{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T06:41:12Z","timestamp":1791528072902,"version":"4.3.4"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"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>Purposes<\/jats:title>\n                    <jats:p>This study aimed to develop a machine learning model to predict body mass index (BMI) in adolescents based on readily accessible daily information and to investigate the influence of modifiable factors on BMI changes through model interpretation techniques.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This study is a one-year prospective cohort study. Baseline data were collected through anthropometric measurements and questionnaires, and BMI were reassessed after 1 year. Six machine learning models were developed to predict BMI. Nested cross-validation (CV) was used for hyperparameter tuning and performance estimation. Predictors were prescreened on the inner-training folds of the nested CV using univariable analyses. Model performance was evaluated using Root Mean Squared Error (RMSE), Mean Squared Error (MSE), Mean Absolute Error (MAE), and coefficient of determination (R\n                      <jats:sup>2<\/jats:sup>\n                      ). SHapley Additive exPlanations (SHAP) was used for global and local interpretations of the models.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The mean BMI of the 1,827 students included in the final analysis increased from 21.18\u202f\u00b1\u202f3.63\u202fkg\/m\n                      <jats:sup>2<\/jats:sup>\n                      at baseline to 21.54\u202f\u00b1\u202f3.59\u202fkg\/m\n                      <jats:sup>2<\/jats:sup>\n                      after 1 year, with an average change of 0.36\u202f\u00b1\u202f1.40\u202fkg\/m\n                      <jats:sup>2<\/jats:sup>\n                      . The CatBoost (CB) model demonstrated the best predictive performance. After calibration, it achieved an RMSE of 1.200 [95% confidence interval (CI): 1.101\u20131.303], MSE of 1.440 (95% CI: 1.211\u20131.697), MAE of 0.895 (95% CI: 0.818\u20130.981) and R\n                      <jats:sup>2<\/jats:sup>\n                      of 0.902 (95% CI: 0.882\u20130.918). In the SHAP analysis, the top 5 modifiable features at the population level were: level of health literacy, recognize self-weight status correctly, sedentariness duration on weekends, participation in professional sports training, frequency of staying up late.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study developed a BMI prediction model for adolescents using readily accessible daily information. The model accurately predicts BMI values 1 year later and provides both population-level and individual-level interpretability. Compared to existing studies, it offers key advantages, including independence from complex clinical data, the ability to predict continuous BMI values, and strong model interpretability. Our findings provide a promising research tool for screening high-risk adolescents, informing public health prevention and intervention strategies, and supporting personalized clinical interventions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2025.1657551","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T05:12:08Z","timestamp":1763615528000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Development and interpretation of a machine learning model for predicting body mass index in Chinese adolescents: a prospective cohort study"],"prefix":"10.3389","volume":"13","author":[{"given":"Zikang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoming","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangwen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yining","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e22119","DOI":"10.7759\/cureus.22119","article-title":"Body mass index (BMI): a screening tool analysis","volume":"14","author":"Khanna","year":"2022","journal-title":"Cureus"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1186\/s13058-024-01907-5","article-title":"Body mass index and breast cancer risk in premenopausal and postmenopausal east Asian women: a pooled analysis of 13 cohort studies","volume":"26","author":"Wada","year":"2024","journal-title":"Breast Cancer Res"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1007\/s11906-022-01213-5","article-title":"Cardiovascular disease risk reduction and body mass index","volume":"24","author":"Samson","year":"2022","journal-title":"Curr Hypertens Rep"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1111\/1753-0407.13370","article-title":"Expansion of human alpha-cell area is associated with a higher maximum body mass index before the onset of type 2 diabetes","volume":"15","author":"Ozawa","year":"2023","journal-title":"J Diabetes"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"8928","DOI":"10.1038\/s41598-023-36111-6","article-title":"The risk of colorectal cancer according to obesity status at four-year intervals: a nationwide population-based cohort study","volume":"13","author":"Seo","year":"2023","journal-title":"Sci Rep"},{"key":"ref6","volume-title":"World obesity atlas 2024","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"371","DOI":"10.3945\/ajcn.116.130252","article-title":"Genetic and environmental effects on body mass index from infancy to the onset of adulthood: an individual-based pooled analysis of 45 twin cohorts participating in the COllaborative project of development of anthropometrical measures in twins (CODATwins) study","volume":"104","author":"Silventoinen","year":"2016","journal-title":"Am J Clin Nutr"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1186\/s12966-024-01587-6","article-title":"Longitudinal associations of screen time, physical activity, and sleep duration with body mass index in US youth","volume":"21","author":"Zink","year":"2024","journal-title":"Int