Artificial intelligence–based assessment of built environment from Google Street View and coronary artery disease prevalence

Abstract

Background and Built environment plays an important role in the development of cardiovascular disease. Tools to evaluate the built envirAims onment using machine vision and informatic approaches have been limited. This study aimed to investigate the association between machine vision–based built environment and prevalence of cardiometabolic disease in US cities. Methods This cross-sectional study used features extracted from Google Street View (GSV) images to measure the built environment and link them with prevalence of coronary heart disease (CHD). Convolutional neural networks, linear mixed-effects models, and activation maps were utilized to predict health outcomes and identify feature associations with CHD at the census tract level. The study obtained 0.53 million GSV images covering 789 census tracts in seven US cities (Cleveland, OH; Fremont, CA; Kansas City, MO; Detroit, MI; Bellevue, WA; Brownsville, TX; and Denver, CO). Results Built environment features extracted from GSV using deep learning predicted 63% of the census tract variation in CHD prevalence. The addition of GSV features improved a model that only included census tract-level age, sex, race, income, and education or composite indices of social determinant of health. Activation maps from the features revealed a set of neighbourhood features represented by buildings and roads associated with CHD prevalence. Conclusions In this cross-sectional study, the prevalence of CHD was associated with built environment factors derived from GSV through deep learning analysis, independent of census tract demographics. Machine vision–enabled assessment of the built environment could potentially offer a more precise approach to identify at-risk neighbourhoods, thereby providing an efficient avenue to address and reduce cardiovascular health disparities in urban environments. Structured Graphical Abstract Key Question Is a deep learning-based assessment of the built environment from street view images associated with coronary heart disease (CHD) prevalence at the census tract level in the United States? Key Finding Google Street View (GSV) images of seven US cities were associated with 63% of the variance in prevalence of CHD. Compared with a model including age, sex, race, income, education, and composite indices for social determinants of health, addition of GSV features enhanced the association with CHD. Take Home Message Neighborhood characteristics derived from street view imagery are significantly associated with more than 60% of the regional variability in cardiovascular disease. This suggests that further exploring GSV-based cardiometabolic risk estimation is warranted. Street view images in neighborhoods Built environment features extraction with distinct CHD prevalence with convolutional neural networks Visualization of deep learning features Features associated with CHD prevalence compared on original street view images to demographic and socio-economic factors LMEM R2 Log. model AIC BIC Marg. Cond. Lik. Test LRT p value DSE+GSV 632.0 697.0 0.760 0.792 -308.0 DSE 706.0 743.0 0.645 0.738 -368.0 DSE+GSV vs. DSE 120