Abstract
Previous studies indicate that natural and built environment factors significantly influence health outcomes in older adults. However, most cross-sectional studies exploring the impact of these factors on health fail to quantify the relative importance of each factor. Here, we use the XGBoost machine learning technique with SHAPley Additive exPlanations (SHAP) to rank the importance of built environment factors, natural environmental factors, and sociodemographic factors in shaping older adults’ odds of good self-rated health (SRH), in Shanghai, Guangzhou, and Shenzhen, China. To address self-selection bias in housing choice, older adults living in private housing, who have more freedom to choose residential locations, were distinguished from those living in public or self-built housing. To better interpret the results of XGBoost outcomes and analyse the association between factors and SRH, we used SHAP dependence plots. Results show that both built environment and natural environment factors play important roles in predicting SRH. Four built environment factors (accessibility to public transit stations, points of interest density, road density, and population density) and two natural environment factors (air quality index and surrounding greenness) have considerable predictive power for SRH for both groups. Among these factors, accessibility to public transit stations, road density, and air quality index become less important after controlling for self-selection bias. We also trace potential threshold effects of residential greenness, points of interest density, and road density on decreasing older adults' SRH within certain intervals after controlling for self-selection bias. Findings from this study can support the decision-making of policymakers regarding urban planning, landscape design, and environmental management to improve overall health of older adults.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.