J Cardiovasc Comput Tomogr. Fay Y Lin et al.

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 ​+ ​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 ​= ​0.23), but superior for CV mortality (0.847 vs 0.845, p ​= ​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.