Deep Learning to Estimate Cardiovascular Risk From Chest Radiographs : A Risk Prediction Study.

BACKGROUND: Guidelines for primary prevention of atherosclerotic cardiovascular disease (ASCVD) recommend a risk calculator (ASCVD risk score) to estimate 10-year risk for major adverse cardiovascular events (MACE). Because the necessary inputs are often missing, complementary approaches for opportunistic risk assessment are desirable. OBJECTIVE: To develop and test a deep-learning model (CXR CVD-Risk) that estimates 10-year risk for MACE from a routine chest radiograph (CXR) and compare its performance with that of the traditional ASCVD risk score for implications for statin eligibility. DESIGN: Risk prediction study. SETTING: Outpatients potentially eligible for primary cardiovascular prevention. PARTICIPANTS: The CXR CVD-Risk model was developed using data from a cancer screening trial. It was externally validated in 8869 outpatients with unknown ASCVD risk because of missing inputs to calculate the ASCVD risk score and in 2132 outpatients with known risk whose ASCVD risk score could be calculated. MEASUREMENTS: 10-year MACE predicted by CXR CVD-Risk versus the ASCVD risk score. RESULTS: Among 8869 outpatients with unknown ASCVD risk, those with a risk of 7.5% or higher as predicted by CXR CVD-Risk had higher 10-year risk for MACE after adjustment for risk factors (adjusted hazard ratio [HR], 1.73 [95% CI, 1.47 to 2.03]). In the additional 2132 outpatients with known ASCVD risk, CXR CVD-Risk predicted MACE beyond the traditional ASCVD risk score (adjusted HR, 1.88 [CI, 1.24 to 2.85]). LIMITATION: Retrospective study design using electronic medical records. CONCLUSION: On the basis of a single CXR, CXR CVD-Risk predicts 10-year MACE beyond the clinical standard and may help identify individuals at high risk whose ASCVD risk score cannot be calculated because of missing data. PRIMARY FUNDING SOURCE: None.

Deep learning analysis of epicardial adipose tissue to predict cardiovascular risk in heavy smokers.

BACKGROUND: Heavy smokers are at increased risk for cardiovascular disease and may benefit from individualized risk quantification using routine lung cancer screening chest computed tomography. We investigated the prognostic value of deep learning-based automated epicardial adipose tissue quantification and compared it to established cardiovascular risk factors and coronary artery calcium. METHODS: We investigated the prognostic value of automated epicardial adipose tissue quantification in heavy smokers enrolled in the National Lung Screening Trial and followed for 12.3 (11.9-12.8) years. The epicardial adipose tissue was segmented and quantified on non-ECG-synchronized, non-contrast low-dose chest computed tomography scans using a validated deep-learning algorithm. Multivariable survival regression analyses were then utilized to determine the associations of epicardial adipose tissue volume and density with all-cause and cardiovascular mortality (myocardial infarction and stroke). RESULTS: Here we show in 24,090 adult heavy smokers (59% men; 61 ± 5 years) that epicardial adipose tissue volume and density are independently associated with all-cause (adjusted hazard ratios: 1.10 and 1.38; P < 0.001) and cardiovascular mortality (adjusted hazard ratios: 1.14 and 1.78; P < 0.001) beyond demographics, clinical risk factors, body habitus, level of education, and coronary artery calcium score. CONCLUSIONS: Our findings suggest that automated assessment of epicardial adipose tissue from low-dose lung cancer screening images offers prognostic value in heavy smokers, with potential implications for cardiovascular risk stratification in this high-risk population.

Heavy smokers are at increased risk of poor health outcomes, particularly outcomes related to cardiovascular disease. We explore how fat surrounding the heart, known as epicardial adipose tissue, may be an indicator of the health of heavy smokers. We use an artificial intelligence system to measure the heart fat on chest scans of heavy smokers taken during a lung cancer screening trial and following their health for 12 years. We find that higher amounts and denser epicardial adipose tissue are linked to an increased risk of death from any cause, specifically from heart-related issues, even when considering other health factors. This suggests that measuring epicardial adipose tissue during lung cancer screenings could be a valuable tool for identifying heavy smokers at greater risk of heart problems and death, possibly helping to guide their medical management and improve their cardiovascular health.

