Identifying factors associated with central obesity in school students using artificial intelligence techniques

Area of Science:

• Pediatric Health
• Public Health
• Machine Learning in Healthcare

Background:

• Central obesity is a growing concern in school-aged children.
• Identifying predictive factors is crucial for early intervention and prevention strategies.

Purpose of the Study:

• To identify the minimal set of factors predicting central obesity in Beijing school students.
• To determine the optimal machine learning algorithm for this prediction.

Main Methods:

• A cross-sectional survey of 11,308 students aged 6-14 in Beijing.
• Data analysis using machine learning algorithms, including Light Gradient Boosting Machine (LGBM).
• Cluster sampling and online questionnaires were employed.

Main Results:

• The Light Gradient Boosting Machine (LGBM) model showed superior performance.
• A minimal set of six factors (parental BMI, food preferences, outdoor activity, screen time, sex) effectively predicted central obesity.
• Prediction accuracy using the minimal set was comparable to using the entire dataset.

Conclusions:

• A validated minimal set of six factors can predict central obesity risk in children.
• The LGBM model provides an optimal approach for central obesity prediction.
• These findings can inform targeted public health interventions for pediatric obesity.