{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T18:00:28Z","timestamp":1790359228117,"version":"4.1.0"},"reference-count":23,"publisher":"Human Kinetics","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,1]]},"abstract":"<jats:p>\n                    <jats:italic>\n                      <jats:bold>Background<\/jats:bold>\n                      :\n                    <\/jats:italic>\n                    Physical activity among adults with disabilities is influenced by functional limitations, health status, and socioeconomic conditions; yet, the relative predictive importance of these factors remains insufficiently understood. This study compared multiple machine learning approaches for predicting exercise participation and used explainable artificial intelligence to identify the most influential predictors.\n                    <jats:italic>\n                      <jats:bold>Methods<\/jats:bold>\n                      :\n                    <\/jats:italic>\n                    Using the Centers for Disease Control and Prevention Behavioral Risk Factor Surveillance System data, we modeled self-reported exercise participation from 5 disability indicators\u2014blindness, deafness, cognitive disability, self-care disability, and mobility disability, along with demographic, socioeconomic, behavioral, psychosocial, and self-rated health factors. Five machine learning models were compared: logistic regression, LASSO, support vector machine, random forest, and XGBoost. Performance was evaluated with AUC, accuracy, F1 score, sensitivity, specificity, and Cohen kappa. Exercise participation was also summarized across disability types by income and education. Model explainability for the best performing model was assessed using SHAP plots.\n                    <jats:italic>\n                      <jats:bold>Results<\/jats:bold>\n                      :\n                    <\/jats:italic>\n                    XGBoost demonstrated the strongest overall performance (AUC\u2009=\u20090.83, accuracy\u2009=\u20090.79, F1\u2009=\u20090.78, sensitivity\u2009=\u20090.77, specificity\u2009=\u20090.80, \u03ba\u2009=\u2009.54), followed by random forest (AUC\u2009=\u20090.80). Exercise participation showed a pronounced socioeconomic gradient within disability groups. Among respondents with cognitive disability, exercise participation declined from 75.2% in the high-income group to 40.7% in the low-income group, while among those with mobility disability, it declined from 51.7% to 29.9%. SHAP analyses identified mobility status, education attainment, income, physical health, and age as the top 5 contributors to exercise participation.\n                    <jats:italic>\n                      <jats:bold>Conclusions<\/jats:bold>\n                      :\n                    <\/jats:italic>\n                    Explainable machine learning may improve identification of individuals at elevated risk of inactivity and highlights the combined importance of disability type and socioeconomic context in shaping exercise participation.\n                  <\/jats:p>","DOI":"10.1123\/jpah.2026-0347","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T13:59:10Z","timestamp":1783432750000},"page":"1485-1488","source":"Crossref","is-referenced-by-count":1,"title":["Understanding Drivers of Physical Activity Through Explainable Machine Learning: The Role of Disability and Social Determinants"],"prefix":"10.1123","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1476-113X","authenticated-orcid":true,"given":"Aditya","family":"Chakraborty","sequence":"first","affiliation":[{"name":"Department of Epidemiology, Biostatistics, and Environmental Health, Joint School of Public Health, Old Dominion University, Norfolk, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8515-8709","authenticated-orcid":true,"given":"Emily J","family":"Nicklett","sequence":"additional","affiliation":[{"name":"College for Health, Community and Policy, University of Texas, San Antonio, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"100","reference":[{"issue":"4","key":"r1","series-title":"Health Psychol Rev","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1080\/17437199.2016.1198240","article-title":"A