AUTHOR=Thamrin Sri Astuti , Arsyad Dian Sidik , Kuswanto Hedi , Lawi Armin , Nasir Sudirman 

TITLE=Predicting Obesity in Adults Using Machine Learning Techniques: An Analysis of Indonesian Basic Health Research 2018

JOURNAL=Frontiers in Nutrition

VOLUME=Volume 8 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/nutrition/articles/10.3389/fnut.2021.669155

DOI=10.3389/fnut.2021.669155

ISSN=2296-861X

ABSTRACT=Obesity is strongly associated with multiple risk factors and it is significantly contributing to an increased risk of chronic disease morbidity and mortality worldwide.  There are various challenges to better understand the association between risk factors and the occurrence of obesity. The traditional regression approach limits the analysis to a small number of predictors and imposes assumptions of independence and linearity. The machine learning (ML) method is an alternative in providing information with a unique approach at the application stage of data analysis on obesity. The main objective of this paper is to compare the performance of three ML methods, namely Logistic regression, Classification and regression trees (CART) and Naïve Bayes for the classification of obesity status using Indonesian Basic Health Research (RISKESDAS) 2018.  This study indicates that the logistic regression method has a better performance based on metrics of accuracy, precision, F1-score, and F_β in the classification to predict obesity status compared to CART and Naïve Bayes methods. Age, checking blood pressure, grilled food consumption, days of consumption fruits per weeks, smoking habit, vigorous activity, moderate activity, stress, and blood pressure measures are significant in predicting obesity status. Identifying these risk factors could inform health authorities in designing or modifying existing policies for better controlling chronic disease especially in relation to risk factors associated to obesity. Moreover, applying ML methods on publicly available health data such as RISKESDAS is a promising strategy to fill the gap for a more robust understanding on the associations of multiple risk factors in predicting health outcomes.