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.

Trends in tracheal, bronchial and lung cancer attributed to smoking in South America: Global Burden of Disease analysis 1990-2019.

Objective: To investigate the burden of tracheal, bronchus, and lung (TBL) cancer due to tobacco exposure in the last 30 years in 12 South American countries. Methods: We used the Global Burden of Disease (GBD) 2019 exposure-response function to analyze the total tobacco, smoking, and secondhand smoke exposure-related TBL cancer deaths and disability-adjusted life years (DALYs), for 12 South American countries, between 1990 and 2019. Metrics were described as absolute numbers or rates per 100 000 individuals. The relative change in burden was assessed by comparing the 1990-1994 to 2015-2019 periods. Results: In 2019, the all-ages number of TBL cancer deaths and DALYs associated with tobacco exposure in South America was 29 348 and 658 204 in males and 14 106 and 318 277 in females, respectively. Age-adjusted death and DALYs rates for the region in 2019 were 182.8 and 4035 in males and 50.8 and 1162 in females, respectively. In males, 10/12 countries observed relative declines in TBL death rates attributed to tobacco exposure while only 4 countries reduced their mortality in females. Conclusion: While significant efforts on tobacco control are under place in South America, substantial burden of TBL cancer persists in the region with significant sex-specific disparities. Increased country-specific primary data on TBL cancer and tobacco exposure is needed to optimize healthcare strategies and improve comprehension of regional trends.

Environmental Exposome and Atrial Fibrillation: Emerging Evidence and Future Directions.

There has been increased awareness of the linkage between environmental exposures and cardiovascular health and disease. Atrial fibrillation is the most common sustained cardiac arrhythmia, affecting millions of people worldwide and contributing to substantial morbidity and mortality. Although numerous studies have explored the role of genetic and lifestyle factors in the development and progression of atrial fibrillation, the potential impact of environmental determinants on this prevalent condition has received comparatively less attention. This review aims to provide a comprehensive overview of the current evidence on environmental determinants of atrial fibrillation, encompassing factors such as air pollution, temperature, humidity, and other meteorologic conditions, noise pollution, greenspace, and the social environment. We discuss the existing evidence from epidemiological and mechanistic studies, critically evaluating the strengths and limitations of these investigations and the potential underlying biological mechanisms through which environmental exposures may affect atrial fibrillation risk. Furthermore, we address the potential implications of these findings for public health and clinical practice and identify knowledge gaps and future research directions in this emerging field.

Trends in tracheal, bronchial and lung cancer attributed to smoking in South America: Global Burden of Disease analysis 1990-2019

[ABSTRACT]. Objective. To investigate the burden of tracheal, bronchus, and lung (TBL) cancer due to tobacco exposure in the last 30 years in 12 South American countries. Methods. We used the Global Burden of Disease (GBD) 2019 exposure-response function to analyze the total tobacco, smoking, and secondhand smoke exposure-related TBL cancer deaths and disability-adjusted life years (DALYs), for 12 South American countries, between 1990 and 2019. Metrics were described as abso- lute numbers or rates per 100 000 individuals. The relative change in burden was assessed by comparing the 1990-1994 to 2015-2019 periods. Results. In 2019, the all-ages number of TBL cancer deaths and DALYs associated with tobacco expo- sure in South America was 29 348 and 658 204 in males and 14 106 and 318 277 in females, respectively. Age-adjusted death and DALYs rates for the region in 2019 were 182.8 and 4035 in males and 50.8 and 1162 in females, respectively. In males, 10/12 countries observed relative declines in TBL death rates attributed to tobacco exposure while only 4 countries reduced their mortality in females. Conclusion. While significant efforts on tobacco control are under place in South America, substantial bur- den of TBL cancer persists in the region with significant sex-specific disparities. Increased country-specific primary data on TBL cancer and tobacco exposure is needed to optimize healthcare strategies and improve comprehension of regional trends.

