How the physical inactivity is affected by social-, economic- and physical-environmental factors: an exploratory study using the machine learning approach

Previous studies have utilized regression models to investigate the impact of environmental factors on physical activity. However, such approaches are inadequate for data-driven analysis seeking identify robust associations from intricate and multi-variable interactions between activity factors. With emergence concept exposome, which encompasses totality exposures, this paper explores machine learning predicting percentage inactivity in U.S. counties, while considering 28 social-, economic-, physical-environmental The aim study is address research gap gain insight into complex exposures Five were tested, performances compared select best classifier further investigation. This used data Behavioral Risk Factor Surveillance System (BRFSS) Centers Disease Control Prevention. mean population all counties was 102,841, below 18 years 22.3%. partial dependence plot indicated that only one feature – bachelor’s degree exhibited a close-to-linear relationship with inactivity. Motor-vehicle crash death rate temperature showed nonlinear non-monotonic relationships predicted