Health of the Food Environment Is Associated With Heart Failure Mortality in the United States

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

BACKGROUND AND AIMS

Built environment plays an important role in the development of cardiovascular disease. Tools to evaluate the built environment 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.

Scoping Review of Screening and Assessment Tools for Social Determinants of Health in the Field of Cardiovascular Disease

BACKGROUND

Despite the importance of implementing the concept of social determinants of health (SDOH) in the clinical practice of cardiovascular disease (CVD), the tools available to assess SDOH have not been systematically investigated. We conducted a scoping review for tools to assess SDOH and comprehensively evaluated how these tools could be applied in the field of CVD.

METHODS AND RESULTS

We conducted a systematic literature search of PubMed and Embase databases on July 25, 2023. Studies that evaluated an SDOH screening tool with CVD as an outcome or those that explicitly sampled or included participants based on their having CVD were eligible for inclusion. In addition, studies had to have focused on at least one SDOH domain defined by Healthy People 2030. After screening 1984 articles, 58 articles that evaluated 41 distinct screening tools were selected. Of the 58 articles, 39 (67.2%) targeted populations with CVD, whereas 16 (27.6%) evaluated CVD outcome in non-CVD populations. Three (5.2%) compared SDOH differences between CVD and non-CVD populations. Of 41 screening tools, 24 evaluated multiple SDOH domains and 17 evaluated only 1 domain.

CONCLUSIONS

Our review revealed recent interest in SDOH in the field of CVD, with many useful screening tools that can evaluate SDOH. Future studies are needed to clarify the importance of the intervention in SDOH regarding CVD.

Determinants of Health and Outcomes in Medicare Recipients With Heart Disease: A Population Study

CONTEXT

Heart disease (HD) is a primary cause of mortality and morbidity in the United States. While there is a growing body of evidence demonstrating the contribution of social determinants of health (SDoH) to HD outcomes, the impact of combined or individual SDoH on health-related quality of life (HRQoL) in patients with HD is not well understood.

OBJECTIVES

To analyze the National Health and Aging Trends Study (NHATS) to explore the relationship of SDoH with HRQoL, advance care planning, and treatment preferences in Medicare beneficiaries with HD.

METHODS

The study design was a secondary data analysis using latent class analysis (LCA) and multivariable analysis of NHATS participants with HD, Round 8, that included End of Life Plans and Care questions.

RESULTS

1202 participants, median age 81 years, 57% female, 70% non-Hispanic White, 20% non-Hispanic Black, 10% Other. LCA identified two SDoH risk profiles (low/high), using 12 measures within the NHATS Economic and Social Consequences key concept area. The high-risk SDoH profile participants were more likely to have fair/poor HRQoL, and identify as female, non-White (P < 0.0001); and less likely to have completed advance care planning (P < 0.0001). High-risk SDoH participants were more likely to want life-prolonging treatments (P < 0.0001), however, this association was not significant after adjusting for age, sex, and race (P = 0.344).

CONCLUSION

Higher risk SDoH profiles are associated with reduced HRQoL, reduced advance care planning completion, female sex, and non-White race in a cohort of Medicare beneficiaries. These findings provide opportunities to improve SDoH-related care practices in older patients with HD.

Built Environment Features Obtained from Google Street View Are Associated with Coronary Artery Disease Prevalence: A Deep-Learning Framework

Background

Built environment plays an important role in development of cardiovascular disease. Tools to evaluate the built environment using machine vision and informatic approaches has been limited. We sought to investigate the association between machine vision-based built environment and prevalence of cardiometabolic disease in urban 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 cardiometabolic disease. Convolutional neural networks, light gradient boosting machines and activation maps were utilized to predict health outcomes and identify feature associations with coronary heart disease (CHD). The study obtained 0.53 million GSV images covering 789 census tracts in 7 cities (Cleveland, OH; Fremont, CA; Kansas City, MO; Detroit, MI; Bellevue, WA; Brownsville, TX; and Denver, CO). Analyses were conducted from February 2022 to December 2022. We used census tract-level data from the Centers for Disease Control and Prevention's PLACES dataset. Main outcomes included census tract-level estimated prevalence of CHD based on GSV built environment features.

Results

Built environment features extracted from GSV using deep learning predicted 63% of the census tract variation in CHD prevalence. The ExtraTrees Regressor achieved the best result among all models with the lowest average mean absolute error of 1.11% and Root mean square of error of 1.58. The addition of GSV features outperformed and improved a model that only included census-tract level age, sex, race, income and education. Activation maps from the features revealed a set of neighborhood features represented by buildings and roads associated with CHD prevalence.

Conclusions

In this cross-sectional study, a significant portion of CHD prevalence were explained by GSV-based built environment factors analyzed using deep learning, independent of census tract demographics. Machine vision enabled assessment of the built environment could help play a significant role in designing and improving heart-heathy cities.