Fig. 5

Multivariate cardiovascular outcome modeling using clinical risk factors and CACV-AI volume as predictors in partial least squares regression (PLS). CACV-AI volume was the largest predictor of acute coronary syndrome/myocardial infarction, major adverse cardiac events (MACE), and percutaneous coronary intervention/coronary artery bypass grafting in 1 year of follow-up (AUC = 0.900, 0.911, 0.811, respectively). a Receiver-operator curves describing predictive power of individual cardiovascular outcomes. b Correlation biplots describing the magnitude and direction of associations of predictors with individual cardiovascular outcomes. c Model parameters. Variables with VIP > 1 and 95% CI significant from zero were considered important in the model. The models have a moderate fit and excellently predict cardiovascular events in 1 year of follow-up. ACS/MI, acute coronary syndrome/myocardial infarction; MACE, major adverse cardiac event; PCI, percutaneous coronary intervention; AUC, area under the curve; BMI, body mass index; HTN, hypertension; HLD, hyperlipidemia; VIP, variable importance projection; RMSE, root mean squared error; CI, confidence interval; CAC-AI Volume, coronary artery calcium-artificial intelligence volume; CAC-Expert volume, coronary artery calcium-expert volume