","author":"Dawson-Townsend","year":"2019","journal-title":"SSM Popul Health."},{"key":"B5","doi-asserted-by":"publisher","first-page":"593","DOI":"10.46234\/ccdcw2021.158","article-title":"Trends and challenges for population and health during population aging - China, 2015-2050","volume":"3","author":"Luo","year":"2021","journal-title":"China CDC Wkly."},{"key":"B6","doi-asserted-by":"publisher","first-page":"e011164","DOI":"10.1136\/bmjopen-2016-011164","article-title":"All-cause mortality risk in elderly individuals with disabilities: a retrospective observational study","volume":"6","author":"Wu","year":"2016","journal-title":"BMJ Open."},{"key":"B7","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.arr.2012.10.001","article-title":"Prevention of onset and progression of basic ADL disability by physical activity in community dwelling older adults: a meta-analysis","volume":"12","author":"Tak","year":"2013","journal-title":"Ageing Res Rev."},{"key":"B8","first-page":"147","article-title":"Rethinking the theory of disability in Chinese older adults and the conception of its measurement model","volume":"5","author":"Wang","year":"2020","journal-title":"Soc Sci Ningxia."},{"key":"B9","doi-asserted-by":"publisher","first-page":"3073","DOI":"10.1007\/s40520-021-01827-w","article-title":"Metabolic syndrome predicts incident disability and functional decline among Chinese older adults: results from the China health and retirement longitudinal study","volume":"33","author":"Zhang","year":"2021","journal-title":"Aging Clin Exp Res."},{"key":"B10","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1186\/s12877-022-02905-y","article-title":"Novel physical performance-based models for activities of daily living disability prediction among Chinese older community population: a nationally representative survey in China","volume":"22","author":"Zhang","year":"2022","journal-title":"BMC Geriatr."},{"key":"B11","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":"B12","doi-asserted-by":"publisher","first-page":"1056","DOI":"10.1111\/jgs.14868","article-title":"Effect of chronic diseases and multimorbidity on survival and functioning in elderly adults","volume":"65","author":"Rizzuto","year":"2017","journal-title":"J Am Geriatr Soc."},{"key":"B13","doi-asserted-by":"publisher","first-page":"104835","DOI":"10.1016\/j.archger.2022.104835","article-title":"Machine learning-based prediction of disability risk in geriatric patients with hypertension for different time intervals","volume":"105","author":"Xiang","year":"2023","journal-title":"Arch Gerontol Geriatr."},{"key":"B14","doi-asserted-by":"publisher","first-page":"1271595","DOI":"10.3389\/fpubh.2023.1271595","article-title":"Disability risk prediction model based on machine learning among Chinese healthy older adults: results from the China health and retirement longitudinal study","volume":"11","author":"Han","year":"2023","journal-title":"Front Public Health."},{"key":"B15","doi-asserted-by":"publisher","first-page":"105552","DOI":"10.1016\/j.ijmedinf.2024.105552","article-title":"Examining individual and contextual predictors of disability in Chinese older adults: a machine learning approach","volume":"191","author":"Wu","year":"2024","journal-title":"Int J Med Inform."},{"key":"B16","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":"B17","doi-asserted-by":"publisher","first-page":"e66723","DOI":"10.2196\/66723","article-title":"Development of a longitudinal model for disability prediction in older adults in China: analysis of CHARLS data (2015-2020)","volume":"8","author":"Chu","year":"2025","journal-title":"JMIR Aging."},{"key":"B18","doi-asserted-by":"publisher","first-page":"g7594","DOI":"10.1136\/bmj.g7594","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"350","author":"Collins","year":"2015","journal-title":"BMJ."},{"key":"B19","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1093\/ije\/dys203","article-title":"Cohort profile: the China health and retirement longitudinal study (CHARLS)","volume":"43","author":"Zhao","year":"2014","journal-title":"Int J Epidemiol."