Related Experiment Video
Updated: Oct 27, 2025
Assessment of Child Anthropometry in a Large Epidemiologic Study
Published on: February 2, 2017
An ensemble-based feature selection framework to select risk factors of childhood obesity for policy decision making
Xi Shi1, Gorana Nikolic2, Gorka Epelde3,4
1Department of Electrical Engineering (ESAT), Stadius Centre for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Kasteelpark Arenberg 10 - box 2446, 3001, Leuven, Belgium. xi.shi@esat.kuleuven.be.
Insights
Identifying childhood obesity risk factors is crucial. A new ensemble framework, BFSMR, effectively pinpointed key factors like age, sex, diet, and maternal health, aiding in better prevention strategies.
Area of Science:
- Public Health
- Data Science
- Pediatrics
Background:
- Childhood obesity prevalence necessitates studying population-representative risk factors for effective policy.
- Developing advanced analytical frameworks is essential for identifying these factors in large datasets.
Purpose of the Study:
- To develop an ensemble feature selection framework (BFSMR) for identifying childhood obesity risk factors.
- To ensure the selected features are interpretable and clinically relevant for intervention planning.
Main Methods:
- Analyzed data from 426,813 children (2000-2019), defining overweight by BMI percentile.
- Proposed the Bagging-based Feature Selection framework integrating MapReduce (BFSMR) using 5 distinct feature selection models.
- Implemented a weighted voting strategy considering feature and model importance for robust risk factor identification.
Main Results:
- The BFSMR framework demonstrated superior performance in selecting interpretable and clinically relevant features.
- Top identified risk factors include age, sex, birth year, breastfeeding, child/maternal diet knowledge, exercise, and maternal blood pressure.
Conclusions:
- The BFSMR framework offers a robust, unbiased solution for analyzing large-scale health data.
- This approach facilitates the identification of diverse, interpretable risk factors for childhood obesity and other diseases, informing future interventions.
Background:
The increasing prevalence of childhood obesity makes it essential to study the risk factors with a sample representative of the population covering more health topics for better preventive policies and interventions. It is aimed to develop an ensemble feature selection framework for large-scale data to identify risk factors of childhood obesity with good interpretability and clinical relevance.
Methods:
We analyzed the data collected from 426,813 children under 18 during 2000-2019. A BMI above the 90th percentile for the children of the same age and gender was defined as overweight. An ensemble feature selection framework, Bagging-based Feature Selection framework integrating MapReduce (BFSMR), was proposed to identify risk factors. The framework comprises 5 models (filter with mutual information/SVM-RFE/Lasso/Ridge/Random Forest) from filter, wrapper, and embedded feature selection methods. Each feature selection model identified 10 variables based on variable importance. Considering accuracy, F-score, and model characteristics, the models were classified into 3 levels with different weights: Lasso/Ridge, Filter/SVM-RFE, and Random Forest. The voting strategy was applied to aggregate the selected features, with both feature weights and model weights taken into consideration. We compared our voting strategy with another two for selecting top-ranked features in terms of 6 dimensions of interpretability.
Results:
Our method performed the best to select the features with good interpretability and clinical relevance. The top 10 features selected by BFSMR are age, sex, birth year, breastfeeding type, smoking habit and diet-related knowledge of both children and mothers, exercise, and Mother's systolic blood pressure.
Conclusion:
Our framework provides a solution for identifying a diverse and interpretable feature set without model bias from large-scale data, which can help identify risk factors of childhood obesity and potentially some other diseases for future interventions or policies.
Related Concept Videos
01:24Obesity
01:25Statistical Methods for Analyzing Epidemiological Data
01:25Strategies for Assessing and Addressing Confounding
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
01:12Statistical Software for Data Analysis and Clinical Trials
01:11Genome-wide Association Studies-GWAS
GWAS does not require the identification of the target gene involved in...
01:20Lifestyle Factors and Health
Benefits of Physical Activity
Physical activity, whether through structured exercise or casual activities like walking, biking, or dancing, is a cornerstone of a...