Deep Learning-Based Assessment of Built Environment From Satellite Images and Cardiometabolic Disease Prevalence.

Importance: Built environment plays an important role in development of cardiovascular disease. Large scale, pragmatic evaluation of built environment has been limited owing to scarce data and inconsistent data quality. Objective: To investigate the association between image-based built environment and the prevalence of cardiometabolic disease in urban cities. Design, Setting, and Participants: This cross-sectional study used features extracted from Google satellite images (GSI) to measure the built environment and link them with prevalence of cardiometabolic disease. Convolutional neural networks, light gradient-boosting machines, and activation maps were used to assess the association with health outcomes and identify feature associations with coronary heart disease (CHD), stroke, and chronic kidney disease (CKD). The study obtained aerial images from GSI covering census tracts in 7 cities (Cleveland, Ohio; Fremont, California; Kansas City, Missouri; Detroit, Michigan; Bellevue, Washington; Brownsville, Texas; and Denver, Colorado). The study used census tract-level data from the US Centers for Disease Control and Prevention's 500 Cities project. The data were originally collected from the Behavioral Risk Factor Surveillance System that surveyed people 18 years and older across the country. Analyses were conducted from February to December 2022. Exposures: GSI images of built environment and cardiometabolic disease prevalence. Main Outcomes and Measures: Census tract-level estimated prevalence of CHD, stroke, and CKD based on image-based built environment features. Results: The study obtained 31 786 aerial images from GSI covering 789 census tracts. Built environment features extracted from GSI using machine learning were associated with prevalence of CHD (R2 = 0.60), stroke (R2 = 0.65), and CKD (R2 = 0.64). The model performed better at distinguishing differences between cardiometabolic prevalence between cities than within cities (eg, highest within-city R2 = 0.39 vs between-city R2 = 0.64 for CKD). Addition of GSI features both outperformed and improved the model that only included age, sex, race, income, education, and composite indices for social determinants of health (R2 = 0.83 vs R2 = 0.76 for CHD; P <.001). Activation maps from the features revealed certain health-related built environment such as roads, highways, and railroads and recreational facilities such as amusement parks, arenas, and baseball parks. Conclusions and Relevance: In this cross-sectional study, a significant portion of cardiometabolic disease prevalence was associated with GSI-based built environment using convolutional neural networks.

Mapping Proximity to Infectious Disease Physicians Across the United States.

Enduring shortages of infectious disease physicians across the United States continue despite efforts to mitigate the problem. The recent fellowship match results underscore the difficulty in rectifying that shortage. Our report sheds light on the current geographic distribution of US infectious disease physicians and highlights the challenges faced by rural communities.

County-Level Socio-Environmental Factors Associated With Stroke Mortality in the United States: A Cross-Sectional Study.

We used machine learning methods to explore sociodemographic and environmental determinants of health (SEDH) associated with county-level stroke mortality in the USA. We conducted a cross-sectional analysis of individuals aged ≥15 years who died from all stroke subtypes between 2016 and 2020. We analyzed 54 county-level SEDH possibly associated with age-adjusted stroke mortality rates/100,000 people. Classification and Regression Tree (CART) was used to identify specific county-level clusters associated with stroke mortality. Variable importance was assessed using Random Forest analysis. A total of 501,391 decedents from 2397 counties were included. CART identified 10 clusters, with 77.5% relative increase in stroke mortality rates across the spectrum (28.5 vs 50.7 per 100,000 persons). CART identified 8 SEDH to guide the classification of the county clusters. Including, annual Median Household Income ($), live births with Low Birthweight (%), current adult Smokers (%), adults reporting Severe Housing Problems (%), adequate Access to Exercise (%), adults reporting Physical Inactivity (%), adults with diagnosed Diabetes (%), and adults reporting Excessive Drinking (%). In conclusion, SEDH exposures have a complex relationship with stroke. Machine learning approaches can help deconstruct this relationship and demonstrate associations that allow improved understanding of the socio-environmental drivers of stroke and development of targeted interventions.

Quantifying lead-attributable cardiovascular disease burden in the United States.

Lead exposure has been linked to a myriad of cardiovascular diseases. Utilizing data from the 2019 Global Burden of Disease Study, we quantified age-standardized lead exposure-related mortality and disability-adjusted life years (DALYs) in the United States between 1990 and 2019. Our analysis revealed a substantial reduction in age-standardized cardiovascular disease (CVD) mortality attributable to lead exposure by 60 % (from 7.4 to 2.9 per 100,000), along with a concurrent decrease in age-standardized CVD DALYs by 66 % (from 143.2 to 48.7 per 100,000).

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.

Impact of Residential Social Deprivation on Prediction of Heart Failure in Patients With Type 2 Diabetes: External Validation and Recalibration of the WATCH-DM Score Using Real World Data.

