Assessing greenspace and cardiovascular health through deep-learning analysis of street-view imagery in a cohort of US children
This study assessed the relationship between street-level greenspace and cardiovascular health (CVH) in a cohort of US children using deep learning analysis of street-view imagery. While a higher density of street-view trees was associated with better CVH scores in late adolescence, no significant associations were found longitudinally or cumulatively across different developmental stages. Overall, the findings suggest limited evidence of a connection between greenspace and children's CVH, with potential variations depending on growth stages.
College of Health researcher(s)
Highlights
- We examined associations of greenspace associations with cardiovascular health (CVH) throughout childhood and adolescence.
- Participants in the Project Viva cohort had their CVH scores assessed by Life's Essential 8 algorithm.
- Greenspace exposure, including trees, grass, flowers, and plants, were derived from street-view images.
- Street-view greenspace was not associated with CVH longitudinally.
- Cross-sectionally, street-view trees were protectively associated with CVH at late adolescence.
Abstract
Background
Accurately capturing individuals' experiences with greenspace at ground-level can provide valuable insights into their impact on children's health. However, most previous research has relied on coarse satellite-based measurements.
Methods
We utilized CVH and residential address data from Project Viva, a US-based pre-birth cohort, tracking participants from mid-childhood to late adolescence (2007-21). A deep learning segmentation algorithm was applied to street-view images across the US to estimate % street-view trees, grass, and other greenspace (flowers, field, and plants). Exposure estimates were derived by linking street-view greenspace metrics to 500m of participants' residences during mid-childhood, early and late adolescence. CVH scores (range 0–100; higher indicate better CVH) were calculated using the American Heart Association's Life's Essential 8 algorithm at these three time points, incorporating four biomedical components (body weight, blood lipids, blood glucose, blood pressure) and four behavioral components (diet, physical activity, nicotine exposure, sleep). Linear regression models were used to examine cross-sectional and cumulative associations between street-view greenspace metrics and CVH scores. Generalized estimating equations models were used to examine associations between street-view greenspace metrics and changes in CVH scores across three timepoints. All models were adjusted for individual and neighborhood-level confounders.
Results
Adjusting for confounders, a one-SD increase in street-view trees within 500m of residence was cross-sectionally associated with a 1.92-point (95%CI: 0.50, 3.35) higher CVH score in late adolescence, but not mid-childhood or early adolescence. Longitudinally, street-view greenspace metrics at baseline (either mid-childhood or early adolescence) were not associated with changes in CVH scores at the same and all subsequent time points. Cumulative street-view greenspace metrics across the three time points were also not associated with CVH scores in late adolescence.
Conclusion and Relevance
In this US cohort of children, we observed few evidence of associations between street-level greenspace children's CVH, though the impact may vary with children's growth stage.
Greenspace and Cardiovascular Health in Children: FAQ
What is cardiovascular health (CVH) and why is it important for children?
Cardiovascular health (CVH) refers to the well-being of the heart and blood vessels. It's crucial for children because good CVH in childhood is linked to better CVH in adulthood, lowering the risk of cardiovascular diseases and promoting overall well-being throughout life.
How was CVH measured in this study?
This study used the American Heart Association's "Life's Essential 8" (LE8) score to assess CVH. This score incorporates four behavioral factors (sleep, physical activity, diet, and nicotine exposure) and four biomedical factors (blood lipids, blood glucose, body mass index (BMI), and blood pressure), each scored from 0 to 100. A higher overall LE8 score indicates better CVH.
What type of greenspace data did the study use and why?
The study utilized street-view imagery and a deep learning algorithm to analyze specific types of greenspace (trees, grass, and other vegetation like flowers and plants) within a certain radius of participants' homes. This approach provides a more detailed and ground-level understanding of the greenspace children are exposed to compared to traditional satellite-based measures.
What were the main findings of the study regarding greenspace and CVH?
The study found no significant overall associations between street-view greenspace and CVH across mid-childhood, early adolescence, and late adolescence. However, a positive association was observed between street-view trees and CVH scores in late adolescence, particularly the biomedical components of the score (BMI, blood glucose, blood lipids, and blood pressure).
Were there any differences in the associations based on race and ethnicity or neighborhood socioeconomic status (SES)?
Yes, the study found some evidence that the association between street-view trees and CVH scores was more pronounced among non-Hispanic White participants in early adolescence and among children living in higher SES neighborhoods during mid-childhood.
What are the potential implications of these findings?
The findings suggest that specific types of greenspace, like trees, might play a role in promoting CVH in late adolescence. However, more research is needed to understand the complex interplay between greenspace, individual factors, and CVH across different life stages.
What are the limitations of the study?
The study had limitations including a relatively small sample size and the inherent limitations of street-view imagery, which captures only a snapshot in time and may not represent all the places where children spend their time. Further research is needed to confirm these findings and explore potential causal relationships.
What are the next steps for research in this area?
Future studies could investigate the mechanisms by which greenspace may impact CVH in children, considering factors like air quality, physical activity opportunities, and psychological well-being. Larger, more diverse studies are also needed to confirm these findings and understand the influence of individual and neighborhood characteristics.