Tehran University of Medical Sciences Iranian Journal of Public Health 2251-6085 54 12 2025 12 31 2690 2700 Changgyun Kim Department of Electronic and AI System Engineering, Kangwon National University, Kangwon, Samcheok, 25913, Republic of Korea Ji-Yong Lee Center for Sports and Performance Analysis, Korea National Sports University, Seoul, Songpa-gu, 05541, Republic of Korea 2025 04 30 2025 06 21 Background: Childhood obesity poses serious long-term health risks and is a growing global concern. In South Korea, national health surveys collect behavioral and physical data from elementary students, but the large number of questionnaire items can burden young respondents and reduce accuracy. Thus, simplified models with high predictive power are needed. Methods: We analyzed data from over 250,000 elementary students collected by the Korean Ministry of Education (2015–2022). Using the Rohrer Index as the outcome variable, key predictors were selected via Lasso and Elastic Net regression. Categorical variables were reduced using Multiple Correspondence Analysis (MCA), and a deep learning model (NECTOR) combining MLP and self-attention was developed. Results: NECTOR achieved high predictive performance with R² scores of 0.994 (boys) and 0.996 (girls), and low mean squared errors of 3.072 and 1.841, respectively. It outperformed baseline models using the same inputs. Conclusion: A small set of core health indicators can effectively predict the Rohrer Index. The proposed model enables efficient and reliable obesity screening in school settings, supporting early intervention efforts. https://ijph.tums.ac.ir/index.php/ijph/article/view/38957 https://ijph.tums.ac.ir/index.php/ijph/article/download/38957/8729