Impact of Sleep Patterns on Obesity: A Machine Learning Approach Using Sleep Health and Lifestyle Dataset

Abstract

The escalating global prevalence of obesity remains a critical public health issue. While traditional research often focuses on diet and exercise, the significant impact of sleep duration and quality is increasingly recognized, particularly with advancements in health monitoring and data collection. This study leverages the publicly available 2022 Sleep Health and Lifestyle dataset to investigate the relationship between sleep patterns and obesity. Employing contemporary machine learning techniques such as Decision Tree, Random Forest, and Logistic Regression, we identify and evaluate predictive patterns. Our findings highlight strong correlations between sleep duration and BMI category, with the Decision Tree model achieving a notable classification accuracy of 87%. This demonstrates the growing utility of machine learning in uncovering subtle but crucial health associations from lifestyle data, offering actionable insights for public health initiatives.