{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T17:18:52Z","timestamp":1785345532575,"version":"3.55.0"},"reference-count":55,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T00:00:00Z","timestamp":1762387200000},"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>Frailty is a public health concern linked to falls, disability, and mortality. Early screening and tailored interventions can mitigate adverse outcomes, but community settings require tools that are accurate and explainable. Korea is entering a super-aged phase, yet few approaches have used nationally representative survey data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to identify key predictors of frailty risk using the K-FRAIL scale using explainable machine learning (ML), based on data from the 2023 National Survey of Older Koreans (NSOK). It also sought to develop and internally validate prediction models. To demonstrate the potential applicability of these models in community public health and clinical practice, a web-based application was implemented.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Data from 10,078 older adults were analyzed, with frailty defined by the K-FRAIL scale (robust\u202f=\u202f0, pre-frail\u202f=\u202f1\u20132, and frail\u202f=\u202f3\u20135). A total of 132 candidate variables were constructed through selection and derivation. Using CatBoost with out-of-fold (OOF) SHapley Additive exPlanations (SHAP, a game-theoretic approach to quantify feature contributions), 15 key predictors were identified and applied across 10 algorithms under nested cross-validation (CV). Model performance was evaluated using receiver operating characteristic\u2013area under the curve (ROC-AUC), precision\u2013recall area under the curve (PR-AUC), F1-score, balanced accuracy, and the Brier score. To assess feasibility, a single-page bilingual web application was developed, integrating the CatBoost inference pipeline for offline use.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>SHAP analysis identified depression score, age, instrumental activities of daily living (IADL) count, sleep quality, and cognition as the leading predictors, followed by smartphone use, number of medications, province, driving status, hospital use, physical activity, osteoporosis, eating alone, digital adaptation difficulty, and sex, yielding 15 key predictors across the mental, functional, lifestyle, social, and digital domains. Using these predictors, boosting models outperformed other algorithms, with CatBoost achieving the best performance (ROC-AUC\u202f=\u202f0.813\u202f\u00b1\u202f0.014; PR-AUC\u202f=\u202f0.748\u202f\u00b1\u202f0.019).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An explainable machine learning model with strong discrimination performance and adequate calibration was developed, accompanied by a lightweight web application for potential use in community and clinical settings. However, external validation, recalibration, and subgroup fairness assessments are needed to ensure generalizability and clinical adoption.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2025.1698062","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T12:00:47Z","timestamp":1762430447000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Development of machine learning models with explainable AI for frailty risk prediction and their web-based application in community public health"],"prefix":"10.3389","volume":"13","author":[{"given":"Seungmi","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byung Kwan","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeong Su","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Up","family":"Huh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Myung-Jun","family":"Shin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zoran","family":"Obradovic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel J.","family":"Rubin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae Il","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jong-Hwan","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,6]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1016\/S0140-6736(12)62167-9","article-title":"Frailty in elderly people","volume":"381","author":"Clegg","year":"2013","journal-title":"Lancet"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"M146","DOI":"10.1093\/gerona\/56.3.m146","article-title":"Frailty in older adults: evidence for a phenotype","volume":"56","author":"Fried","year":"2001","journal-title":"J Gerontol A Biol Sci Med Sci"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1093\/gerona\/62.7.722","article-title":"Frailty in relation to the accumulation of deficits","volume":"62","author":"Rockwood","year":"2007","journal-title":"J Gerontol A Biol Sci Med Sci"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1503\/cmaj.050051","article-title":"A global clinical measure of fitness and frailty in elderly people","volume":"173","author":"Rockwood","year":"2005","journal-title":"CMAJ"},{"key":"ref5","volume-title":"World population prospects 2024","year":"2024"},{"key":"ref6","volume-title":"World report on ageing and health","year":"2015"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1038\/s42256-019-0048-x","article-title":"Stop explaining black box machine learning models for high-stakes decisions","volume":"1","author":"Rudin","year":"2019","journal-title":"Nat Mach Intell"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1002\/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4","article-title":"Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors","volume":"15","author":"Harrell","year":"1996","journal-title":"Stat Med"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.07874","article-title":"A unified approach to interpreting model predictions","volume":"80","author":"Lundberg","year":"2017","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"ref11","first-page":"1135","article-title":"\u201cWhy should I trust you?\u201d explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e0118432","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot on imbalanced datasets","volume":"10","author":"Saito","year":"2015","journal-title":"PLoS One"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::aid-cncr2820030106>3.0.co;2-3","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1002\/bimj.200410135","article-title":"Estimation of the Youden index and its cut-point","volume":"6","author":"Fluss","year":"2005","journal-title":"Biostatistics"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1186\/s12916-019-1466-7","article-title":"Calibration: the Achilles heel of predictive analytics","volume":"17","author":"Van Calster","year":"2019","journal-title":"BMC Med"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1175\/1520-0493(1950)078<>2.0.CO;2","article-title":"Verification of forecasts expressed in terms of probability","volume":"78","author":"Brier","year":"1950","journal-title":"Mon Weather Rev"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"91","DOI":"10.48550\/jmlr.v11.cawley10a","article-title":"Bias in error estimation when using cross-validation for model selection","volume":"7","author":"Varma","year":"2006","journal-title":"BMC Bioinformatics"},{"key":"ref18","first-page":"2079","article-title":"On