Related Experiment Video
Updated: May 29, 2025
Assessment of Child Anthropometry in a Large Epidemiologic Study
Published on: February 2, 2017
Factors associated with underweight, overweight, and obesity in Chinese children aged 3-14 years using ensemble
Kening Chen1, Fangjieyi Zheng2, Xiaoqian Zhang3,4
1China-Japan Friendship Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
Insights
Machine learning accurately predicts childhood underweight, overweight, and obesity. Key factors include maternal BMI, paternal BMI, age, and lifestyle choices like fast food intake and sedentary time.
Area of Science:
- Pediatric Nutrition
- Computational Biology
- Public Health
Background:
- Childhood malnutrition (underweight, overweight, obesity) factors remain unclear.
- Traditional models struggle with complex, large-scale data.
- Machine learning offers advanced analytical capabilities.
Purpose of the Study:
- Identify key factors contributing to childhood underweight, overweight, and obesity.
- Utilize machine learning for predictive modeling in Chinese children.
- Develop a practical tool for assessing malnutrition risk.
Main Methods:
- Ensemble learning algorithms (Random Forest) applied to data from 18,503 children (aged 3-14).
- Weight status classified using World Health Organization criteria.
- Factors ranked by importance; optimal predictive sets identified.
Main Results:
- Random Forest demonstrated superior performance in predicting all three conditions.
- Optimal factors for underweight: maternal BMI, age, paternal BMI, reproductive ages, birth weight.
- Optimal factors for overweight/obesity: age, fast food intake, maternal BMI, paternal BMI, sedentary time, maternal reproductive age.
Conclusions:
- Random Forest is an effective algorithm for predicting childhood weight status.
- Identified key predictive factors for underweight, overweight, and obesity.
- A web application was developed to apply these findings.
Background:
Factors underlying the development of childhood underweight, overweight, and obesity are not fully understood. Traditional models have drawbacks in handling large-scale, high-dimensional, and nonlinear data. In this study, we aimed to identify factors responsible for underweight, overweight, and obesity using machine learning methods among Chinese children.
Methods:
Our study participants were children aged 3-14 from 30 kindergartens and 26 schools in Beijing and Tangshan. Weight status was defined per the World Health Organization criteria. We implemented three ensemble learning algorithms and compared their performance and ranked the contributing factors by importance and identified an optimal set. A user-friendly web application was developed to calculate the predicted probability of childhood underweight, overweight, and obesity.
Results:
We analysed data from 18 503 children aged 3-14, including 1798 underweight, 10 579 of normal weight, 3257 overweight, and 2869 with obesity. Of all algorithms, random forest performed the best, with the area under the receiver operating characteristic reaching 0.759 for underweight, 0.806 for overweight, and 0.849 for obesity, with other metrics also reinforcing this algorithm. Further cumulative analyses showed that, for underweight, the optimal set of six factors included maternal body mass index (BMI), age, paternal BMI, maternal reproductive age, paternal reproductive age, and birth weight. The optimal set for overweight comprised of five factors: age, fast food intake, maternal BMI, paternal BMI, and sedentary time. For obesity, the optimal set included six factors: age, fast food intake, maternal BMI, paternal BMI, sedentary time, and maternal reproductive age. Further logistic regression analyses confirmed the predictive capability of individual top factors.
Conclusions:
Our findings indicate that random forest is the best ensemble learning algorithm for predicting underweight, overweight, and obesity in children aged 3-14 years. We identified the optimal set of significant factors for each malnutrition status and incorporated them into a web application to support the application of this study's findings.
Related Concept Videos
01:47Lung Capacity
01:24Obesity
00:57Weighted Mean
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
01:10Nature and Nurture