},{"key":"B20","unstructured":"Analysis of the 7th Population Census of Zhejiang Province (Series VIII): Population Aging\n          \n          2022"},{"key":"B21","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1093\/geront\/9.3_Part_1.179","article-title":"Assessment of older people: self-maintaining and instrumental activities of daily living1","volume":"9","author":"Lawton","year":"1969","journal-title":"Gerontologist"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1188552","DOI":"10.3389\/fragi.2023.1188552","article-title":"Is the combination of depression symptoms and multimorbidity associated with the increase of the prevalence of functional disabilities in Brazilian older adults? A cross-sectional study","volume":"4","author":"Rosa PP de S","year":"2023","journal-title":"Front Aging"},{"key":"B23","doi-asserted-by":"publisher","first-page":"105124","DOI":"10.1016\/j.archger.2023.105124","article-title":"Predicting functional dependency using machine learning among a middle-aged and older Chinese population","volume":"115","author":"Yu","year":"2023","journal-title":"Arch Gerontol Geriatr."},{"key":"B24","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1016\/0021-9681(87)90171-8","article-title":"A new method of classifying prognostic comorbidity in longitudinal studies: development and validation","volume":"40","author":"Charlson","year":"1987","journal-title":"J Chronic Dis."},{"key":"B25","doi-asserted-by":"publisher","first-page":"2384","DOI":"10.1002\/cncr.23462","article-title":"Age-adjusted Charlson comorbidity score is associated with treatment decisions and clinical outcomes for patients undergoing radical cystectomy for bladder cancer","volume":"112","author":"Koppie","year":"2008","journal-title":"Cancer."},{"key":"B26","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/S0749-3797(18)30622-6","article-title":"Screening for depression in well older adults: evaluation of a short form of the CES-D","volume":"10","author":"Andresen","year":"1994","journal-title":"Am J Prev Med."},{"key":"B27","doi-asserted-by":"publisher","first-page":"M85","DOI":"10.1093\/geronj\/49.2.M85","article-title":"A short physical performance battery assessing lower extremity function: association with self-reported disability and prediction of mortality and nursing home admission","volume":"49","author":"Guralnik","year":"1994","journal-title":"J Gerontol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1186\/s12874-021-01234-9","article-title":"LASSO type penalized spline regression for binary data","volume":"21","author":"Mullah","year":"2021","journal-title":"BMC Med Res Methodol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"e70056","DOI":"10.1111\/cts.70056","article-title":"Practical guide to SHAP analysis: explaining supervised machine learning model predictions in drug development","volume":"17","author":"Ponce-Bobadilla","year":"2024","journal-title":"Clin Transl Sci."},{"key":"B30","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/S0167-9473(02)00225-6","article-title":"On the exact distribution of maximally selected rank statistics","volume":"43","author":"Hothorn","year":"2003","journal-title":"Comput Stat Data Anal."},{"key":"B31","doi-asserted-by":"publisher","first-page":"2946","DOI":"10.1002\/sim.4044","article-title":"Accuracy and cut-off point selection in three-class classification problems using a generalization of the Youden index","volume":"29","author":"Nakas","year":"2010","journal-title":"Stat Med."},{"key":"B32","doi-asserted-by":"publisher","first-page":"620467","DOI":"10.2147\/CIA.S620467","article-title":"Predictive risk models for frailty onset in older adults: a scoping review of methodological trends, model performance, and clinical translation gap","volume":"21","author":"Xiao","year":"2026","journal-title":"Clin Interv Aging."},{"key":"B33","doi-asserted-by":"publisher","first-page":"2486","DOI":"10.1007\/s11606-023-08215-2","article-title":"Machine learning\u2013based prediction of functional disability: a cohort study of Japanese older adults in 2013\u20132019","volume":"38","author":"Lu","year":"2023","journal-title":"J Gen Intern Med."},{"key":"B34","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1038\/s41576-022-00511-7","article-title":"Measuring biological age using omics data","volume":"23","author":"Rutledge","year":"2022","journal-title":"Nat Rev Genet."},{"key":"B35","doi-asserted-by":"publisher","first-page":"573","DOI":"10.18632\/aging.101414","article-title":"An epigenetic biomarker of aging for lifespan and healthspan","volume":"10","author":"Levine","year":"2018","journal-title":"Aging."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.2147\/CIA.S322696","article-title":"Malnutrition risk, physical function decline and disability in middle-aged and older adults followed up in the Singapore longitudinal ageing study","volume":"16","author":"Hai","year":"2021","journal-title":"Clin Interv Aging."