BACKGROUND: Patients with type 2 diabetes are at risk of heart failure hospitalization. As social determinants of health are rarely included in risk models, we validated and recalibrated the WATCH-DM score in a diverse patient-group using their social deprivation index (SDI). METHODS: We identified US Veterans with type 2 diabetes without heart failure that received outpatient care during 2010 at Veterans Affairs medical centers nationwide, linked them to their SDI using residential ZIP codes and grouped them as SDI <20%, 21% to 40%, 41% to 60%, 61% to 80%, and >80% (higher values represent increased deprivation). Accounting for all-cause mortality, we obtained the incidence for heart failure hospitalization at 5 years follow-up; overall and in each SDI group. We evaluated the WATCH-DM score using the C statistic, the Greenwood Nam D'Agostino test χ2 test and calibration plots and further recalibrated the WATCH-DM score for each SDI group using a statistical correction factor. RESULTS: In 1 065 691 studied patients (mean age 67 years, 25% Black and 6% Hispanic patients), the 5-year incidence of heart failure hospitalization was 5.39%. In SDI group 1 (least deprived) and 5 (most deprived), the 5-year heart failure hospitalization was 3.18% and 11%, respectively. The score C statistic was 0.62; WATCH-DM systematically overestimated heart failure risk in SDI groups 1 to 2 (expected/observed ratios, 1.38 and 1.36, respectively) and underestimated the heart failure risk in groups 4 to 5 (expected/observed ratios, 0.95 and 0.80, respectively). Graphical evaluation demonstrated that the recalibration of WATCH-DM using an SDI group-based correction factor improved predictive capabilities as supported by reduction in the χ2 test results (801-27 in SDI groups I; 623-23 in SDI group V). CONCLUSIONS: Including social determinants of health to recalibrate the WATCH-DM score improved risk prediction highlighting the importance of including social determinants in future clinical risk prediction models.

Sex-specific heart failure burden across the United States: Global burden of disease 1990-2019.

BACKGROUND: Heart failure (HF) has unique aspects that vary by biological sex. Thus, understanding sex-specific trends of HF in the US population is crucial to develop targeted interventions. We aimed to analyze the burden of HF in female and male patients across the US, from 1990 to 2019. METHODS: Using the Global Burden of Disease (GBD) study data from 2019, we performed an analysis of the burden of HF from 1990-2019, across US states and regions. The GBD defined HF through studies that used symptom-based criteria and expressed the burden of HF as the age-adjusted prevalence and years lived with disability (YLDs) rates per 100,000 individuals. RESULTS: The age-adjusted prevalence of HF for the US in 2019 was 926.2 (95% UI [799.6, 1,079.0]) for females and 1,291.2 (95% UI [1,104.1, 1,496.8]) for males. Notably, our findings also highlight cyclic fluctuations in HF prevalence over time, with peaks occurring in the mid-1990s and around 2010, while reaching their lowest points in around 2000 and 2018. Among individuals >70 years of age, the absolute number of individuals with HF was higher in females, and this age group doubled the absolute count between 1990 and 2019. Comparing 1990-1994 to 2015-2019, 10 states had increased female HF prevalence, while only 4 states increased male prevalence. Overall, Western states had the greatest relative decline in HF burden, in both sexes. CONCLUSION: The burden of HF in the US is high, although the magnitude of this burden varies according to age, sex, state, and region. There is a significant increase in the absolute number of individuals with HF, especially among women >70 years, expected to continue due to the aging population.

Environmental exposures and blood pressure in adolescents and adults in the T1D exchange clinic registry.

AIMS: To examine the associations between environmental determinants of health and blood pressure and whether age, sex, or race moderated the associations among 18,754 adolescents and adults from the type 1 diabetes (T1D) Exchange Clinic Registry. METHODS: We used multivariable linear regression. Environmental determinants included exposure to ambient fine particulate matter (PM2.5, obtained from an integrated model), nitrogen dioxide (NO2), noise and light pollution, and the normalized difference vegetation index (NDVI, a marker of green space) at the ZIP code level of residence. RESULTS: Higher exposure to PM2.5 and NO2, and lower NDVI, was associated with higher systolic and diastolic blood pressure, and higher light pollution exposure were similarly associated with higher diastolic blood pressure. These associations between environmental exposures and blood pressure remained significant after accounting for other covariates (age, sex, race/ethnicity, BMI, and T1D duration). With aging, the negative association between NDVI and blood pressure weakened. CONCLUSIONS: These findings emphasize the significance of minimizing exposure to environmental pollutants, including PM2.5 and NO2, as well as ensuring access to areas with higher NDVI, to promote cardiovascular health in individuals with T1D.

