![[2602.20303] Multilevel Determinants of Overweight and Obesity Among U.S. Children Aged 10-17: Comparative Evaluation of Statistical and Machine Learning Approaches Using the 2021 National Survey of Children's Health](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.20303] Multilevel Determinants of Overweight and Obesity Among U.S. Children Aged 10-17: Comparative Evaluation of Statistical and Machine Learning Approaches Using the 2021 National Survey of Children's Health
Summary
This study evaluates multilevel determinants of overweight and obesity among U.S. children aged 10-17, comparing statistical and machine learning approaches using data from the 2021 National Survey of Children's Health.
Why It Matters
Childhood obesity is a critical public health issue in the U.S., influenced by various factors. Understanding these determinants and the effectiveness of different predictive models can inform better interventions and policies aimed at reducing obesity rates among children.
Key Takeaways
- Multilevel predictors of obesity include diet, physical activity, and socioeconomic factors.
- Logistic regression and gradient boosting models showed the best balance of discrimination and calibration.
- Increased model complexity offers limited improvements over simpler models.
- Performance disparities exist across different racial and socioeconomic groups.
- Improved data quality and equity-focused approaches are essential for effective obesity surveillance.
Computer Science > Artificial Intelligence arXiv:2602.20303 (cs) [Submitted on 23 Feb 2026] Title:Multilevel Determinants of Overweight and Obesity Among U.S. Children Aged 10-17: Comparative Evaluation of Statistical and Machine Learning Approaches Using the 2021 National Survey of Children's Health Authors:Joyanta Jyoti Mondal View a PDF of the paper titled Multilevel Determinants of Overweight and Obesity Among U.S. Children Aged 10-17: Comparative Evaluation of Statistical and Machine Learning Approaches Using the 2021 National Survey of Children's Health, by Joyanta Jyoti Mondal View PDF HTML (experimental) Abstract:Background: Childhood and adolescent overweight and obesity remain major public health concerns in the United States and are shaped by behavioral, household, and community factors. Their joint predictive structure at the population level remains incompletely characterized. Objectives: The study aims to identify multilevel predictors of overweight and obesity among U.S. adolescents and compare the predictive performance, calibration, and subgroup equity of statistical, machine-learning, and deep-learning models. Data and Methods: We analyze 18,792 children aged 10-17 years from the 2021 National Survey of Children's Health. Overweight/obesity is defined using BMI categories. Predictors included diet, physical activity, sleep, parental stress, socioeconomic conditions, adverse experiences, and neighborhood characteristics. Models include logistic regression,...