Variant Coronary Arterial Collateral Ring.

A 74-year-old man presented with symptoms and noninvasive diagnostic studies suggestive of myocardial infarction. Coronary angiography revealed total occlusion of the distal right coronary artery with a unique accessory coronary ring that provided retrograde collateral flow to the left ventricle, demonstrating the importance of considering non-native vessels when identifying target lesions.

External Testing of a Deep Learning Model to Estimate Biologic Age Using Chest Radiographs.

Purpose To assess the prognostic value of a deep learning-based chest radiographic age (hereafter, CXR-Age) model in a large external test cohort of Asian individuals. Materials and Methods This single-center, retrospective study included chest radiographs from consecutive, asymptomatic Asian individuals aged 50-80 years who underwent health checkups between January 2004 and June 2018. This study performed a dedicated external test of a previously developed CXR-Age model, which predicts an age adjusted based on the risk of all-cause mortality. Adjusted hazard ratios (HRs) of CXR-Age for all-cause, cardiovascular, lung cancer, and respiratory disease mortality were assessed using multivariable Cox or Fine-Gray models, and their added values were evaluated by likelihood ratio tests. Results A total of 36 924 individuals (mean chronological age, 58 years ± 7 [SD]; CXR-Age, 60 years ± 5; 22 352 male) were included. During a median follow-up of 11.0 years, 1250 individuals (3.4%) died, including 153 cardiovascular (0.4%), 166 lung cancer (0.4%), and 98 respiratory (0.3%) deaths. CXR-Age was a significant risk factor for all-cause (adjusted HR at chronological age of 50 years, 1.03; at 60 years, 1.05; at 70 years, 1.07), cardiovascular (adjusted HR, 1.11), lung cancer (adjusted HR for individuals who formerly smoked, 1.12; for those who currently smoke, 1.05), and respiratory disease (adjusted HR, 1.12) mortality (P < .05 for all). The likelihood ratio test demonstrated added prognostic value of CXR-Age to clinical factors, including chronological age for all outcomes (P < .001 for all). Conclusion Deep learning-based chest radiographic age was associated with various survival outcomes and had added value to clinical factors in asymptomatic Asian individuals, suggesting its generalizability. Keywords: Conventional Radiography, Thorax, Heart, Lung, Mediastinum, Outcomes Analysis, Quantification, Prognosis, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Adams and Bressem in this issue.

Selective Use of CT Fractional Flow at a Large Academic Medical Center: Insights from Clinical Implementation after 1 Year of Practice.

Purpose This special report outlines a retrospective observational study of CT fractional flow reserve (CT-FFR) analysis using dual-source coronary CT angiography (CTA) scans performed without heart rate control and its impact on clinical outcomes. Materials and Methods All patients who underwent clinically indicated coronary CTA between August 2020 and August 2021 were included in this retrospective observational study. Scans were performed in the late systolic to early diastolic period without heart rate control and analyzed at the interpreting physician's discretion. Demographics, coronary CTA features, and rates of invasive coronary angiography (ICA), percutaneous coronary intervention (PCI), myocardial infarction, and all-cause death at 3 months were assessed by chart review. Results During the study period, 3098 patients underwent coronary CTA, of whom 113 with coronary bypass grafting were excluded. Of the remaining 2985 patients, 292 (9.7%) were referred for CT-FFR analysis. Two studies (0.7%) were rejected from CT-FFR analysis, and six (2.1%) analyses did not evaluate the lesion of concern. A total of 160 patients (56.3%) had CT-FFR greater than 0.80. Among patients with significant stenosis at coronary CTA, patients who underwent CT-FFR analysis presented with lower rates of ICA (74.5% vs 25.5%, P = .04) and PCI (78.9% vs 21.1%, P = .05). Conclusion CT-FFR was implemented in patients not requiring heart rate control by using dual-source coronary CTA acquisition and showed the potential to decrease rates of ICA and PCI without compromising safety in patients with significant stenosis and an average heart rate of 65 beats per minute. Keywords: Angiography, CT, CT-Angiography, Fractional Flow Reserve, Cardiac, Heart, Arteriosclerosis Supplemental material is available for this article. © RSNA, 2024.