Historical Neighborhood Redlining and Contemporary Environmental Racism.

To stabilize the housing market during the great depression, the government-sanctioned Home Owners' Loan Corporation (HOLC) created color coded maps of nearly 200 United States cities according to lending risk. These maps were largely driven by racial segregation, with the worst graded neighborhoods colored in red, later termed redlined neighborhoods. We sought to investigate the association between historical redlining, and trends in environmental disparities across the US over the past few decades. We characterized environmental exposures including air pollutants (e.g., NO2 and fine particulate matter), vegetation, noise, and light at night, proximity hazardous emission sources (e.g., hazardous water facilities, wastewater discharge indicator) and other environmental and social indicators harnessed from various sources across HOLC graded neighborhoods and extrapolated census tracts (A [lowest risk neighborhoods] to D [highest risk neighborhoods]). Lower graded areas (C and D) had consistently higher exposures to worse environmental factors. Additionally, there were consistent relative disparities in the exposures to PM2.5 (1981-2018) and NO2 (2005-2019), without significant improvement in the gap compared with HOLC grade A neighborhoods. Our findings illustrate that historical redlining, a form of residential segregation largely based on racial discrimination is associated with environmental injustice over the past 2-4 decades.

Alzheimer`s disease mortality in the United States: Cross-sectional analysis of county-level socio-environmental factors.

BACKGROUND: Geographical disparities in mortality among Alzheimer`s disease (AD) patients have been reported and complex sociodemographic and environmental determinants of health (SEDH) may be contributing to this variation. Therefore, we aimed to explore high-risk SEDH factors possibly associated with all-cause mortality in AD across US counties using machine learning (ML) methods. METHODS: We performed a cross-sectional analysis of individuals ≥65 years with any underlying cause of death but with AD in the multiple causes of death certificate (ICD-10,G30) between 2016 and 2020. Outcomes were defined as age-adjusted all-cause mortality rates (per 100,000 people). We analyzed 50 county-level SEDH and Classification and Regression Trees (CART) was used to identify specific county-level clusters. Random Forest, another ML technique, evaluated variable importance. CART`s performance was validated using a "hold-out" set of counties. RESULTS: Overall, 714,568 individuals with AD died due to any cause across 2,409 counties during 2016-2020. CART identified 9 county clusters associated with an 80.1% relative increase of mortality across the spectrum. Furthermore, 7 SEDH variables were identified by CART to drive the categorization of clusters, including High School Completion (%), annual Particulate Matter 2.5 Level in Air, live births with Low Birthweight (%), Population under 18 years (%), annual Median Household Income in US dollars ($), population with Food Insecurity (%), and houses with Severe Housing Cost Burden (%). CONCLUSION: ML can aid in the assimilation of intricate SEDH exposures associated with mortality among older population with AD, providing opportunities for optimized interventions and resource allocation to reduce mortality among this population.

Association Between Historical Neighborhood Redlining and Cardiovascular Outcomes Among US Veterans With Atherosclerotic Cardiovascular Diseases.

Importance: In the 1930s, the government-sponsored Home Owners' Loan Corporation (HOLC) established maps of US neighborhoods that identified mortgage risk (grade A [green] characterizing lowest-risk neighborhoods in the US through mechanisms that transcend traditional risk factors to grade D [red] characterizing highest risk). This practice led to disinvestments and segregation in neighborhoods considered redlined. Very few studies have targeted whether there is an association between redlining and cardiovascular disease. Objective: To evaluate whether redlining is associated with adverse cardiovascular outcomes in US veterans. Design, Setting, and Participants: In this longitudinal cohort study, US veterans were followed up (January 1, 2016, to December 31, 2019) for a median of 4 years. Data, including self-reported race and ethnicity, were obtained from Veterans Affairs medical centers across the US on individuals receiving care for established atherosclerotic disease (coronary artery disease, peripheral vascular disease, or stroke). Data analysis was performed in June 2022. Exposure: Home Owners' Loan Corporation grade of the census tracts of residence. Main Outcomes and Measures: The first occurrence of major adverse cardiovascular events (MACE), comprising myocardial infarction, stroke, major adverse extremity events, and all-cause mortality. The adjusted association between HOLC grade and adverse outcomes was measured using Cox proportional hazards regression. Competing risks were used to model individual nonfatal components of MACE. Results: Of 79 997 patients (mean [SD] age, 74.46 [10.16] years, female, 2.9%; White, 55.7%; Black, 37.3%; and Hispanic, 5.4%), a total of 7% of the individuals resided in HOLC grade A neighborhoods, 20% in B neighborhoods, 42% in C neighborhoods, and 31% in D neighborhoods. Compared with grade A neighborhoods, patients residing in HOLC grade D (redlined) neighborhoods were more likely to be Black or Hispanic with a higher prevalence of diabetes, heart failure, and chronic kidney disease. There were no associations between HOLC and MACE in unadjusted models. After adjustment for demographic factors, compared with grade A neighborhoods, those residing in redlined neighborhoods had an increased risk of MACE (hazard ratio [HR], 1.139; 95% CI, 1.083-1.198; P < .001) and all-cause mortality (HR, 1.129; 95% CI, 1.072-1.190; P < .001). Similarly, veterans residing in redlined neighborhoods had a higher risk of myocardial infarction (HR, 1.148; 95% CI, 1.011-1.303; P < .001) but not stroke (HR, 0.889; 95% CI, 0.584-1.353; P = .58). Hazard ratios were smaller, but remained significant, after adjustment for risk factors and social vulnerability. Conclusions and Relevance: In this cohort study of US veterans, the findings suggest that those with atherosclerotic cardiovascular disease who reside in historically redlined neighborhoods continue to have a higher prevalence of traditional cardiovascular risk factors and higher cardiovascular risk. Even close to a century after this practice was discontinued, redlining appears to still be adversely associated with adverse cardiovascular events.

