{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T23:37:51Z","timestamp":1793835471999,"version":"4.6.1"},"reference-count":28,"publisher":"BMJ","issue":"3","license":[{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"unspecified","delay-in-days":22,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["bmjph"],"accepted":{"date-parts":[[2026,7,7]]},"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Adolescent obesity is a growing concern in India, shaped by sociodemographic, behavioural, familial, sleep and mental health factors. Validated AI-based prediction models for adolescents are scarce. Generative AI (GenAI) offers opportunities to improve accuracy through synthetic data augmentation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A case-control, school-based study included 1292 adolescents aged 10\u201316 years from Mysuru and Chamarajanagar, selected via stratified random sampling. Data on sociodemographic, lifestyle, sleep, mental health, familial and anthropometric measures were collected using validated tools. The dataset was split into training (80%), validation (10%) and testing (10%). Conditional tabular generative adversarial network (CTGAN) generated 1000 synthetic samples and a variational autoencoder (VAE) produced 500, expanding training to 2532 records. Fidelity was assessed using Kolmogorov-Smirnov tests, principal component analysis (PCA), Wasserstein distance and privacy risk checks. A stacking ensemble combining XGBoost, TabNet and TabTransformer with logistic regression stacking was trained using 10-fold cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The final model achieved an accuracy of 0.977, sensitivity 0.97, specificity 0.985, F1 score 0.97 and AUC 0.994. Calibration was strong (Brier score 0.042; Hosmer\u2013Lemeshow p&gt;0.05). SHAP and TabNet analyses highlighted screen time, sleep duration, parental obesity, physical activity and diet as key predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The GenAI-enhanced stacking ensemble model accurately predicts adolescent obesity, with strong calibration and interpretability. It identifies behavioural and familial determinants, supporting school and community deployment for early detection and prevention.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjph-2025-004650","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T18:00:16Z","timestamp":1784829616000},"page":"e004650","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Generative AI-enhanced ensemble model for predicting adolescent obesity in India: a school-based study in two southern districts of Karnataka"],"prefix":"10.1136","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2011-1790","authenticated-orcid":false,"given":"Jayashankar","family":"Rakshitha","sequence":"first","affiliation":[{"name":"Department Of Community Medicine, JSS Medical College, JSS Academy of Higher Education and Research, Mysuru, Karnataka, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8755-3975","authenticated-orcid":false,"given":"Doddaiah","family":"Sunil Kumar","sequence":"additional","affiliation":[{"name":"Department Of Community Medicine, JSS Medical College, JSS Academy of Higher Education and Research, Mysuru, Karnataka, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M","family":"Santhosh Kumar","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, JSS Medical College, JSS Academy of Higher Education and Research, Mysuru, Karnataka, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vanishri","family":"Arun","sequence":"additional","affiliation":[{"name":"Department of Information Science and Engineering, JSS Science and Technology University, Mysuru, Karnataka, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4433-8567","authenticated-orcid":false,"given":"Kamidi Venkatesh","family":"Krishnamurthy","sequence":"additional","affiliation":[{"name":"Department Of Community Medicine, JSS Medical College, JSS Academy of Higher Education and Research, Mysuru, Karnataka, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"key":"2026072311000897000_4.3.e004650.1","unstructured":"World Health Organisation . Obesity and overweight. Geneva: WHO, 2024."},{"key":"2026072311000897000_4.3.e004650.2","first-page":"645","article-title":"Prevalence and correlates of overweight and obesity among adolescents in India: A scoping review","volume":"46","author":"Moitra","year":"2021","journal-title":"Indian J Community Med"},{"key":"2026072311000897000_4.3.e004650.3","doi-asserted-by":"crossref","first-page":"187","DOI":"10.4103\/2249-4863.154628","article-title":"Childhood obesity: causes and consequences","volume":"4","author":"Sahoo","year":"2015","journal-title":"J Family Med Prim Care"},{"key":"2026072311000897000_4.3.e004650.4","article-title":"Co-occurrence of behavioural risk factors among Indian adolescents","volume":"21","author":"Moitra","year":"2021","journal-title":"BMC Public