Mortality impact of low CAC density predominantly occurs in early atherosclerosis: explainable ML in the CAC consortium.

BACKGROUND: Machine learning (ML) models of risk prediction with coronary artery calcium (CAC) and CAC characteristics exhibit high performance, but are not inherently interpretable. OBJECTIVES: To determine the direction and magnitude of impact of CAC characteristics on 10-year all-cause mortality (ACM) with explainable ML. METHODS: We analyzed asymptomatic subjects in the CAC consortium. We trained ML models on 80% and tested on 20% of the data with XGBoost, using clinical characteristics â€‹+ â€‹CAC (ML 1) and additional CAC characteristics of CAC density and number of calcified vessels (ML 2). We applied SHAP, an explainable ML tool, to explore the relationship of CAC and CAC characteristics with 10-year all-cause and CV mortality. RESULTS: 2376 deaths occurred among 63,215 patients [68% male, median age 54 (IQR 47-61), CAC 3 (IQR 0-94.3)]. ML2 was similar to ML1 to predict all-cause mortality (Area Under the Curve (AUC) 0.819 vs 0.821, p â€‹= â€‹0.23), but superior for CV mortality (0.847 vs 0.845, p â€‹= â€‹0.03). Low CAC density increased mortality impact, particularly ≤0.75. Very low CAC density ≤0.75 was present in only 4.3% of the patients with measurable density, and 75% occurred in CAC1-100. The number of diseased vessels did not increase mortality overall when simultaneously accounting for CAC and CAC density. CONCLUSION: CAC density contributes to mortality risk primarily when it is very low ≤0.75, which is primarily observed in CAC 1-100. CAC and CAC density are more important for mortality prediction than the number of diseased vessels, and improve prediction of CV but not all-cause mortality. Explainable ML techniques are useful to describe granular relationships in otherwise opaque prediction models.

Vessel-specific plaque features on coronary computed tomography angiography among patients of varying atherosclerotic cardiovascular disease risk.

AIMS: The relationship between AtheroSclerotic CardioVascular Disease (ASCVD) risk and vessel-specific plaque evaluation using coronary computed tomography angiography (CCTA), focusing on plaque extent and composition, has not been examined. To evaluate differences in quantified plaque characteristics (using CCTA) between the three major coronary arteries [left anterior descending (LAD), right coronary (RCA), and left circumflex (LCx)] among subgroups of patients with varying ASCVD risk. METHODS AND RESULTS: Patients were included from a prospective, international registry of consecutive patients who underwent CCTA for evaluation of coronary artery disease. ASCVD risk groups were <7.5% (low), 7.5-20% (intermediate), and ≥20% (high). Among the ASCVD risk groups, the three coronary arteries were compared regarding quantified plaque volume and composition. Whole-heart plaque quantification was performed in 1340 patients (age 60 ± 9 years, 58% men). Across low, intermediate, and high ASCVD risk patients, the volume of plaque increased proportionally but was least in the LCx (7.4, 9.0, and 25.3 mm3, respectively) as compared with the RCA (19.3, 32.6, and 67.0 mm3, respectively, all P ≤ 0.006) and LAD (39.9, 60.8, and 93.3 mm3, respectively, all P < 0.001). In each ASCVD risk group, the composition of plaque in the LCx exhibited the least necrotic core and fibrofatty plaque (P < 0.05 vs. LAD and RCA). CONCLUSION: Among patients with varying risk of ASCVD, plaque in the LCx is decidedly less and is comprised of less non-calcified plaque supporting prior evidence of the lower rates of acute coronary events in this vessel.