The Exposome and Cardiovascular Health.

The study of the interplay between social factors, environmental hazards, and health has garnered much attention in recent years. The term "exposome" was coined to describe the total impact of environmental exposures on an individual's health and well-being, serving as a complementary concept to the genome. Studies have shown a strong correlation between the exposome and cardiovascular health, with various components of the exposome having been implicated in the development and progression of cardiovascular disease. These components include the natural and built environment, air pollution, diet, physical activity, and psychosocial stress, among others. This review provides an overview of the relationship between the exposome and cardiovascular health, highlighting the epidemiologic and mechanistic evidence of environmental exposures on cardiovascular disease. The interplay between various environmental components is discussed, and potential avenues for mitigation are identified.

Geographical Patterns and Risk Factor Association of Cardio-Oncology Mortality in the United States.

Cardio-oncology mortality (COM) is a complex issue that is compounded by multiple factors that transcend a depth of socioeconomic, demographic, and environmental exposures. Although metrics and indexes of vulnerability have been associated with COM, advanced methods are required to account for the intricate intertwining of associations. This cross-sectional study utilized a novel approach that combined machine learning and epidemiology to identify high-risk sociodemographic and environmental factors linked to COM in United States counties. The study consisted of 987,009 decedents from 2,717 counties, and the Classification and Regression Trees model identified 9 county socio-environmental clusters that were closely associated with COM, with a 64.1% relative increase across the spectrum. The most important variables that emerged from this study were teen birth, pre-1960 housing (lead paint indicator), area deprivation index, median household income, number of hospitals, and exposure to particulate matter air pollution. In conclusion, this study provides novel insights into the socio-environmental drivers of COM and highlights the importance of utilizing machine learning approaches to identify high-risk populations and inform targeted interventions for reducing disparities in COM.

Neighbourhood-level social deprivation and the risk of recurrent heart failure hospitalizations in type 2 diabetes.

BACKGROUND: The importance of type 2 diabetes mellitus (T2D) in heart failure hospitalizations (HFH) is acknowledged. As information on the prevalence and influence of social deprivation on HFH is limited, we studied this issue in a racially diverse cohort. METHODS: Linking data from US Veterans with stable T2D (without prevalent HF) with a zip-code derived population-level social deprivation index (SDI), we grouped them according to increasing SDI as follows: SDI: group I: ≤20; II: 21-40; III: 41-60; IV: 61-80; and V (most deprived) 81-100. Over a 10-year follow-up period, we identified the total (first and recurrent) number of HFH episodes for each patient and calculated the age-adjusted HFH rate [per 1000 patient-years (PY)]. We analysed the incident rate ratio between SDI groups and HFH using adjusted analyses. RESULTS: In 1 012 351 patients with T2D (mean age 67.5 years, 75.7% White), the cumulative incidence of first HFH was 9.4% and 14.2% in SDI groups I and V respectively. The 10-year total HFH rate was 54.8 (95% CI: 54.5, 55.2)/1000 PY. Total HFH increased incrementally from SDI group I [43.3 (95% CI: 42.4, 44.2)/1000 PY] to group V [68.6 (95% CI: 67.8, 69.9)/1000 PY]. Compared with group I, group V patients had a 53% higher relative risk of HFH. The negative association between SDI and HFH was stronger in Black patients (SDI × Race pinteraction < .001). CONCLUSIONS: Social deprivation is associated with increased HFH in T2D with a disproportionate influence in Black patients. Strategies to reduce social disparity and equalize racial differences may help to bridge this gap.

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.