Health"},{"key":"2026072311000897000_4.3.e004650.5","doi-asserted-by":"publisher","DOI":"10.3390\/nu5072708"},{"key":"2026072311000897000_4.3.e004650.6","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-020-01082-z"},{"key":"2026072311000897000_4.3.e004650.7","first-page":"25","article-title":"Synthetic data for healthcare: A review of methods and applications","volume":"11","author":"Yelamanchili","year":"2023","journal-title":"Health Inf Sci Syst"},{"key":"2026072311000897000_4.3.e004650.8","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-025-31928-9","article-title":"Enhanced diabetes prediction using CTGAN-MLP approach on body composition data","volume":"16","author":"Joloudari","year":"2025","journal-title":"Sci Rep"},{"key":"2026072311000897000_4.3.e004650.9","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1007\/s10729-025-09718-6","article-title":"Innovations in early detection of chronic non-communicable diseases among adolescents through an easy-to-Use AutoML paradigm","volume":"28","author":"Rankovic","year":"2025","journal-title":"Health Care Manag Sci"},{"key":"2026072311000897000_4.3.e004650.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.109834"},{"key":"2026072311000897000_4.3.e004650.11","doi-asserted-by":"crossref","first-page":"2282","DOI":"10.1109\/JBHI.2024.3356580","article-title":"DeepHealthNet: Adolescent Obesity Prediction System Based on a Deep Learning Framework","volume":"28","author":"Jeong","year":"2023","journal-title":"IEEE J Biomed Health Inform"},{"key":"2026072311000897000_4.3.e004650.12","doi-asserted-by":"crossref","first-page":"231","DOI":"10.56450\/JEFI.2025.v3i03.002","article-title":"Artificial Intelligence\u2013Driven Models for Predicting Adolescent Obesity: A Comprehensive Review","volume":"3","author":"Rakshitha","year":"2025","journal-title":"JEFI"},{"key":"2026072311000897000_4.3.e004650.13","doi-asserted-by":"publisher","DOI":"10.4103\/0971-5916.180203"},{"key":"2026072311000897000_4.3.e004650.14","unstructured":"NFHS-5. National family health survey. Ministry of Health & Family Welfare, Government of India; 2021."},{"key":"2026072311000897000_4.3.e004650.15","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.6361"},{"key":"2026072311000897000_4.3.e004650.16","first-page":"377","article-title":"Increasing prevalence of childhood obesity in Korea","volume":"61","author":"Park","year":"2018","journal-title":"Clin Exp Pediatr"},{"key":"2026072311000897000_4.3.e004650.17","first-page":"1019","article-title":"Sedentary behaviour and adiposity in youth: A systematic review","volume":"47","author":"Biddle","year":"2017","journal-title":"Sports Med"},{"key":"2026072311000897000_4.3.e004650.18","doi-asserted-by":"publisher","DOI":"10.1139\/apnm-2015-0627"},{"key":"2026072311000897000_4.3.e004650.19","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1007\/s12098-012-0923-5","article-title":"Childhood Obesity and the Metabolic Syndrome in Developing Countries","volume":"80","author":"Gupta","year":"2013","journal-title":"Indian J Pediatr"},{"key":"2026072311000897000_4.3.e004650.20","unstructured":"Xu L , Skoularidou M , Cuesta-Infante A , et al . Modeling tabular data using conditional GAN. NeurIPS; 2019"},{"key":"2026072311000897000_4.3.e004650.21","doi-asserted-by":"crossref","unstructured":"Steyerberg EW . Clinical prediction models. Springer, 2019.","DOI":"10.1007\/978-3-030-16399-0"},{"key":"2026072311000897000_4.3.e004650.22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105637"},{"key":"2026072311000897000_4.3.e004650.23","first-page":"17","article-title":"Childhood obesity prediction using machine-learning techniques","volume":"7","author":"Hussain","year":"2019","journal-title":"Health Inf Sci Syst"},{"key":"2026072311000897000_4.3.e004650.24","article-title":"Predictors of obesity among adolescents: A machine-learning approach","volume":"16","author":"Toh","year":"2021","journal-title":"Pediatr Obes"},{"key":"2026072311000897000_4.3.e004650.25","doi-asserted-by":"publisher","DOI":"10.1126\/science.aax2342"},{"key":"2026072311000897000_4.3.e004650.26","first-page":"1","article-title":"Childhood obesity: Global evidence","volume":"10","author":"Lobstein","year":"2015","journal-title":"Int J Pediatr Obes"},{"key":"2026072311000897000_4.3.e004650.27","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.38470.670903.E0"},{"key":"2026072311000897000_4.3.e004650.28","unstructured":"WHO . Report of the commission on ending childhood obesity. World Health Organization, 2016."}],"container-title":["BMJ Public Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjph-2025-004650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T18:00:21Z","timestamp":1784829621000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjpublichealth.bmj.com\/lookup\/doi\/10.1136\/bmjph-2025-004650"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":28,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,7,23]]},"published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1136\/bmjph-2025-004650"],"URL":"https:\/\/doi.org\/10.1136\/bmjph-2025-004650","relation":{},"ISSN":["2753-4294"],"issn-type":[{"value":"2753-4294","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}