Coronary artery calcium is an accurate predictor of cardiovascular events. While it is visible on all computed tomography (CT) scans of the chest, this information is not routinely quantified as it requires expertise, time, and specialized equipment. Here, we show a robust and time-efficient deep learning system to automatically quantify coronary calcium on routine cardiac-gated and non-gated CT. As we evaluate in 20,084 individuals from distinct asymptomatic (Framingham Heart Study, NLST) and stable and acute chest pain (PROMISE, ROMICAT-II) cohorts, the automated score is a strong predictor of cardiovascular events, independent of risk factors (multivariable-adjusted hazard ratios up to 4.3), shows high correlation with manual quantification, and robust test-retest reliability. Our results demonstrate the clinical value of a deep learning system for the automated prediction of cardiovascular events. Implementation into clinical practice would address the unmet need of automating proven imaging biomarkers to guide management and improve population health.

Uptake of pre-exposure prophylaxis (PrEP) among Black women living in the US is suboptimal. We sought to determine the association between HIV conspiracy beliefs (HIV-related medical mistrust) and willingness to use PrEP among Black women. We analyzed data from the 2016 National Survey on HIV in the Black Community (NSHBC), a nationally representative crosssectional survey. Among NSHBC participants, 522 were women and 347(66.5%) reported expanded PrEP indications. Only 14.1% were aware that PrEP exists; 30.8% reported willingness to use PrEP. HIV-related medical mistrust was reported by 60.4% of women. In multivariable analysis, controlling for income, education, marital status and health care engagement, belief in conspiracy theories was significantly associated with higher willingness to use PrEP. The conspiracy scale item: "there is a cure for HIV, but the government is withholding it from the poor" was independently associated with PrEP willingness. This finding speaks to the need for an improved understanding of the role of HIV-related medical mistrust among Black women to improve uptake of biomedical HIV prevention. KeywordsHIV and women; women and pre-exposure prophylaxis; mistrust and PrEP; HIV conspiracy theories; HIV-related medical mistrust and PrEP; Black women and PrEP; African-American women and PrEP

Background Men and women are labeled as obese on the basis of a body mass index (BMI) using the same criterion despite known differences in their fat distributions. Subcutaneous adipose tissue and visceral adipose tissue (VAT), as measured by computed tomography, are advanced measures of obesity that closely correlate with cardiometabolic risk independent of BMI. However, it remains unknown whether prognostic significance of anthropometric measures of adiposity versus VAT varies in men versus women. Methods and Results In 3482 FHS (Framingham Heart Study) participants (48.1% women; mean age, 50.8±10.3 years), we tested the associations of computed tomography–based versus anthropometric measures of fat with cardiometabolic and cardiovascular disease (CVD) risk. Mean follow‐up was 12.7±2.1 years. In men, VAT, as compared with BMI, had a similar strength of association with incident cardiometabolic risk factors (eg, adjusted odds ratio [OR], 2.36 [95% CI, 1.84–3.04] versus 2.66 [95% CI, 2.04–3.47] for diabetes mellitus) and CVD events (eg, adjusted hazard ratio [HR], 1.32 [95% CI, 0.97–1.80] versus 1.74 [95% CI, 1.14–2.65] for CVD death). In women, however, VAT, when compared with BMI, conferred a markedly greater association with incident cardiometabolic risk factors (eg, adjusted OR, 4.51 [95% CI, 3.13–6.50] versus 2.33 [95% CI, 1.88–3.04] for diabetes mellitus) as well as CVD events (eg, adjusted HR, 1.85 [95% CI, 1.26–2.71] versus 1.19 [95% CI, 1.01–1.40] for CVD death). Conclusions Anthropometric measures of obesity, including waist circumference and BMI, adequately capture VAT‐associated cardiometabolic and cardiovascular risk in men but not in women. In women, abdominal computed tomography–based VAT measures permit more precise assessment of obesity‐associated cardiometabolic and cardiovascular risk.

Background Cardiovascular disease (CVD) and associated comorbidities increase the risk of cognitive impairment in persons living with human immunodeficiency virus (PLWH). Given the potential composite effect of multiple cardiovascular risk factors on cognition, we examined the ability of the Atherosclerotic Cardiovascular Disease (ASCVD) risk score and the Framingham Heart Study Global CVD risk score (FRS) to predict future cognitive function in older PLWH. Methods We constructed linear regression models evaluating the association between baseline 10-year cardiovascular risk scores and cognitive function (measured by a summary z-score, the NPZ-4) at a year 4 follow-up visit. Results Among 988 participants (mean age, 52 years; 20% women), mean 10-year ASCVD risk score at entry into the cohort was 6.8% (standard deviation [SD], 7.1%) and FRS was 13.1% (SD, 10.7%). In models adjusted only for cognitive function at entry, the ASCVD risk score significantly predicted year 4 NPZ-4 in the entire cohort and after stratification by sex (for every 1% higher ASCVD risk, year 4 NPZ-4 was lower by 0.84 [SD, 0.28] overall, P = .003; lower by 2.17 [SD, 0.67] in women, P = .001; lower by 0.78 [SD, 0.32] in men, P = .016). A similar relationship was observed between FRS and year 4 NPZ-4. In multivariable models, higher 10-year ASCVD risk and FRS predicted lower NPZ-4 in women. Conclusions Baseline 10-year ASCVD risk and FRS predicted future cognitive function in older PLWH with well-controlled infection. Cardiovascular risk scores may help to identify PLWH, especially women, who are at risk for worse cognition over time.

Supplemental Digital Content is available in the text.