[RESUMEN]. Objetivo. Investigar la carga del cáncer de tráquea, bronquios y pulmón por exposición al tabaco en los últi- mos 30 años en 12 países de Sudamérica. Métodos. Se utilizó la función de relación entre exposición y respuesta de la carga mundial de morbilidad del 2019 para analizar las muertes por cáncer de tráquea, bronquios y pulmón asociadas a la exposición total al tabaco, al tabaquismo activo y al tabaquismo pasivo, así como los años de vida ajustados en función de la discapacidad (AVAD), en 12 países de Sudamérica, entre 1990 y el 2019. Los resultados se presentaron en forma de número absoluto o de tasa por 100 000 personas. Se evaluó el cambio relativo de la carga mediante la comparación de los períodos 1990-1994 y 2015-2019. Resultados. En el 2019, el número de muertes por cáncer de tráquea, bronquios y pulmón y los AVAD aso- ciados a la exposición al tabaco para todas las edades en Sudamérica fueron de 29 348 y 658 204 en los hombres y de 14 106 y 318 277 en las mujeres, respectivamente. La tasa de mortalidad y los AVAD ajustados por la edad correspondientes al 2019 en la región fueron de 182,8 y 4035 en los hombres y de 50,8 y 1162 en las mujeres, respectivamente. En el caso de los hombres, en 10 de los 12 países se observaron disminuciones relativas de la tasa de mortalidad por cáncer de tráquea, bronquios y pulmón atribuido a la exposición al tabaco, mientras que en el caso de las mujeres solo en 4 países hubo una reducción de la mortalidad. Conclusión. Aunque en Sudamérica se están llevando a cabo iniciativas importantes para el control del tabaco, en esta región persiste una carga considerable de cáncer de tráquea, bronquios y pulmón, con diferencias significativas en función del sexo. Es preciso contar con más datos primarios específicos de cada país sobre el cáncer de tráquea, bronquios y pulmón, así como sobre la exposición al tabaco, para optimizar las estrategias de atención de salud y mejorar la comprensión de las tendencias regionales.

[RESUMO]. Objetivo. Investigar a carga de câncer de traqueia, brônquios e pulmão (TBP) decorrente da exposição ao tabaco nos últimos 30 anos em 12 países da América do Sul. Métodos. A função de exposição-resposta do estudo Carga Global de Doença (GBD, na sigla em inglês) 2019 foi usada para analisar o número de mortes e de anos de vida ajustados por incapacidade (AVAI) por câncer de TBP relacionado à exposição total ao tabaco e ao tabagismo e ao fumo passivo em 12 países da América do Sul entre 1990 e 2019. Os índices foram descritos em números absolutos ou taxas por 100 mil pessoas. A variação relativa da carga foi avaliada comparando-se os períodos de 1990 a 1994 e de 2015 a 2019. Resultados. Em 2019, os números de mortes e de AVAI por câncer de TBP associado à exposição ao tabaco na América do Sul, em todas as idades, foram, respectivamente, 29.348 e 658.204 em homens e 14.106 e 318.277 em mulheres. As taxas de mortalidade e os AVAI ajustados por idade na região foram, respecti- vamente, 182,8 e 4.035 em homens e 50,8 e 1.162 em mulheres em 2019. Em homens, 10 dos 12 países registraram uma diminuição relativa das taxas de mortalidade por câncer de TBP atribuído à exposição ao tabaco, mas somente 4 países obtiveram uma redução da mortalidade em mulheres. Conclusão. Apesar dos consideráveis esforços atuais para o controle do tabaco na América do Sul, ainda há uma expressiva carga de câncer de TBP na região, com disparidades significativas entre os sexos. É necessário dispor de mais dados primários sobre câncer de TBP e exposição ao tabaco específicos para cada país para aprimorar as estratégias de atenção à saúde e melhorar a compreensão das tendências regionais.

Second-year results from CINEMA: A novel, patient-centered, team-based intervention for patients with Type 2 diabetes or prediabetes at high cardiovascular risk.

Background: The care for patients with type 2 diabetes mellitus (T2DM) necessitates a multidisciplinary team approach to reduce cardiovascular (CV) risk but implementation of effective integrated strategies has been limited. Methods and Results: We report 2-year results from a patient-centered, team-based intervention called CINEMA at University Hospitals Cleveland Medical Center. Patients with T2DM or prediabetes at high-risk for CV events, including those with established atherosclerotic CVD, elevated coronary artery calcium score ≥100, chronic heart failure with reduced ejection fraction, chronic kidney disease (CKD) stages 2-4, and/or prevalent metabolic syndrome were included. From May 2020 through September 2022, 426 patients were enrolled in the CINEMA program. A total of 227 (54%) completed ≥1 follow-up visit after an initial baseline visit with median (IQR) follow-up time 4 [3], [4], [5], [6], [7] months with maximum follow-up time 19 months. Mean age was 60 years, 47 % were women, and 37 % were Black and 85% had prevalent T2DM, 48 % had established ASCVD, 29% had chronic HF, 27% had CKD and mean baseline 10-year ASCVD risk estimate was 25.1 %; baseline use of a SGLT2i or GLP-1RA was 21 % and 18 %, respectively. Patients had significant reductions from baseline in body weight (-5.5 lbs), body mass index (-0.9 kg/m2), systolic (-3.6 mmHg) and diastolic (-1.2 mmHg) blood pressure, Hb A1c (-0.5 %), total (-10.7 mg/dL) and low-density lipoprotein (-9.0 mg/dL) cholesterol, and triglycerides (-13.5 mg/dL) (p<0.05 for all). Absolute 10-year predicted ASCVD risk decreased by ∼2.4 % (p<0.001) with the intervention. In addition, rates of guideline-directed cardiometabolic medication prescriptions significantly increased during follow-up with the most substantive changes seen in rates of SGLT2i and GLP-1RA use which approximately tripled from baseline (21 % to 57 % for SGLT2i and 18 % to 65 % for GLP-1RA, p<0.001 for both). Conclusions: The CINEMA program, an integrated, patient-centered, team-based intervention for patients with T2DM or prediabetes at high risk for cardiovascular disease has continued to demonstrate effectiveness with significant improvements in ASCVD risk factors and improved use of evidence-based therapies. Successful implementation and dissemination of this care delivery paradigm remains a key priority.