systematic review of review articles addressing factors related to physical activity participation among children and adults with physical disabilities","volume":"10","author":"Martin Ginis KA","year":"2016","unstructured":"Martin Ginis KA, Ma JK, Latimer-Cheung AE, Rimmer JH. A systematic review of review articles addressing factors related to physical activity participation among children and adults with physical disabilities. Health Psychol Rev. 2016;10(4):478\u2013494. doi:10.1080\/17437199.2016.1198240"},{"issue":"5","key":"r2","series-title":"Am J Prev Med","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.amepre.2004.02.002","article-title":"Physical activity participation among persons with disabilities: barriers and facilitators","volume":"26","author":"Rimmer JH","year":"2004","unstructured":"Rimmer JH, Riley B, Wang E, Rauworth A, Jurkowski J. Physical activity participation among persons with disabilities: barriers and facilitators. Am J Prev Med. 2004;26(5):419\u2013425. doi:10.1016\/j.amepre.2004.02.002"},{"issue":"10298","key":"r3","series-title":"Lancet","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1016\/S0140-6736(21)01164-8","article-title":"Participation of people living with disabilities in physical activity: a global perspective","volume":"398","author":"Ginis KAM","year":"2021","unstructured":"Ginis KAM, van der Ploeg HP, Foster C, et\u00a0al. Participation of people living with disabilities in physical activity: a global perspective. Lancet. 2021;398(10298):443\u2013455. doi:10.1016\/S0140-6736(21)01164-8"},{"issue":"1","key":"r4","series-title":"J Environ Public Health","first-page":"4283027","article-title":"Physical activity among adults with low socioeconomic status living in industrialized countries: a meta\u2010ethnographic approach to understanding socioecological complexities","volume":"2020","author":"Rawal LB","year":"2020","unstructured":"Rawal LB, Smith BJ, Quach H, Renzaho AM. Physical activity among adults with low socioeconomic status living in industrialized countries: a meta\u2010ethnographic approach to understanding socioecological complexities. J Environ Public Health. 2020;2020(1):4283027."},{"issue":"14","key":"r5","series-title":"Transl J Am Coll Sports Med","first-page":"125","article-title":"Promoting physical activity among underserved populations","volume":"1","author":"Mendoza-Vasconez AS","year":"2016","unstructured":"Mendoza-Vasconez AS, Linke S, Mu\u00f1oz M, et\u00a0al. Promoting physical activity among underserved populations. Transl J Am Coll Sports Med. 2016;1(14):125\u2013132."},{"issue":"1","key":"r6","series-title":"Int J Environ Res Public Health","doi-asserted-by":"publisher","first-page":"699","DOI":"10.3390\/ijerph20010699","article-title":"Social support initiatives that facilitate exercise participation in community gyms for people with disability: a scoping review","volume":"20","author":"Kennedy RA","year":"2022","unstructured":"Kennedy RA, McKenzie G, Holmes C, Shields N. Social support initiatives that facilitate exercise participation in community gyms for people with disability: a scoping review. Int J Environ Res Public Health. 2022;20(1):699. doi:10.3390\/ijerph20010699"},{"issue":"2","key":"r7","series-title":"Adap Phys Act Q","first-page":"347","article-title":"Factors related to physical activity in adults with intellectual disabilities in group home settings: a systematic literature review","volume":"40","author":"Laxton P","year":"2022","unstructured":"Laxton P, Patterson F, Healy S. Factors related to physical activity in adults with intellectual disabilities in group home settings: a systematic literature review. Adap Phys Act Q. 2022;40(2):347\u2013377."},{"key":"r8","series-title":"Res Dev Disabil","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.ridd.2017.06.008","article-title":"Understanding low levels of physical activity in people with intellectual disabilities: a systematic review to identify barriers and facilitators","volume":"68","author":"Bossink LW","year":"2017","unstructured":"Bossink LW, van der Putten AA, Vlaskamp C. Understanding low levels of physical activity in people with intellectual disabilities: a systematic review to identify barriers and facilitators. Res Dev Disabil. 