Model and variable selection using machine learning methods with applications to childhood stunting in Bangladesh

ABSTRACT

Childhood stunting is a serious public health concern in Bangladesh. Earlier research used conventional statistical methods to identify the risk factors of stunting, and very little is known about the applications and usefulness of machine learning (ML) methods that can identify the risk factors of various health conditions based on complex data. This research evaluates the performance of ML methods in predicting stunting among under-5 aged children using 2014 Bangladesh Demographic and Health Survey data. Besides, this paper identifies variables which are important to predict stunting in Bangladesh. Among the selected ML methods, gradient boosting provides the smallest misclassification error in predicting stunting, followed by random forests, support vector machines, classification tree and logistic regression with forward-stepwise selection. The top 10 important variables (in order of importance) that better predict childhood stunting in Bangladesh are child age, wealth index, maternal education, preceding birth interval, paternal education, division, household size, maternal age at first birth, maternal nutritional status, and parental age. Our study shows that ML can support the building of prediction models and emphasizes on the demographic, socioeconomic, nutritional and environmental factors to understand stunting in Bangladesh.

KEYWORDS:

• Machine learning
• prediction
• variable importance
• stunting
• Bangladesh

Author’s Contribution

JRK conceptualized the study and compiled the data. JRK and JHT finalized analysis plan, performed the statistical analysis, and drafted/revised the manuscript. ER critically reviewed the manuscript and contributed in manuscript writing. All authors read and approved the final manuscript.

Acknowledgments

The authors would like to acknowledge MEASURE DHS for making data publicly available. The authors would also like to acknowledge individuals and institutions involved in conducting the 2014 BDHS. The author JHT greatly acknowledges the computing facilities he received from Compute Canada. We thank the Editor, and the anonymous reviewer for insightful comments, which substantially strengthened the arguments presented here.

Disclosure statement

The authors declare no competing interests.

Financial support

Authors did not receive any funding for this research.

Supplementary material

Supplemental data for this article can be accessed on the publisher’s website