How do neighborhood environments impact adolescent health: a comprehensive study from subjective and objective perspectives using machine learning method

Existing studies have established a linear relationship between urban environments and adolescent health, but the combined impacts of subjective and objective environments on multi-dimensional health status (including physical and mental health) have not been fully explored. Furthermore, while some studies have examined the non-linear relationship between urban environments and adult health, research specifically focusing on adolescents is sparse. Using Kunming, China, as a case study, we employ Random Forest model to examine the non-linear relationship between subjective/objective neighborhood environments and adolescent physical/mental health. The results indicate that the objective environment plays a more significant role in influencing physical and mental health in adolescents. There are generally non-linear correlations and threshold effects between neighborhood environment variables and adolescents' health status. Specifically, the effects of distance to subway station, ratio of traffic safety facilities, and greening view index on adolescent physical and mental health differ. Additionally, subjective environments characterized by community management, community image, and community capital tend to positively influence adolescents' health status. This study provides valuable insights for the planning of healthy communities, environmental interventions, and health promotion in specific dimensions among adolescents.