2017;68, 95\u2013110. doi:10.1016\/j.ridd.2017.06.008"},{"issue":"14","key":"r9","series-title":"Int J Environ Res Public Health","doi-asserted-by":"publisher","first-page":"7341","DOI":"10.3390\/ijerph18147341","article-title":"Barriers to, and facilitators of, exercising in fitness centres among adults with and without physical disabilities: a scoping review","volume":"18","author":"Nikolajsen H","year":"2021","unstructured":"Nikolajsen H, Sandal LF, Juhl CB, Troelsen J, Juul-Kristensen B. Barriers to, and facilitators of, exercising in fitness centres among adults with and without physical disabilities: a scoping review. Int J Environ Res Public Health. 2021;18(14):7341. doi:10.3390\/ijerph18147341"},{"issue":"4","key":"r10","series-title":"Res Q Exerc Sport","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1080\/02701367.2024.2343815","article-title":"A data-driven approach to predicting recreational activity participation using machine learning","volume":"95","author":"Lee S","year":"2024","unstructured":"Lee S, Kang M. A data-driven approach to predicting recreational activity participation using machine learning. Res Q Exerc Sport. 2024;95(4):873\u2013885. doi:10.1080\/02701367.2024.2343815"},{"issue":"4","key":"r11","series-title":"J Stat Theory Appl","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/s44199-023-00063-7","article-title":"An AI-driven predictive model for pancreatic cancer patients using extreme gradient boosting","volume":"22","author":"Chakraborty A","year":"2023","unstructured":"Chakraborty A, Tsokos CP. An AI-driven predictive model for pancreatic cancer patients using extreme gradient boosting. J Stat Theory Appl. 2023;22(4):262\u2013282. doi:10.1007\/s44199-023-00063-7"},{"issue":"1","key":"r12","series-title":"Mach Learn","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman L","year":"2001","unstructured":"Breiman L. Random forests. Mach Learn. 2001;45(1):5\u201332. doi:10.1023\/A:1010933404324"},{"issue":"1","key":"r13","series-title":"J R Stat Soc Ser B Stat Methodol","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani R","year":"1996","unstructured":"Tibshirani R. Regression shrinkage and selection via the lasso. J R Stat Soc Ser B Stat Methodol. 1996;58(1):267\u2013288. doi:10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"r14","series-title":"Support Vector Machines: Theory and Applications","first-page":"1","article-title":"Support vector machines\u2013an introduction","author":"Kecman V","year":"2005","unstructured":"Kecman V.\u00a0Support vector machines\u2013an introduction. In:\u00a0Wang L, ed. Support Vector Machines: Theory and Applications (pp.\u00a01\u201347). Springer Berlin Heidelberg; 2005."},{"key":"r15","series-title":"Int J Med Inform","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 Y","year":"2024","unstructured":"Wu Y, Ye Z, Wang Z, Duan S, Zhu J, Fang Y. Examining individual and contextual predictors of disability in Chinese older adults: a machine learning approach. Int J Med Inform. 2024;191:105552. doi:10.1016\/j.ijmedinf.2024.105552"},{"key":"r16","series-title":"Ann Epidemiol","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.annepidem.2025.06.012","article-title":"Integrated statistical modeling and machine learning techniques with SHAP for epidemiological data analysis","volume":"108","author":"Ain SQU","year":"2025","unstructured":"Ain SQU, Rather KUI. Integrated statistical modeling and machine learning techniques with SHAP for epidemiological data analysis. Ann Epidemiol. 2025;108:85\u201391. doi:10.1016\/j.annepidem.2025.06.012"},{"issue":"8","key":"r17","series-title":"Med Sci Sports Exerc","doi-asserted-by":"publisher","first-page":"1267","DOI":"10.1249\/mss.0b013e3180618bbe","article-title":"Reliability and validity of the instrument used in BRFSS to assess physical activity","volume":"39","author":"Yore MM","year":"2007","unstructured":"Yore MM, Ham SA, Ainsworth BE, et\u00a0al. Reliability and validity of the instrument used in BRFSS to assess physical activity. Med Sci Sports Exerc. 