Posted By :  Admin1

Researchers, led by Prof. Sadeer Al-Kindi and Prof. Sanjay Rajagopalan from University Hospitals Harrington Heart & Vascular Institute and Case Western Reserve University, Ohio, USA, along with Dr. Zhuo Chen, a post-doctoral fellow in Prof. Rajagopalan's laboratory, have utilized Google Street View to analyze numerous aspects of the built environment. This includes buildings, green spaces, pavements, and roads, examining their interrelation and impact on coronary artery disease among residents in these areas. Published in the European Heart Journal, their findings indicate that these factors can anticipate 63% of the variance in coronary heart disease risk acrossdifferent regions. Coronary heart disease, characterized by the obstruction of blood flow to the heart due to a buildup of fatty substances in the coronary arteries, stands as one of the most prevalent forms of cardiovascular disease. The researchers propose that leveraging Google Street View can offer insights into physical environmental risk factors within both built and natural environments. This understanding could aid in the assessment of risk factors and contribute to the creation or adaptation of urban areas to foster healthier living environments. The study involved analyzing over half a million Google Street View images from cities such as Detroit, Michigan; Kansas City, Missouri; Cleveland, Ohio; Brownsville, Texas; Fremont, California; Bellevue, Washington State; and Denver, Colorado. Researchers also gathered data on coronary heart disease rates based on 'census tracts,' which are smaller areas averaging 4,000 residents each. Using a convolutional neural network, a form of artificial intelligence capable of recognizing patterns in images, the researchers found that features visible in Google Street View images could predict 63% of the variation in coronary heart disease across these small regions of US cities. Prof. Al-Kindi mentioned utilizing attention mapping to highlight crucial regions in the images, offering insight into features like green spaces and walkable roads associated with lower risk, and poorly paved roads linked to higher risk. However, further investigation is warranted. The study demonstrates the potential of computer vision methods in identifying environmental factors impacting cardiovascular risk, with implications for heart-healthy urban planning on a large scale.

Prof. Rajagopalan emphasized the urgent necessity to comprehend urban environments on a large scale, especially with impending challenges like climate change and a demographic shift towards urban living, where nearly 70% of the global population is expected to reside. He advocated for the use of computer vision approaches to provide detailed insights into urban environments at an unprecedented level. In a related editorial, Dr. Rohan Khera from Yale University School of Medicine noted the significance of residential location in determining outcomes, often surpassing biological risk factors. He highlighted the innovative nature of the study by Chen and colleagues, which utilized Google's panoramic street-view imagery to comprehensively evaluate the built environment. Dr. Khera emphasized the importance of employing AI-enhanced methods to study the physical environment's association with cardiovascular health, noting that measures of cardiovascular health are strongly reflected in the visual appearance of neighborhoods. He stressed the critical need to utilize this information effectively to prioritize interventions in vulnerable communities and intensify efforts to enhance cardiovascular health in areas most in need