J Behav Nutr Phys Act"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"386","DOI":"10.3390\/healthcare13040386","article-title":"What factors influence obesity in Spain? A multivariate analysis of sociodemographic, nutritional, and lifestyle factors affecting body mass index in the Spanish population","volume":"13","author":"Sandri","year":"2025","journal-title":"Healthcare"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1682","DOI":"10.1007\/s11682-019-00101-y","article-title":"Accurate neuroimaging biomarkers to predict body mass index in adolescents: a longitudinal study","volume":"14","author":"Park","year":"2020","journal-title":"Brain Imaging Behav"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2949","DOI":"10.3390\/diagnostics13182949","article-title":"Estimation of obesity levels through the proposed predictive approach based on physical activity and nutritional habits","volume":"13","author":"Gozukara Bag","year":"2023","journal-title":"Diagnostics"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.3390\/s20041134","article-title":"Motion-to-BMI: using motion sensors to predict the body mass index of smartphone users","volume":"20","author":"Yao","year":"2020","journal-title":"Sensors"},{"key":"ref13","first-page":"6034","article-title":"Multi-view body image-based prediction of body mass index and various body part sizes","author":"Kim","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1002\/pds.5367","article-title":"Predicting obesity and smoking using medication data: a machine-learning approach","volume":"31","author":"Ali","year":"2022","journal-title":"Pharmacoepidemiol Drug Saf"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1469981","DOI":"10.3389\/fdata.2024.1469981","article-title":"Prediction and classification of obesity risk based on a hybrid metaheuristic machine learning approach","volume":"7","author":"Helforoush","year":"2024","journal-title":"Front Big Data"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1186\/s12911-025-02944-6","article-title":"The role of explainable artificial intelligence in disease prediction: a systematic literature review and future research directions","volume":"25","author":"Alkhanbouli","year":"2025","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref17","first-page":"4768","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"470","DOI":"10.62347\/TFUC2568","article-title":"Development and validation of a prediction model for myelosuppression in lung cancer patients after platinum-based doublet chemotherapy: a multifactorial analysis approach","volume":"15","author":"Li","year":"2025","journal-title":"Am J Cancer Res"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e41142","DOI":"10.2196\/41142","article-title":"Machine learning-based prediction of acute kidney injury following pediatric cardiac surgery: model development and validation study","volume":"25","author":"Luo","year":"2023","journal-title":"J Med Internet Res"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1489848","DOI":"10.3389\/fpubh.2024.1489848","article-title":"Predicting grip strength-related frailty in middle-aged and older Chinese adults using interpretable machine learning models: a prospective cohort study","volume":"12","author":"Yu","year":"2024","journal-title":"Front Public Health"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.1111\/jopy.12816","article-title":"Body mass predicts personality development across 18 years in middle to older adulthood","volume":"91","author":"Arum\u00e4e","year":"2023","journal-title":"J Pers"},{"key":"ref22","first-page":"231","article-title":"A machine learning approach for predicting weight gain risks in young adults","author":"Singh","year":"2019"},{"key":"ref23","volume-title":"Annex 1: equations for the prediction of basal metabolic rate","year":"2004"},{"key":"ref24","volume-title":"Human energy requirements","year":"2004"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"97","DOI":"10.3760\/j.issn:0254-6450.2004.02.003","article-title":"Body mass index reference norm for screening overweight and obesity in Chinese children and adolescents","volume":"25","year":"2004","journal-title":"Zhonghua Liu Xing Bing Xue Za Zhi"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"193","DOI":"10.2147\/IJGM.S395281","article-title":"Body self-perception, dietary self-efficacy, and body mass index in young adults: a cross-sectional survey","volume":"16","author":"Ramirez Luque","year":"2023","journal-title":"Int J Gen Med"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1128552","DOI":"10.3389\/fpubh.2023.1128552","article-title":"Secular trends and sociodemographic determinants of thinness, overweight and obesity among Chinese children and adolescents aged 7-18 years from 2010 to 2018","volume":"11","author":"Li","year":"2023","journal-title":"Front Public Health"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"410","DOI":"10.4324\/9780203771587","volume-title":"Statistical power analysis for the behavioral sciences","author":"Cohen","year":"2013"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"20170213","DOI":"10.1098\/rsif.2017.0213","article-title":"The coefficient of determination R2 and intra-class correlation coefficient from generalized linear mixed-effects models revisited and expanded","volume":"14","author":"Nakagawa","year":"2017","journal-title":"J R Soc Interface"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"3083","DOI":"10.1002\/sim.3697","article-title":"Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples","volume":"28","author":"Austin","year":"2009","journal-title":"Stat Med"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"16","DOI":"10.21037\/atm.2018.12.10","article-title":"Balance diagnostics after propensity score matching","volume":"7","author":"Zhang","year":"2019","journal-title":"Ann