Data Analysis and Computational Methods for Assessing Knowledge of Obesity Risk Factors among Saudi Citizens

Abstract

Introduction. According to the World Health Organization (2020), obesity is a growing problem worldwide. In fact, obesity is characterized as an epidemic. Objective. The aim of this paper is to use a logistic regression model as one of the generalized linear models and decision tree as one of the machine learning in order to assess the knowledge of the risk factors for obesity among citizens in Saudi Arabia. Methods and Materials. A cross-sectional questionnaire was given to the general population in KSA, using Google forms, to collect data. A total of 1369 people responded. Results. The findings showed that there is widespread knowledge of risk factors for obesity among citizens in Saudi Arabia. Participants' knowledge of risk factors was very high (95.5%). In addition, a significant association was found between demographics (gender, age, and level of education) and knowledge of risk factors for obesity, in assessing variables for knowledge of the risk factors for obesity in relation to the demographics of gender and level of education. In addition, from decision tree results, we found that level of education and marital status were the most important variables to affect knowledge of risk factors for obesity among respondents. The accuracy of correctly classified cases was 95.5%, the same in logistic regression and decision tree. Conclusion. The majority of participants saw regular exercise and diet as an essential way to reduce obesity; however, awareness campaigns should be maintained in order to avoid complacency and combat the disease.