},{"key":"B37","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1186\/s12877-024-05015-z","article-title":"Age-adjusted Charlson comorbidity index is associated with the risk of osteoporosis in older fall-prone men: a retrospective cohort study","volume":"24","author":"Pan","year":"2024","journal-title":"BMC Geriatr."},{"key":"B38","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.ijsu.2020.08.017","article-title":"Charlson comorbidity index predicts postoperative complications in surgically treated hip fracture patients in a tertiary care hospital: retrospective cohort of 1045 patients","volume":"82","author":"Hasan","year":"2020","journal-title":"Int J Surg."},{"key":"B39","doi-asserted-by":"publisher","first-page":"7173","DOI":"10.1245\/s10434-021-09779-1","article-title":"Influences of the Charlson comorbidity index and nutrition status on prognosis after esophageal cancer surgery","volume":"28","author":"Kubo","year":"2021","journal-title":"Ann Surg Oncol."},{"key":"B40","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1093\/gerona\/glv202","article-title":"Physical resilience in older adults: systematic review and development of an emerging construct","volume":"71","author":"Whitson","year":"2016","journal-title":"J Gerontol A Biol Sci Med Sci."},{"key":"B41","doi-asserted-by":"publisher","first-page":"101701","DOI":"10.1016\/j.arr.2022.101701","article-title":"Physical resilience in older adults: potential use in promoting healthy aging","volume":"81","author":"Li","year":"2022","journal-title":"Ageing Res Rev."},{"key":"B42","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1093\/gerona\/glab257","article-title":"Risk factors for nonresilient outcomes in older adults after total knee replacement","volume":"77","author":"Laskow","year":"2022","journal-title":"J Gerontol A Biol Sci Med Sci."},{"key":"B43","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1007\/s10067-018-4382-x","article-title":"Risk factors for progression and prognosis of rheumatoid arthritis-associated interstitial lung disease: single center study with a large sample of Chinese population","volume":"38","author":"Fu","year":"2019","journal-title":"Clin Rheumatol."},{"key":"B44","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.ijnss.2025.12.007","article-title":"Lagged effects of risk factors on the disability of older adults: a distributed lag non-linear model approach","volume":"13","author":"Mao","year":"2026","journal-title":"Int J Nurs Sci."},{"key":"B45","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1093\/geront\/gnu094","article-title":"Mobility disability in older adults: at the intersection of people and places","volume":"56","author":"Satariano","year":"2016","journal-title":"Gerontologist."},{"key":"B46","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1093\/ageing\/afy169","article-title":"Sarcopenia: revised European consensus on definition and diagnosis","volume":"48","author":"Cruz-Jentoft","year":"2019","journal-title":"Age Ageing."},{"key":"B47","doi-asserted-by":"publisher","first-page":"5787","DOI":"10.1007\/s00415-022-11268-8","article-title":"Sarcopenia and nervous system disorders","volume":"269","author":"Yang","year":"2022","journal-title":"J Neurol."},{"key":"B48","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1037\/0003-066X.46.4.368","article-title":"Cognitive therapy: a 30-year retrospective","volume":"46","author":"Beck","year":"1991","journal-title":"Am Psychol."},{"key":"B49","doi-asserted-by":"publisher","first-page":"105199","DOI":"10.1016\/j.archger.2023.105199","article-title":"Relating depression, anxiety, stress and loneliness to 5-year decline in physical function and frailty","volume":"115","author":"Pinton","year":"2023","journal-title":"Arch Gerontol Geriatr."},{"key":"B50","doi-asserted-by":"publisher","first-page":"968343","DOI":"10.3389\/fpsyg.2022.968343","article-title":"Cognitive reserve and mental health in cognitive frailty phenotypes: insights from a study with a Portuguese sample","volume":"13","author":"Gaspar","year":"2022","journal-title":"Front Psychol."}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1904998\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T04:36:14Z","timestamp":1789706174000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1904998\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":50,"alternative-id":["10.3389\/fpubh.2026.1904998"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1904998","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]},"article-number":"1904998"}}