Search

This study identifies and ranks predictors of cardiovascular health at the neighborhood level in the United States. We merged the 500 Cities Data and the 2011-2015 American Community Survey to create a new data set that includes sociodemographic characteristics, health behaviors, prevention measures, and cardiovascular health outcomes for more than 28 000 census tracts in the United States. We used random forest to rank predictors of coronary heart disease and stroke. For coronary heart disease, the top 5 ordered predictors were the prevalence of taking medicine for high blood pressure control, binge drinking, being aged 65 years or older, lack of leisure-time physical activity, and obesity. For stroke, the top 5 ordered predictors were the prevalence of obesity, lack of leisure-time physical activity, taking medicine for high blood pressure, being black, and binge drinking. Machine learning approaches have the potential to inform policy makers on important resource allocation decisions at the neighborhood level.

Background and Purpose: It has been hypothesized that cerebral small vessel disease (SVD) and chronic renal impairment may be part of a multisystem small-vessel disorder, but their association may simply be as a result of shared risk factors (eg, hypertension) rather than to a systemic susceptibility to premature SVD. However, most previous studies were hospital based, most had inadequate adjustment for hypertension, many were confined to patients with lacunar stroke, and none stratified by age., Methods: In a population-based study of transient ischemic attack and ischemic stroke (OXVASC [Oxford Vascular Study]), we evaluated the magnetic resonance imaging markers of cerebral SVD, including lacunes, white matter hyperintensities, cerebral microbleeds, and enlarged perivascular space. We studied the age-specific associations of renal impairment (estimated glomerular filtration rate <60 mL/min per 1.73 m 2 ) and total SVD burden (total SVD score) adjusting for age, sex, vascular risk factors, and premorbid blood pressure (mean blood pressure during 15 years preevent)., Results: Of 1080 consecutive patients, 1028 (95.2%) had complete magnetic resonance imaging protocol and creatinine measured at baseline. Renal impairment was associated with total SVD score (odds ratio [OR], 2.16; 95% confidence interval [CI], 1.69-2.75; P <0.001), but only at age <60 years (<60 years: OR, 3.97; 95% CI, 1.69-9.32; P =0.002; 60-79 years: OR, 1.01; 95% CI, 0.72-1.41; P =0.963; ≥80 years: OR, 0.95; 95% CI, 0.59-1.54; P =0.832). The overall association of renal impairment and total SVD score was also attenuated after adjustment for age, sex, history of hypertension, diabetes mellitus, and premorbid average systolic blood pressure (adjusted OR, 0.76; 95% CI, 0.56-1.02; P =0.067), but the independent association of renal impairment and total SVD score at age <60 years was maintained (adjusted OR, 3.11; 95% CI, 1.21-7.98; P =0.018). Associations of renal impairment and SVD were consistent for each SVD marker at age <60 years but were strongest for cerebral microbleeds (OR, 5.84; 95% CI, 1.45-23.53; P =0.013) and moderate-severe periventricular white matter hyperintensities (OR, 6.28; 95% CI, 1.54-25.63; P =0.010)., Conclusions: The association of renal impairment and cerebral SVD was attenuated with adjustment for shared risk factors at older ages, but remained at younger ages, consistent with a shared susceptibility to premature disease., (© 2018 The Authors.)