Health and the built environment in United States cities: measuring associations using Google Street View-derived indicators of the built environment

• DOI: 10.1186/s12889-020-8300-1
• Publication Date: 2020-02-12T13:03:00Z
• Authors: Jessica M. Keralis; Mehran Javanmardi; Sahil Khanna; Pallavi Dwivedi; Dina Huang; Tolga Tasdizen; Quynh C. Nguyen
• Keywords: Biostatistics; Level design

The built environment is a structural determinant of health and has been shown to influence expenditures, behaviors, outcomes. Traditional methods assessing characteristics are time-consuming difficult combine or compare. Google Street View (GSV) images represent large, publicly available data source that can be used create indicators the physical with machine learning techniques. aim this study use GSV measure association features health-related behaviors outcomes at census tract level.We computer vision techniques derive from approximately 31 million 7.8 intersections. Associations between derived on census-tract level were assessed using multivariate regression models, controlling for demographic factors socioeconomic position. Statistical significance was α = 0.05 level.Single lane roads associated increased diabetes obesity, while non-single-family home buildings decreased inactivity. greenness prevalence mental distress, as well binge drinking, but obesity. Socioeconomic disadvantage negatively drinking positively all other outcomes.Structural determinants such population health. Our suggests higher levels urban development have mixed effects adds further evidence distress adverse impacts multiple