Social disadvantage, coronary artery calcium, and their interplay in the prediction of atherosclerotic cardiovascular disease events.

BACKGROUND AND AIMS: Social determinants of health (SDOH) are key for the identification of populations at increased risk of atherosclerotic cardiovascular disease (ASCVD). However, whether at the individual level SDOH improve current ASCVD risk prediction paradigms beyond traditional risk factors and the coronary artery calcium (CAC) score, is unknown. We evaluated the interplay between CAC and SDOH in ASCVD risk prediction. METHODS: MESA is a prospective study of US adults free of clinical ASCVD at baseline. We used an SDOH index inclusive of 14 determinants from 5 domains. The index ranged 0-1 and was divided into quartiles, with higher ones representing worse SDOH. Cox regression was used to evaluate the adjusted associations between CAC, SDOH, their interplay, and ASCVD events. The C-statistic was computed to assess improvement in risk discrimination for prediction of ASCVD events. RESULTS: We included 6479 MESA participants (50% with CAC = 0, 24% CAC>100). ASCVD incidence increased with increasing CAC scores across SDOH quartiles. The lowest incidence was noted in those with CAC = 0 and favourable SDOH (2/1000 person-years) and highest in those with CAC>100 and most unfavourable SDOH (20.6/1000 person-years). While CAC was strongly associated with ASCVD across SDOH quartiles, SDOH was weakly associated with ASCVD across CAC strata. CAC improved the discriminatory ability of all prediction models beyond traditional risk factors, the improvement in C-statistic ranging +0.02 - +0.05. Improvements with SDOH were smaller, and were none on top of CAC. CONCLUSIONS: CAC improves ASCVD risk stratification across the spectrum of social vulnerability, while SDOH fail to improve risk prediction beyond traditional RFs and CAC.

Social Vulnerability and Cardiovascular-Related Mortality Among Older Adults in the United States.

PURPOSE: The association of social vulnerability and cardiovascular disease-related mortality in older adults has not been well characterized. METHODS: The Centers for Disease Control and Prevention database was evaluated to examine the relationship between county-level Social Vulnerability Index (SVI) and age-adjusted cardiovascular disease-related mortality rates (AAMRs) in adults aged 65 and above in the United States between 2016 and 2020. RESULTS: A total of 3139 counties in the United States were analyzed. Cardiovascular disease-related AAMRs increased in a stepwise manner from first (least vulnerable) to fourth SVI quartiles; (AAMR of 2423, 95% CI [confidence interval] 2417-2428; 2433, 95% CI 2429-2437; 2516, 95% CI 2513-2520; 2660, 95% CI 2657-2664). Similar trends among AAMRs were noted based on sex, all race and ethnicity categories, and among urban and rural regions. Higher AAMR ratios between the highest and lowest SVI quartiles, implying greater relative associations of SVI on mortality rates, were seen among Hispanic individuals (1.52, 95% CI 1.49-1.55), Non-Hispanic-Asian and Pacific Islander individuals (1.32, 95% CI 1.29-1.52), Non-Hispanic- American Indian or Alaskan Native individuals (1.43, 95% CI 1.37-1.50), and rural counties (1.21, 95% CI 1.20-1.21). CONCLUSION: Social vulnerability as measures by the SVI was associated with cardiovascular disease-related mortality in older adults, with the association being particularly prominent in ethnic minority patients and rural counties.

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.

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.

Cardiac Structure and Function and Subsequent Kidney Disease Progression in Adults With CKD: The Chronic Renal Insufficiency Cohort (CRIC) Study.