over-fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","author":"Cawley","year":"2010","journal-title":"JMLR"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"JAIR"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1613\/jair.1.11192","article-title":"SMOTE for learning from imbalanced data: 15-year review","volume":"61","author":"Fern\u00e1ndez","year":"2018","journal-title":"JAIR"},{"key":"ref21","first-page":"785","volume-title":"XGBoost: A scalable tree boosting system","author":"Chen","year":"2016"},{"key":"ref22","first-page":"3146","article-title":"LightGBM: A highly efficient gradient boosting decision tree","author":"Ke","year":"2017"},{"key":"ref23","article-title":"Catboost: unbiased boosting with categorical features","volume-title":"Arxiv","author":"Dorogush","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann Stat"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans Inf Theory"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref29","volume-title":"National Survey of older Koreans 2023: Final report","year":"2024"},{"key":"ref30","volume-title":"Sample design report for the 2023 National Survey of older Koreans","year":"2023"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1002\/9780470374597","volume-title":"Sampling of populations: methods and applications","author":"Levy","year":"2008"},{"key":"ref32","volume-title":"Survey methodology","author":"Groves","year":"2009"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"e0280387","DOI":"10.1371\/journal.pone.0280387","article-title":"Implementing machine learning methods with complex survey data: impacts of accounting for sampling weights","volume":"18","author":"MacNell","year":"2023","journal-title":"PLoS One"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1097\/EDE.0000000000001776","article-title":"Evaluating binary outcome classifiers estimated from survey data","volume":"35","author":"Wadekar","year":"2024","journal-title":"Epidemiology"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1186\/s12877-019-1407-5","article-title":"Associations of sleep quality and sleep duration with frailty and pre-frailty in an elderly population","volume":"20","author":"Sun","year":"2020","journal-title":"BMC Geriatr"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1590\/1980-57642018dn13-020011","article-title":"Limited formal education is strongly associated with lower cognitive status, functional disability and frailty status in older adults","volume":"13","author":"Brigola","year":"2019","journal-title":"Dement Neuropsychol"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.3389\/fpsyg.2017.01687","article-title":"Older adults\u2019 perceptions of technology and barriers to interacting with tablet computers: a focus group study","volume":"8","author":"Vaportzis","year":"2017","journal-title":"Front Psychol"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1001\/jama.1963.03060120024016","article-title":"Studies of illness in the aged. The index of ADL","volume":"185","author":"Katz","year":"1963","journal-title":"JAMA"},{"key":"ref39","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 living","volume":"9","author":"Lawton","year":"1969","journal-title":"Gerontologist"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1145\/2382577.2382579","article-title":"Leakage in data mining: formulation, detection, and avoidance","volume":"6","author":"Kaufman","year":"2012","journal-title":"ACM Trans Knowl Discov Data"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"594","DOI":"10.3904\/kjim.2014.331","article-title":"The Korean version of the FRAIL scale: clinical feasibility and validity","volume":"31","author":"Jung","year":"2016","journal-title":"Korean J Intern Med"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/s12603-012-0084-2","article-title":"A simple frailty questionnaire (FRAIL) predicts outcomes in middle-aged African Americans","volume":"16","author":"Morley","year":"2012","journal-title":"J Nutr Health Aging"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1201\/9780429246593","volume-title":"An introduction to the bootstrap","author":"Efron","year":"1994"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.arr.2017.03.005","article-title":"Relationship between depression and frailty in older adults: a systematic review and meta-analysis","volume":"36","author":"Soysal","year":"2017","journal-title":"Ageing Res Rev"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1016\/j.jamda.2017.02.009","article-title":"Polypharmacy is associated with higher frailty risk in older people: an 8-year longitudinal cohort study","volume":"18","author":"Veronese","year":"2017","journal-title":"J Am Med Dir Assoc"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"1776","DOI":"10.1111\/j.1532-5415.2009.02480.x","article-title":"Neighborhood deprivation, SES, and frailty","volume":"57","author":"Lang","year":"2009","journal-title":"J Am Geriatr Soc"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1016\/j.jamda.2013.03.022","article-title":"Frailty consensus: a call to action","volume":"14","author":"Morley","year":"2013","journal-title":"J Am Med Dir Assoc"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"153","DOI":"10.14283\/jfa.2019.15","article-title":"Living with family yet eating alone is associated with frailty in community-dwelling older adults","volume":"8","author":"Suthutvoravut","year":"2019","journal-title":"J Frailty Aging"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"105004","DOI":"10.1016\/j.archger.2022.105004","article-title":"Longitudinal association between eating alone and frailty among community-dwelling older adults","volume":"109","author":"Park","year":"2023","journal-title":"Arch Gerontol Geriatr"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1186\/s12877-023-04077-9","article-title":"The association between osteoporosis and frailty: a cross-sectional study among community-dwelling older adults in Thailand","volume":"23","author":"Pothisiri","year":"2023","journal-title":"BMC Geriatr"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","article-title":"Dissecting racial bias in an algorithm used to manage the health of populations","volume":"366","author":"Obermeyer","year":"2019","journal-title":"Science"},{"key":"ref52","volume-title":"Decade of healthy ageing: baseline report","year":"2020"},{"key":"ref53","volume-title":"United Nations decade of healthy ageing (2021\u20132030). Resolution a\/RES\/75\/131","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.48550\/jmlr.v12.pedregosa11a","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"JMLR"},{"key":"ref55","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1093\/ageing\/afw039","article-title":"Development and validation of an electronic frailty index using routine primary care electronic health record data","volume":"45","author":"Clegg","year":"2016","journal-title":"Age Ageing"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1698062\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T12:00:50Z","timestamp":1762430450000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1698062\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,6]]},"references-count":55,"alternative-id":["10.3389\/fpubh.2025.1698062"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2025.1698062","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,6]]},"article-number":"1698062"}}