Transl Med"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1186\/1471-2105-7-91","article-title":"Bias in error estimation when using cross-validation for model selection","volume":"7","author":"Varma","year":"2006","journal-title":"BMC Bioinformatics"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"3093","DOI":"10.1093\/bioinformatics\/btaa046","article-title":"Consensus features nested cross-validation","volume":"36","author":"Parvandeh","year":"2020","journal-title":"Bioinformatics"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.2307\/1911963","article-title":"A simple test for heteroscedasticity and random coefficient variation","volume":"47","author":"Breusch","year":"1979","journal-title":"Econometrica"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4899-2873-3","volume-title":"Transformation and weighting in regression","author":"Carroll","year":"1988"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.jchromb.2008.07.043","article-title":"Weighted least squares in calibration: the problem with using \u201cquality coefficients\u201d to select weighting formulas","volume":"872","author":"Tellinghuisen","year":"2008","journal-title":"J Chromatogr B"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1507379","DOI":"10.3389\/fped.2024.1507379","article-title":"The role of health literacy in intervention studies targeting children living with overweight or obesity and their parents\u2014a systematic mixed methods review","volume":"12","author":"Holmen","year":"2025","journal-title":"Front Pediatr"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"805","DOI":"10.3390\/children11070805","article-title":"Self-perception profile, body image perception and satisfaction in relation to body mass index: an investigation in a sample of adolescents from the Campania region, Italy","volume":"11","author":"Ballarin","year":"2024","journal-title":"Children"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"14738","DOI":"10.1038\/s41598-017-15137-7","article-title":"Development of multivariable models to predict change in body mass index within a clinical trial population of psychotic individuals","volume":"7","author":"Harrison","year":"2017","journal-title":"Sci Rep"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"8781","DOI":"10.1038\/s41598-023-35935-6","article-title":"Predicting body mass index in early childhood using data from the first 1000 days","volume":"13","author":"Cheng","year":"2023","journal-title":"Sci Rep"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.3390\/s21072361","article-title":"The prediction of body mass index from negative affectivity through machine learning: a confirmatory study","volume":"21","author":"Delnevo","year":"2021","journal-title":"Sensors"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"4617","DOI":"10.21037\/qims-24-7","article-title":"Multiparametric magnetic resonance imaging (MRI)-based radiomics model explained by the Shapley additive exPlanations (SHAP) method for predicting complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer: a multicenter retrospective study","volume":"14","author":"Wang","year":"2024","journal-title":"Quant Imaging Med Surg"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"103715","DOI":"10.1016\/j.iccn.2024.103715","article-title":"Prediction model of pressure injury occurrence in diabetic patients during ICU hospitalization\u2014\u2014XGBoost machine learning model can be interpreted based on SHAP","volume":"83","author":"Xu","year":"2024","journal-title":"Intensive Crit Care Nurs"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"423301","DOI":"10.1007\/s10409-023-23301-x","article-title":"Ensemble machine learning for predicting the homogenized elastic properties of unidirectional composites: a SHAP-based interpretability analysis","volume":"40","author":"Wang","year":"2024","journal-title":"Acta Mech Sinica"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1049\/itr2.12514","article-title":"Predicting travel mode choice with a robust neural network and Shapley additive explanations analysis","volume":"18","author":"Tang","year":"2024","journal-title":"IET Intell Transp Syst"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"1445864","DOI":"10.3389\/fpubh.2024.1445864","article-title":"A hybrid self-supervised model predicting life satisfaction in South Korea","volume":"12","author":"Nguyen","year":"2024","journal-title":"Front Public Health"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"174383","DOI":"10.1016\/j.scitotenv.2024.174383","article-title":"Machine learning predicts the growth of cyanobacterial genera in river systems and reveals their different environmental responses","volume":"946","author":"Wang","year":"2024","journal-title":"Sci Total Environ"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"1681","DOI":"10.3390\/nu11071681","article-title":"Phenotyping women based on dietary macronutrients, physical activity, and body weight using machine learning tools","volume":"11","author":"Ramyaa","year":"2019","journal-title":"Nutrients"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"4684","DOI":"10.3390\/ijerph16234684","article-title":"Predicting factors affecting adolescent obesity using general Bayesian network and what-if analysis","volume":"16","author":"Kim","year":"2019","journal-title":"Int J Environ Res Public Health"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1657551\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T05:12:10Z","timestamp":1763615530000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1657551\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,20]]},"references-count":49,"alternative-id":["10.3389\/fpubh.2025.1657551"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2025.1657551","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,20]]},"article-number":"1657551"}}