RATIONALE & OBJECTIVE: Heart-kidney crosstalk is recognized as the cardiorenal syndrome. We examined the association of cardiac function and structure with the risk of kidney failure with replacement therapy (KFRT) in a chronic kidney disease (CKD) population. STUDY DESIGN: Prospective observational cohort study. SETTING & PARTICIPANTS: 3,027 participants from the Chronic Renal Insufficiency Cohort Study. EXPOSURE: Five preselected variables that assess different aspects of cardiac structure and function: left ventricular mass index (LVMI), LV volume, left atrial (LA) area, peak tricuspid regurgitation (TR) velocity, and left ventricular ejection fraction (EF) as assessed by echocardiography. OUTCOME: Incident KFRT (primary outcome), and annual estimated glomerular filtration rate (eGFR) slope (secondary outcome). ANALYTICAL APPROACH: Multivariable Cox models and mixed-effects models. RESULTS: The mean age of the participants was 59±11 SD years, 54% were men, and mean eGFR was 43±17mL/min/1.73m2. Between 2003 and 2018 (median follow-up, 9.9 years), 883 participants developed KFRT. Higher LVMI, LV volume, LA area, peak TR velocity, and lower EF were each statistically significantly associated with an increased risk of KFRT, with corresponding HRs for the highest versus lowest quartiles (lowest vs highest for EF) of 1.70 (95% CI, 1.27-2.26), 1.50 (95% CI, 1.19-1.90), 1.43 (95% CI, 1.11-1.84), 1.45 (95% CI, 1.06-1.96), and 1.26 (95% CI, 1.03-1.56), respectively. For the secondary outcome, participants in the highest versus lowest quartiles (lowest vs highest for EF) had a statistically significantly faster eGFR decline, except for LA area (ΔeGFR slope per year, -0.57 [95% CI, -0.68 to-0.46] mL/min/1.73m2 for LVMI, -0.25 [95% CI, -0.35 to-0.15] mL/min/1.73m2 for LV volume, -0.01 [95% CI, -0.12 to-0.01] mL/min/1.73m2 for LA area, -0.42 [95% CI, -0.56 to-0.28] mL/min/1.73m2 for peak TR velocity, and -0.11 [95% CI, -0.20 to-0.01] mL/min/1.73m2 for EF, respectively). LIMITATIONS: The possibility of residual confounding. CONCLUSIONS: Multiple aspects of cardiac structure and function were statistically significantly associated with the risk of KFRT. These findings suggest that cardiac abnormalities and incidence of KFRT are potentially on the same causal pathway related to the interaction between hypertension, heart failure, and coronary artery diseases. PLAIN-LANGUAGE SUMMARY: Heart disease and kidney disease are known to interact with each other. In this study, we examined whether cardiac abnormalities, as assessed by echocardiography, were linked to the subsequent progression of kidney disease among people living with chronic kidney disease (CKD). We found that people with abnormalities in heart structure and function had a greater risk of progression to advanced CKD that required kidney replacement therapy and had a faster rate of decline in kidney function. Our study indicates the potential role of abnormal heart structure and function in the progression of kidney disease among people living with CKD.

Coronary artery calcium, hepatic steatosis, and atherosclerotic cardiovascular disease risk in patients with type 2 diabetes mellitus: Results from the Dallas heart study.

