Association of Cardiovascular Disease Risk Factor Burden With Progression of Coronary Atherosclerosis Assessed by Serial Coronary Computed Tomographic Angiography.

Importance: Several studies have reported that the progression of coronary atherosclerosis, as measured by serial coronary computed tomographic (CT) angiography, is associated with the risk of future cardiovascular events. However, the cumulative consequences of multiple risk factors for plaque progression and the development of adverse plaque characteristics have not been well characterized. Objectives: To examine the association of cardiovascular risk factor burden, as assessed by atherosclerotic cardiovascular disease (ASCVD) risk score, with the progression of coronary atherosclerosis and the development of adverse plaque characteristics. Design, Setting, and Participants: This cohort study is a subgroup analysis of participant data from the prospective observational Progression of Atherosclerotic Plaque Determined by Computed Tomographic Angiography Imaging (PARADIGM) study, which evaluated the association between serial coronary CT angiography findings and clinical presentation. The PARADIGM international multicenter registry, which includes 13 centers in 7 countries (Brazil, Canada, Germany, Italy, Portugal, South Korea, and the US), was used to identify 1005 adult patients without known coronary artery disease who underwent serial coronary CT angiography scans (median interscan interval, 3.3 years; interquartile range [IQR], 2.6-4.8 years) between December 24, 2003, and December 16, 2015. Based on the 10-year ASCVD risk score, the cardiovascular risk factor burden was classified as low (<7.5%), intermediate (7.5%-20.0%), or high (>20.0%). Data were analyzed from February 8, 2019, to April 17, 2020. Exposures: Association of baseline ASCVD risk burden with plaque progression. Main Outcomes and Measures: Noncalcified plaque, calcified plaque, and total plaque volumes (mm3) were measured. Noncalcified plaque was subclassified using predefined Hounsfield unit thresholds for fibrous, fibrofatty, and low-attenuation plaque. The percent atheroma volume (PAV) was defined as plaque volume divided by vessel volume. Adverse plaque characteristics were defined as the presence of positive remodeling, low-attenuation plaque, or spotty calcification. Results: In total, 1005 patients (mean [SD] age, 60 [8] years; 575 men [57.2%]) were included in the analysis. Of those, 463 patients (46.1%) had a low 10-year ASCVD risk score (low-risk group), 373 patients (37.1%) had an intermediate ASCVD risk score (intermediate-risk group), and 169 patients (16.8%) had a high ASCVD risk score (high-risk group). The annualized progression rate of PAV for total plaque, calcified plaque, and noncalcified plaque was associated with increasing ASCVD risk (r = 0.26 for total plaque, r = 0.23 for calcified plaque, and r = 0.11 for noncalcified plaque; P < .001). The annualized PAV progression of total plaque, calcified plaque, and noncalcified plaque was significantly greater in the high-risk group compared with the low-risk and intermediate-risk groups (for total plaque, 0.99% vs 0.45% and 0.58%, respectively; P < .001; for calcified plaque, 0.61% vs 0.23% and 0.36%; P < .001; and for noncalcified plaque, 0.38%vs 0.22% and 0.23%; P = .01). When further subclassified by noncalcified plaque type, the annualized PAV progression of fibrofatty and low-attenuation plaque was greater in the high-risk group (0.09% and 0.02%, respectively) compared with the low- to intermediate-risk group (n = 836; 0.02% [P = .02] and 0.001% [P = .008], respectively). The interval development of adverse plaque characteristics was greater in the high-risk group compared with the low-risk and intermediate-risk groups (for new positive remodeling, 73 patients [43.2%] vs 151 patients [32.6%] and 133 patients [35.7%], respectively; P = .02; for new low-attenuation plaque, 26 patients [15.4%] vs 44 patients [9.5%] and 35 patients [9.4%]; P = .02; and for new spotty calcification, 37 patients [21.9%] vs 52 patients [11.2%] and 54 patients [14.5%]; P = .002). The progression of noncalcified plaque subclasses and the interval development of adverse plaque characteristics did not significantly differ between the low-risk and intermediate-risk groups. Conclusions and Relevance: Progression of coronary atherosclerosis occurred across all ASCVD risk groups and was associated with an increase in 10-year ASCVD risk. The progression of fibrofatty and low-attenuation plaques and the development of adverse plaque characteristics was greater in patients with a high risk of ASCVD.

Machine Learning Framework to Identify Individuals at Risk of Rapid Progression of Coronary Atherosclerosis: From the PARADIGM Registry.

Background Rapid coronary plaque progression (RPP) is associated with incident cardiovascular events. To date, no method exists for the identification of individuals at risk of RPP at a single point in time. This study integrated coronary computed tomography angiography-determined qualitative and quantitative plaque features within a machine learning (ML) framework to determine its performance for predicting RPP. Methods and Results Qualitative and quantitative coronary computed tomography angiography plaque characterization was performed in 1083 patients who underwent serial coronary computed tomography angiography from the PARADIGM (Progression of Atherosclerotic Plaque Determined by Computed Tomographic Angiography Imaging) registry. RPP was defined as an annual progression of percentage atheroma volume ≥1.0%. We employed the following ML models: model 1, clinical variables; model 2, model 1 plus qualitative plaque features; model 3, model 2 plus quantitative plaque features. ML models were compared with the atherosclerotic cardiovascular disease risk score, Duke coronary artery disease score, and a logistic regression statistical model. 224 patients (21%) were identified as RPP. Feature selection in ML identifies that quantitative computed tomography variables were higher-ranking features, followed by qualitative computed tomography variables and clinical/laboratory variables. ML model 3 exhibited the highest discriminatory performance to identify individuals who would experience RPP when compared with atherosclerotic cardiovascular disease risk score, the other ML models, and the statistical model (area under the receiver operating characteristic curve in ML model 3, 0.83 [95% CI 0.78-0.89], versus atherosclerotic cardiovascular disease risk score, 0.60 [0.52-0.67]; Duke coronary artery disease score, 0.74 [0.68-0.79]; ML model 1, 0.62 [0.55-0.69]; ML model 2, 0.73 [0.67-0.80]; all P<0.001; statistical model, 0.81 [0.75-0.87], P=0.128). Conclusions Based on a ML framework, quantitative atherosclerosis characterization has been shown to be the most important feature when compared with clinical, laboratory, and qualitative measures in identifying patients at risk of RPP.