Standards for quantitative assessments by coronary computed tomography angiography (CCTA): An expert consensus document of the society of cardiovascular computed tomography (SCCT).

In current clinical practice, qualitative or semi-quantitative measures are primarily used to report coronary artery disease on cardiac CT. With advancements in cardiac CT technology and automated post-processing tools, quantitative measures of coronary disease severity have become more broadly available. Quantitative coronary CT angiography has great potential value for clinical management of patients, but also for research. This document aims to provide definitions and standards for the performance and reporting of quantitative measures of coronary artery disease by cardiac CT.

Polygenic Scores and Preclinical Cardiovascular Disease in Individuals With HIV: Insights From the REPRIEVE Trial.

BACKGROUND: Coronary artery disease (CAD) is a leading cause of death among the 38.4 million people with HIV globally. The extent to which cardiovascular polygenic risk scores (PRSs) derived in non-HIV populations generalize to people with HIV is not well understood. METHODS AND RESULTS: PRSs for CAD (GPSMult) and lipid traits were calculated in a global cohort of people with HIV treated with antiretroviral therapy with low-to-moderate atherosclerotic cardiovascular disease risk enrolled in REPRIEVE (Randomized Trial to Prevent Vascular Events in HIV). The PRSs were associated with baseline lipid traits in 4495 genotyped participants, and with subclinical CAD in a subset of 662 who underwent coronary computed tomography angiography. Among participants who underwent coronary computed tomography angiography (mean age, 50.9 [SD, 5.8] years; 16.1% women; 41.8% African, 57.3% European, 1.1% Asian), GPSMult was associated with plaque presence with odds ratio (OR) per SD in GPSMult of 1.42 (95% CI, 1.20-1.68; P=3.8×10-5), stenosis >50% (OR, 2.39 [95% CI, 1.48-3.85]; P=3.4×10-4), and noncalcified/vulnerable plaque (OR, 1.45 [95% CI, 1.23-1.72]; P=9.6×10-6). Effects were consistent in subgroups of age, sex, 10-year atherosclerotic cardiovascular disease risk, ancestry, and CD4 count. Adding GPSMult to established risk factors increased the C-statistic for predicting plaque presence from 0.718 to 0.734 (P=0.02). Furthermore, a PRS for low-density lipoprotein cholesterol was associated with plaque presence with OR of 1.21 (95% CI, 1.01-1.44; P=0.04), and partially calcified plaque with OR of 1.21 (95% CI, 1.01-1.45; P=0.04) per SD. CONCLUSIONS: Among people with HIV treated with antiretroviral therapy without documented atherosclerotic cardiovascular disease and at low-to-moderate calculated risk in REPRIEVE, an externally developed CAD PRS was predictive of subclinical atherosclerosis. PRS for low-density lipoprotein cholesterol was also associated with subclinical atherosclerosis, supporting a role for low-density lipoprotein cholesterol in HIV-associated CAD. REGISTRATION: URL: https://www.reprievetrial.org; Unique identifier: NCT02344290.

Lipoprotein subclasses are associated with Hepatic steatosis: insights from the prospective multicenter imaging study for the evaluation of chest pain (PROMISE) clinical trial.