2007;39(8):1267\u20131274. doi:10.1249\/mss.0b013e3180618bbe"},{"issue":"11","key":"r18","series-title":"Clin Transl Sci","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\u2010Bobadilla AV","year":"2024","unstructured":"Ponce\u2010Bobadilla AV, Schmitt V, Maier CS, Mensing S, Stodtmann S. Practical guide to SHAP analysis: Explaining supervised machine learning model predictions in drug development. Clin Transl Sci. 2024;17(11):e70056. doi:10.1111\/cts.70056"},{"key":"r19","series-title":"J Prim Care Community Health","doi-asserted-by":"publisher","first-page":"21501319251400546","DOI":"10.1177\/21501319251400546","article-title":"Exploring explainable machine learning for predicting and interpreting self-reported diabetes among Tennessee adults: insights from the 2023 Behavioral Risk Factor Surveillance System (BRFSS)","volume":"16","author":"Muhammad MA","year":"2025","unstructured":"Muhammad MA, Sani J, Ahmed MM. Exploring explainable machine learning for predicting and interpreting self-reported diabetes among Tennessee adults: insights from the 2023 Behavioral Risk Factor Surveillance System (BRFSS). J Prim Care Community Health. 2025;16:21501319251400546. doi:10.1177\/21501319251400546"},{"issue":"11","key":"r20","series-title":"JAMA","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.1001\/jama.2013.276566","article-title":"Mobility limitation in the older patient: a clinical review","volume":"310","author":"Brown CJ","year":"2013","unstructured":"Brown CJ, Flood KL. Mobility limitation in the older patient: a clinical review. JAMA. 2013;310(11):1168\u20131177. doi:10.1001\/jama.2013.276566"},{"issue":"2","key":"r21","series-title":"Geriatr Nurs","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.gerinurse.2017.08.002","article-title":"The impact of mobility limitations on health outcomes among older adults","volume":"39","author":"Musich S","year":"2018","unstructured":"Musich S, Wang SS, Ruiz J, Hawkins K, Wicker E. The impact of mobility limitations on health outcomes among older adults. Geriatr Nurs. 2018;39(2):162\u2013169. doi:10.1016\/j.gerinurse.2017.08.002"},{"issue":"1","key":"r22","series-title":"J Dev Phys Disabil","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10882-025-10016-w","article-title":"Exercise considerations for adults with disabilities: a systematic review","volume":"38","author":"Mehringer J","year":"2026","unstructured":"Mehringer J, Fodstad JC, Ghuman G. Exercise considerations for adults with disabilities: a systematic review. J Dev Phys Disabil. 2026;38(1):1\u201321. doi:10.1007\/s10882-025-10016-w"},{"key":"r23","series-title":"Int J Orthop Trauma Nurs","doi-asserted-by":"publisher","first-page":"101161","DOI":"10.1016\/j.ijotn.2025.101161","article-title":"Risk prediction of functional disability among middle-aged and older adults with arthritis: a nationwide cross-sectional study using interpretable machine learning","volume":"56","author":"Li Q","year":"2025","unstructured":"Li Q, Shi W, Wang N, Wang G. Risk prediction of functional disability among middle-aged and older adults with arthritis: a nationwide cross-sectional study using interpretable machine learning. Int J Orthop Trauma Nurs. 2025;56:101161. doi:10.1016\/j.ijotn.2025.101161"}],"container-title":["Journal of Physical Activity and Health"],"original-title":[],"link":[{"URL":"https:\/\/journals.humankinetics.com\/view\/journals\/jpah\/23\/10\/article-p1485.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.humankinetics.com\/downloadpdf\/journals\/jpah\/23\/10\/article-p1485.xml","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/journals.humankinetics.com\/downloadpdf\/journals\/jpah\/23\/10\/article-p1485.xml","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T17:31:22Z","timestamp":1790357482000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.humankinetics.com\/view\/journals\/jpah\/23\/10\/article-p1485.xml"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":23,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1123\/jpah.2026-0347","relation":{},"ISSN":["1543-3080","1543-5474"],"issn-type":[{"value":"1543-3080","type":"print"},{"value":"1543-5474","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]}}}