(HealthDay News) — The prevalence of coronary heart disease (CHD) is associated with built environment factors, according to a study published online March 28 in the European Heart Journal.
Zhuo Chen, PhD, from the Harrington Heart and Vascular Institute in Cleveland, and colleagues examined the association between machine vision-based built environment, measured using features extracted from Google Street View (GSV), and the prevalence of CHD. Health outcomes were predicted using convolutional neural networks, linear mixed-effects models and activation maps. A total of 0.53 million GSV images covering 789 census tracts in seven US cities were obtained.
The researchers found that 63% of the census tract variation in CHD prevalence was predicted by built environment features extracted from GSV using deep learning. A model that only included census tract-level age, sex, race, income and education or composite indices of social determinants of health was improved with the addition of GSV features. A set of neighborhood features represented by buildings and roads associated with CHD prevalence was revealed by activation maps from the features.
“Our study carries significant implications for the field of health research clinical practice,” the authors write. “Firstly, we have pioneered the utilization of street view features in assessing cardiovascular risk, marking a novel approach that introduces new dimensions to our comprehension of the impact of the built environment on health.”
