Cardiometabolic disease, especially hypertension, is a common risk factor for mortality among individuals with SARS-CoV-2 disease (COVID-19). The role of hypertension and vascular disease in COVID-19 has raised considerable debate around how to best manage anti-hypertensive therapy to alter disease trajectory. Given the role of the ACE2 receptor in SARS-CoV-2 viral entry6, angiotensin system modulation by ACE inhibitors (ACE-I) or angiotensin-II receptor blockers (ARBs) in clinical management have taken center stage in this controversy.

Importance: Increased ability to quantify anatomical phenotypes across multiple organs provides the opportunity to assess their cumulative ability to identify individuals at greatest susceptibility for adverse outcomes. Objective: To apply unsupervised machine learning to define the distribution and prognostic importance of computed tomography-based multiorgan phenotypes associated with adverse health outcomes. Design, Setting, and Participants: This asymptomatic community-based cohort study included 2924 Framingham Heart Study participants between July 2002 and April 2005 undergoing computed tomographic imaging of the chest and abdomen. Participants are from the offspring and third-generation cohorts. Exposures: Eleven computed tomography-based measures of valvular/vascular calcification, adiposity, and muscle attenuation. Main Outcomes and Measures: All-cause mortality and cardiovascular disease (myocardial infarction, stroke, or cardiovascular death). Results: The median age of the participants was 50 years (interquartile range, 43-60 years), and 1422 (48.6%) were men. Principal component analysis identified 3 major anatomic axes: (1) global calcification (defined by aortic, thoracic, coronary, and valvular calcification); (2) adiposity (defined by pericardial, visceral, hepatic, and intrathoracic fat); and (3) muscle attenuation that explained 65.7% of the population variation. Principal components showed different evolution with age (continuous increase in global calcification, decrease in muscle attenuation, and U-shaped association with adiposity) but similar patterns in men and women. Using unsupervised clustering approaches in the offspring cohort (n = 1150), we identified a cohort (n = 232; 20.2%) with an unfavorable multiorgan phenotype across all 3 anatomic axes as compared with a favorable multiorgan phenotype. Membership in the unfavorable phenotypic cluster was associated with a greater prevalence of cardiovascular disease risk factors and with increased all-cause mortality (hazard ratio, 2.61; 95% CI, 1.74-3.92; P < .001), independent of coronary artery calcium score, visceral adipose tissue, and 10-year global cardiovascular disease Framingham risk, and it provided improvement in metrics of discrimination and reclassification. Conclusions and Relevance: This proof-of-concept analysis demonstrates that unsupervised machine learning, in an asymptomatic community cohort, identifies an unfavorable multiorgan phenotype associated with adverse health outcomes, especially in elderly American adults. Future investigations in larger populations are required not only to validate the present results, but also to harness clinical, biochemical, imaging, and genetic markers to increase our understanding of healthy cardiovascular aging.

Importance: Modern prevention guidelines substantially increase the number of individuals who are eligible for treatment with statins. Efforts to refine statin eligibility via coronary calcification have been studied in white populations but not, to our knowledge, in large African American populations. Objective: To compare the relative accuracy of US Preventive Services Task Force (USPSTF) and American College of Cardiology/American Heart Association (ACC/AHA) recommendations in identifying African American individuals with subclinical and clinical atherosclerotic cardiovascular disease (ASCVD). Design, Setting, and Participants: In this prospective, community-based study, 2812 African American individuals aged 40 to 75 years without prevalent ASCVD underwent assessment of ASCVD risk. Of these, 1743 participants completed computed tomography. Main Outcomes and Measures: Nonzero coronary artery calcium (CAC) score, abdominal aortic calcium score, and incident ASCVD (ie, myocardial infarction, ischemic stroke, or fatal coronary heart disease). Results: Of the 2812 included participants, the mean (SD) age at baseline was 55.4 (9.4) years, and 1837 (65.3%) were female. The USPSTF guidelines captured 404 of 732 African American individuals (55.2%) with a CAC score greater than 0; the ACC/AHA guidelines identified 507 individuals (69.3%) (risk difference, 14.1%; 95% CI, 11.2-17.0; P < .001). Statin recommendation under both guidelines was associated with a CAC score greater than 0 (odds ratio, 5.1; 95% CI, 4.1-6.3; P < .001). While individuals indicated for statins under both guidelines experienced 9.6 cardiovascular events per 1000 patient-years, those indicated under only ACC/AHA guidelines were at low to intermediate risk (4.1 events per 1000 patient-years). Among individuals who were statin eligible by ACC/AHA guidelines, the 10-year ASCVD incidence per 1000 person-years was 8.1 (95% CI, 5.9-11.1) in the presence of CAC and 3.1 (95% CI, 1.6-5.9) without CAC (P = .02). While statin-eligible individuals by USPSTF guidelines did not have a significantly higher 10-year ASCVD event rate in the presence of CAC, African American individuals not eligible for statins by USPSTF guidelines had a higher ASCVD event rate in the presence of CAC (2.8 per 1000 person-years; 95% CI, 1.5-5.4) relative to without CAC (0.8 per 1000 person-years; 95%, CI 0.3-1.7) (P = .03). Conclusions and Relevance: The USPSTF guidelines focus treatment recommendations on 38% of high-risk African American individuals at the expense of not recommending treatment in nearly 25% of African American individuals eligible for statins by ACC/AHA guidelines with vascular calcification and at low to intermediate ASCVD risk.