Objectives: To determine the relationship between lipoprotein particle size/number with hepatic steatosis (HS), given its association with traditional lipoproteins and coronary atherosclerosis. Methods: Individuals with available CT data and blood samples enrolled in the PROMISE trial were studied. HS was defined based on CT attenuation. Lipoprotein particle size/number were measured by nuclear magnetic resonance spectroscopy. Principal components analysis (PCA) was used for dimensionality reduction. The association of PCA factors and individual lipoprotein particle size/number with HS were assessed in multivariable regression models. Associations were validated in an independent cohort of 59 individuals with histopathology defined HS. Results: Individuals with HS (n=410/1,509) vs those without (n=1,099/1,509), were younger (59±8 vs 61±8 years) and less often females (47.6 % vs 55.9 %). All PCA factors were associated with HS: factor 1 (OR:1.36, 95 %CI:1.21-1.53), factor 3 (OR:1.75, 95 %CI:1.53-2.02) and factor 4 (OR:1.49; 95 %CI:1.32-1.68) were weighted heavily with small low density lipoprotein (LDL) and triglyceride-rich (TRL) particles, while factor 2 (OR:0.86, 95 %CI:0.77-0.97) and factor 5 (OR:0.74, 95 %CI:0.65-0.84) were heavily loaded with high density lipoprotein (HDL) and larger LDL particles. These observations were confirmed with the analysis of individual lipoprotein particles in PROMISE. In the validation cohort, association between HS and large TRL (OR: 8.16, 95 %CI:1.82-61.98), and mean sizes of TRL- (OR: 2.82, 95 %CI:1.14-9.29) and HDL (OR:0.35, 95 %CI:0.13-0.72) were confirmed. Conclusions: Large TRL, mean sizes of TRL-, and HDL were associated with radiographic and histopathologic HS. The use of lipoprotein particle size/number could improve cardiovascular risk assessment in HS.

Association of T-cell subtypes with macrophage-specific arterial infiltration in PWH.

People with human immunodeficiency virus (HIV, PWH) face an increased risk of cardiovascular disease (CVD) compared to the general population. We previously demonstrated that people with (versus without) HIV have higher macrophage-specific arterial infiltration in relation to systemic monocyte activation. We now show that select T lymphocyte subpopulations (naïve CD4+, effector memory CD4+, and central memory CD8+) are differentially associated with macrophage-specific arterial infiltration among participants with versus without HIV, with evidence of interaction by HIV status. Our results suggest that among PWH, circulating T lymphocytes associate with macrophage-specific arterial infiltration, of relevance to atherogenesis and CVD risk. CLINICAL TRIALS REGISTRATION: NCT02542371.

Cytomegalovirus IgG is Associated With Physical Function But Not Muscle Density in People With HIV.

BACKGROUND: Cytomegalovirus (CMV) seropositivity is associated with poor outcomes, including physical function impairment, in people without HIV. We examined associations between CMV IgG titer and physical function in virologically suppressed people with HIV (PWH). METHODS: REPRIEVE is a double-blind randomized trial evaluating pitavastatin for primary prevention of atherosclerotic cardiovascular disease in PWH. This analysis focused on participants enrolled in a substudy with additional biomarker testing, imaging [coronary CT angiography], and physical function measures at entry. CMV IgG was measured using quantitative enzyme immunoassay, physical function by Short Physical Performance Battery, and muscle density and area by CT. Associations between CMV IgG (risk factor) and outcomes were evaluated using the partial Spearman correlation and linear and log-binomial regression. RESULTS: Among 717 participants, 82% male, the median CMV IgG was 2716 (Q1, Q3: 807, 6672) IU/mL, all above the limit of quantification. Among 631 participants with imaging, there was no association between CMV IgG and CT-based muscle density or area, controlling for age (r = -0.03 and r = -0.01, respectively; P ≥ 0.38). Among 161 participants with physical function data, higher CMV IgG was associated with poorer overall modified Short Physical Performance Battery score ( P = 0.02), adjusted for age, nadir CD4, and high-sensitivity C-reactive protein. CONCLUSIONS: Higher CMV IgG titer was associated with poorer physical function, not explained by previous immune compromise, inflammation, or muscle density or area. Further mechanistic studies are needed to understand this association and whether CMV-specific therapy can affect physical function in PWH.