INTRODUCTION: Cardiovascular disease (CVD) risk amongst those with type 2 diabetes (T2D) is heterogenous. The role of imaging-based cardiometabolic biomarkers (e.g., coronary artery calcium [CAC] score, and hepatic triglyceride content [HTC]) in CVD risk stratification in T2D is unclear. To better understand this, we sought to evaluate the individual and joint associations between CAC and hepatic steatosis (HS) with clinical atherosclerotic CVD (ASCVD) in Dallas Heart Study (DHS) participants with and without T2D. METHODS: We examined participants in the DHS, a multi-ethnic cohort study, without self-reported ASCVD. CAC scoring was performed via computed tomography with the mean of two consecutive scores used. HTC was measured using magnetic resonance spectroscopy, and HS was defined as HTC >5.5% The primary outcome was incident ASCVD, defined as coronary heart disease (CHD; myocardial infarction, percutaneous coronary intervention, or coronary artery bypass graft surgery), ischemic stroke, transient ischemic attack, or CVD death. Cox regression analyses, and interaction testing was performed to evaluate the individual and joint associations between CAC and HS with ASCVD. The association between HS and coronary heart disease was validated in the UK Biobank (UKB). RESULTS: A total of 1252 DHS participants were included with mean age 44.8 ± 9.3 years, mean body mass index 28.7 ± 5.9 kg/m2, 55% female, and 59% black with an overall prevalence of T2D of 9.7%. CAC scores were significantly higher (p < 0.01) and HS was significantly more prevalent in those with T2D (p < 0.01). Over a median of 12.3 years, 8.3% of participants experienced ASCVD events. The ASCVD event rate was significantly higher in participants with T2D (20.5% vs 7.0%, p < 0.01). Continuous CAC was associated with ASCVD events in the overall cohort regardless of T2D status with a significant interaction present between CAC and T2D status on ASCVD, Pinteraction = 0.02. HTC was not associated with ASCVD risk in participants without T2D but was inversely associated with risk in participants with T2D (HR 0.91, 95% CI 0.83-0.99 per 1% increase in HTC, p = 0.02), Pinteraction = 0.02. Amongst 37,266 UKB participants, 4.5% had T2D. CHD events occurred in 2.2% of participants, with 10.2% of events occurring amongst those with T2D. An inverse relationship between HTC and CHD was also found amongst those with T2D in UKB with a significant interaction between T2D status and HTC on CHD (HR per 1% increase in HTC 0.95, 95% CI 0.91-0.99, p = 0.01, Pinteraction = 0.02). CONCLUSIONS: In the DHS, we found that CAC was associated with ASCVD risk independent of T2D status. We did not observe an association between HTC and ASCVD in participants without T2D, but there was an inverse association between HTC and ASCVD in those with T2D that was replicated in the UKB cohort. Further investigation is warranted to understand the possible protective association of HS in participants with T2D.

Characteristics and outcomes in acute myocardial infarction hospitalizations among the older population (age ≥80 years) in the United States, 2004-2018.

IMPORTANCE: Acute myocardial infarction (AMI) is a major health concern among older adults (≥80 years). We analyzed a US national database to evaluate the clinical outcomes, resource utilization, and economic burden of AMI hospitalizations in older patients. METHODS AND RESULTS: We analyzed the National Inpatient Sample data between January 2004 and December 2018. We examined the trends of clinical characteristics, inpatient mortality, and healthcare cost utilization in older US adults for AMI hospitalizations. We identified 2,174,587 weighted AMI hospitalizations. There was a decrease in AMI hospitalizations per 100,000 older US adults from 1,679 in 2004 to 1036 in 2018, with a more profound decrease in ST-elevation myocardial infarction (STEMI). We noted an overall increase in comorbidities (hypertension, heart failure, dyslipidemia, atrial fibrillation, diabetes, peripheral vascular disease). Overall, inpatient mortality was 10.6%; adjusted inpatient mortality decreased from 14% in 2004 to 8% in 2018 (p trend <0.001)- consistent across sexes and races. There was increased percutaneous intervention (PCI) utilization [19.3% (2004-2008) to 24.0% (2014-2018)] with a concomitant increase in bleeding and acute kidney injury (AKI). Black adults and women underwent revascularization less frequently than White adults and men. White patients had higher inpatient mortality compared to black patients. There was a decrease in adjusted mean length of stay (LOS) from 6.2 days in 2004 to 3.9 days in 2018 (p trend <0.001). There was an increase in discharge disposition to home with a concomitant decrease in utilization of rehabilitation facilities at discharge. CONCLUSION: Our study showed that the inpatient mortality and LOS has decreased for AMI hospitalizations in the older patient population in the US. While utilization of revascularization strategies has increased, sex and racial disparities exist in the utilization of PCI.

Risk factors and geographic disparities in premature cardiovascular mortality in US counties: a machine learning approach.

Disparities in premature cardiovascular mortality (PCVM) have been associated with socioeconomic, behavioral, and environmental risk factors. Understanding the "phenotypes", or combinations of characteristics associated with the highest risk of PCVM, and the geographic distributions of these phenotypes is critical to targeting PCVM interventions. This study applied the classification and regression tree (CART) to identify county phenotypes of PCVM and geographic information systems to examine the distributions of identified phenotypes. Random forest analysis was applied to evaluate the relative importance of risk factors associated with PCVM. The CART analysis identified seven county phenotypes of PCVM, where high-risk phenotypes were characterized by having greater percentages of people with lower income, higher physical inactivity, and higher food insecurity. These high-risk phenotypes were mostly concentrated in the Black Belt of the American South and the Appalachian region. The random forest analysis identified additional important risk factors associated with PCVM, including broadband access, smoking, receipt of Supplemental Nutrition Assistance Program benefits, and educational attainment. Our study demonstrates the use of machine learning approaches in characterizing community-level phenotypes of PCVM. Interventions to reduce PCVM should be tailored according to these phenotypes in corresponding geographic areas.