Understanding cross-data dynamics of individual and social/environmental factors through a public health lens: explainable machine learning approaches.

Introduction: The rising prevalence of obesity has become a public health concern, requiring efficient and comprehensive prevention strategies. Methods: This study innovatively investigated the combined influence of individual and social/environmental factors on obesity within the urban landscape of Seoul, by employing advanced machine learning approaches. We collected 'Community Health Surveys' and credit card usage data to represent individual factors. In parallel, we utilized 'Seoul Open Data' to encapsulate social/environmental factors contributing to obesity. A Random Forest model was used to predict obesity based on individual factors. The model was further subjected to Shapley Additive Explanations (SHAP) algorithms to determine each factor's relative importance in obesity prediction. For social/environmental factors, we used the Geographically Weighted Least Absolute Shrinkage and Selection Operator (GWLASSO) to calculate the regression coefficients. Results: The Random Forest model predicted obesity with an accuracy of >90%. The SHAP revealed diverse influential individual obesity-related factors in each Gu district, although 'self-awareness of obesity', 'weight control experience', and 'high blood pressure experience' were among the top five influential factors across all Gu districts. The GWLASSO indicated variations in regression coefficients between social/environmental factors across different districts. Conclusion: Our findings provide valuable insights for designing targeted obesity prevention programs that integrate different individual and social/environmental factors within the context of urban design, even within the same city. This study enhances the efficient development and application of explainable machine learning in devising urban health strategies. We recommend that each autonomous district consider these differential influential factors in designing their budget plans to tackle obesity effectively.

Analysis of accessibility to emergency rooms by dynamic population from mobile phone data: Geography of social inequity in South Korea.

Accessibility of emergency medical care is one of the crucial factors in evaluating national primary medical care systems. While many studies have focused on this issue, there was a fundamental limit to the measurement of accessibility of emergency rooms, because the commonly used census-based population data are difficult to provide realistic information in terms of time and space. In this study, we evaluated the geographical accessibility of emergency rooms in South Korea by using dynamic population counts from mobile phone data. Such population counts were more accurate and up-to-date because they are obtained by aggregating the number of mobile phone users in a 50-by-50 m grid of a locational field, weighted by stay time. Considering both supply and demand of emergency rooms, the 2-step floating catchment analysis was implemented. As a result, urban areas, including the capital city Seoul, showed lower accessibility to emergency rooms, whereas rural areas recorded higher accessibility. This result was contrary to the results analyzed by us based on census-based population data: higher accessibility in urban areas and lower in rural. This implies that using solely census data for accessibility analysis could lead to certain errors, and adopting mobile-based population data would represent the real-world situations for solving problems of social inequity in primary medical care.