Machine learning may help researchers better understand the impact of vertical greenspace and neighborhood features on cardiovascular outcomes, according to a press release from the ACC. In a study presented by Chen et al at the ACC Annual Scientific Session 2024, researchers used machine-learning algorithms and robust segmentation methods to analyze the vertical greenspace and neighborhood features—such as trees, grass, sidewalks, buildings, and sky—of Google Street View images from the residences of nearly 50,000 individuals from northeastern Ohio who participated in a free or low-cost coronary artery calcium test program. After a median follow-up of about 27 months, 2,000 of the participants experienced major adverse cardiovascular events. However, those who resided in areas with more trees and clearer skies as well as those who resided in areas with more sidewalks had a respective 5% and 9% lower risk of major adverse cardiovascular events. Factors such as grass and trees alone were not found to be associated with cardiovascular outcomes. The researchers emphasized that with the use of affordable and publicly available tools, their recent findings may offer valuable insights that allow for the quantification of residential environments and cardiovascular risks as well as earlier and more personalized interventions to prevent major adverse cardiovascular events. “It doesn’t necessarily mean that if we plant more trees or build more sidewalks, we’ll reduce cardiovascular risk, but it … gives us preliminary suggestions and indicators that can help us become aware of ways to change behaviors or neighborhood planning in the future to [potentially] lower cardiovascular risk,” concluded lead study author Zhuo Chen, PhD, a postdoctoral researcher at Case Western Reserve University and the University Hospitals Health System in Cleveland.