Risk factors for clonal hematopoiesis of indeterminate potential in people with HIV: a report from the REPRIEVE trial.

ABSTRACT: Clonal hematopoiesis of indeterminate potential (CHIP), the clonal expansion of myeloid cells with leukemogenic mutations, results in increased coronary artery disease (CAD) risk. CHIP is more prevalent among people with HIV (PWH), but the risk factors are unknown. CHIP was identified among PWH in REPRIEVE (Randomized Trial to Prevent Vascular Events in HIV) using whole-exome sequencing. Logistic regression was used to associate sociodemographic factors and HIV-specific factors with CHIP adjusting for age, sex, and smoking status. In the studied global cohort of 4486 PWH, mean age was 49.9 (standard deviation [SD], 6.4) years; 1650 (36.8%) were female; and 3418 (76.2%) were non-White. CHIP was identified in 223 of 4486 (4.97%) and in 38 of 373 (10.2%) among those aged ≥60 years. Age (odds ratio [OR], 1.07; 95% confidence interval [CI], 1.05-1.09; P < .0001) and smoking (OR, 1.37; 95% CI, 1.14-1.66; P < .001) associated with increased odds of CHIP. Globally, participants outside of North America had lower odds of CHIP including sub-Saharan Africa (OR, 0.57; 95% CI, 0.4-0.81; P = .0019), South Asia (OR, 0.45; 95% CI, 0.23-0.80; P = .01), and Latin America/Caribbean (OR, 0.56; 95% CI, 0.34-0.87; P = .014). Hispanic/Latino ethnicity (OR, 0.38; 95% CI, 0.23-0.54; P = .002) associated with significantly lower odds of CHIP. Among HIV-specific factors, CD4 nadir <50 cells/mm3 associated with a 1.9-fold (95%CI, 1.21-3.05; P = .006) increased odds of CHIP, with the effect being significantly stronger among individuals with short duration of antiretroviral therapy (ART; OR, 4.15; 95% CI, 1.51-11.1; P = .005) (Pinteraction= .0492). Among PWH at low-to-moderate CAD risk on stable ART, smoking, CD4 nadir, North American origin, and non-Hispanic ethnicity associated with increased odds of CHIP. This trial was registered at www.ClinicalTrials.gov as NCT02344290.

Effects of Pitavastatin on Coronary Artery Disease and Inflammatory Biomarkers in HIV: Mechanistic Substudy of the REPRIEVE Randomized Clinical Trial.

Importance: Cardiovascular disease (CVD) is increased in people with HIV (PWH) and is characterized by premature noncalcified coronary plaque. In the Randomized Trial to Prevent Vascular Events in HIV (REPRIEVE), pitavastatin reduced major adverse cardiovascular events (MACE) by 35% over a median of 5.1 years. Objective: To investigate the effects of pitavastatin on noncalcified coronary artery plaque by coronary computed tomography angiography (CTA) and on inflammatory biomarkers as potential mechanisms for MACE prevention. Design, Setting, and Participants: This double-blind, placebo-controlled randomized clinical trial enrolled participants from April 2015 to February 2018 at 31 US clinical research sites. PWH without known CVD who were taking antiretroviral therapy and had low to moderate 10-year CVD risk were included. Data were analyzed from April to November 2023. Intervention: Oral pitavastatin calcium, 4 mg per day. Main Outcomes and Measures: Coronary CTA and inflammatory biomarkers at baseline and 24 months. The primary outcomes were change in noncalcified coronary plaque volume and progression of noncalcified plaque. Results: Of 804 enrolled persons, 774 had at least 1 evaluable CTA. Plaque changes were assessed in 611 who completed both CT scans. Of 611 analyzed participants, 513 (84.0%) were male, the mean (SD) age was 51 (6) years, and the median (IQR) 10-year CVD risk was 4.5% (2.6-7.0). A total of 302 were included in the pitavastatin arm and 309 in the placebo arm. The mean noncalcified plaque volume decreased with pitavastatin compared with placebo (mean [SD] change, -1.7 [25.2] mm3 vs 2.6 [27.1] mm3; baseline adjusted difference, -4.3 mm3; 95% CI, -8.6 to -0.1; P = .04; 7% [95% CI, 1-12] greater reduction relative to placebo). A larger effect size was seen among the subgroup with plaque at baseline (-8.8 mm3 [95% CI, -17.9 to 0.4]). Progression of noncalcified plaque was 33% less likely with pitavastatin compared with placebo (relative risk, 0.67; 95% CI, 0.52-0.88; P = .003). Compared with placebo, the mean low-density lipoprotein cholesterol decreased with pitavastatin (mean change: pitavastatin, -28.5 mg/dL; 95% CI, -31.9 to -25.1; placebo, -0.8; 95% CI, -3.8 to 2.2). The pitavastatin arm had a reduction in both oxidized low-density lipoprotein (-29% [95% CI, -32 to -26] vs -13% [95% CI, -17 to -9]; P < .001) and lipoprotein-associated phospholipase A2 (-7% [95% CI, -11 to -4] vs 14% [95% CI, 10-18]; P < .001) compared with placebo at 24 months. Conclusions and Relevance: In PWH at low to moderate CVD risk, 24 months of pitavastatin reduced noncalcified plaque volume and progression as well as markers of lipid oxidation and arterial inflammation. These changes may contribute to the observed MACE reduction in REPRIEVE. Trial Registration: ClinicalTrials.gov Identifier: NCT02344290.

Coronary Plaque in People With HIV vs Non-HIV Asymptomatic Community and Symptomatic Higher-Risk Populations.

Background: People with HIV (PWH) have a high burden of coronary plaques; however, the comparison to people without known HIV (PwoH) needs clarification. Objectives: The purpose of this study was to determine coronary plaque burden/phenotype in PWH vs PwoH. Methods: Nonstatin using participants from 3 contemporary populations without known coronary plaques with coronary CT were compared: the REPRIEVE (Randomized Trial to Prevent Vascular Events in HIV) studying PWH without cardiovascular symptoms at low-to-moderate risk (n = 755); the SCAPIS (Swedish Cardiopulmonary Bioimage Study) of asymptomatic community PwoH at low-to-intermediate cardiovascular risk (n = 23,558); and the PROMISE (Prospective Multicenter Imaging Study for Evaluation of Chest Pain) of stable chest pain PwoH (n = 2,291). The coronary plaque prevalence on coronary CT was compared, and comparisons were stratified by 10-year atherosclerotic cardiovascular disease (ASCVD) risk, age, and coronary artery calcium (CAC) presence. Results: Compared to SCAPIS and PROMISE PwoH, REPRIEVE PWH were younger (50.8 ± 5.8 vs 57.3 ± 4.3 and 60.0 ± 8.0 years; P < 0.001) and had lower ASCVD risk (5.0% ± 3.2% vs 6.0% ± 5.3% and 13.5% ± 11.0%; P < 0.001). More PWH had plaque compared to the asymptomatic cohort (48.5% vs 40.3%; P < 0.001). When stratified by ASCVD risk, PWH had more plaque compared to SCAPIS and a similar prevalence of plaque compared to PROMISE. CAC = 0 was more prevalent in PWH (REPRIEVE 65.2%; SCAPIS 61.6%; PROMISE 49.6%); among CAC = 0, plaque was more prevalent in PWH compared to the PwoH cohorts (REPRIEVE 20.8%; SCAPIS 5.4%; PROMISE 12.3%, P < 0.001). Conclusions: Asymptomatic PWH in REPRIEVE had more plaque than asymptomatic PwoH in SCAPIS but had similar prevalence to a higher-risk stable chest pain cohort in PROMISE. In PWH, CAC = 0 does not reliably exclude plaque.