The following is a summary of “AI-Guided Quantitative Plaque Staging Predicts Long-Term Cardiovascular Outcomes in Patients at Risk for Atherosclerotic CVD,” published in the March 2024 issue of Cardiology by Nurmohamed, et al.

The development of AI-driven analysis for computed tomography angiography (AI-QCT) enables a quick assessment of the quantity and features of atherosclerotic plaque.

Researchers conducted a retrospective study to compare the AI-QCT, coronary computed tomography angiography (CCTA), coronary artery calcium scoring (CACS), and the anatomic risk factors significantly determining the 10-year risk of cardiac events.

They studied 536 patients who were considered to be at risk of coronary artery disease. AI-QCT analysis of CCTA scans was utilized to classify plaque burden using a staging system as stage 0 (0% PAV), stage 1 (>0%-5% PAV), stage 2 (>5%-15% PAV), and stage 3 (>15% PAV). The major adverse cardiac event (MACE) outcome as a primary endpoint consists of non-fatal myocardial infarction, stroke, revascularization, and all-cause mortality.

The results showed that the mean age at baseline was 58.6 years, with 297 patients (55%) being male. Over a median follow-up period of 10.3 years (IQR: 8.6-11.5 years), 114 patients (21%) experienced the primary outcome. Patients with stage 3 PAV and a noncalcified plaque volume exceeding 7.5% demonstrated a more than 3-fold (adjusted HR: 3.57; 95% CI 2.12-6.00; P<0.001) and 4-fold (adjusted HR: 4.37; 95% CI: 2.51-7.62; P<0.001) increased risk of MACE, compared to stages 0 and 1. Incorporating AI-QCT into models with clinical risk factors and CACS at various time points during follow-up significantly improved predictive performance (10-year AUC: 0.82 [95% CI: 0.78-0.87] vs 0.73 [95% CI: 0.68-0.79]; P<0.001; net reclassification improvement: 0.21 [95% CI: 0.09-0.38]). AI-QCT yielded superior area under the curve (AUC) compared to Coronary Artery Disease Reporting and Data System 2.0 (10-year AUC: 0.78; 95% CI: 0.73-0.83; P=0.023) and manual QCT (10-year AUC: 0.78; 95% CI: 0.73-0.83; P=0.040), albeit with modest net reclassification improvement (0.09 [95% CI: −0.02 to 0.29] and 0.04 [95% CI: −0.05 to 0.27]).

Investigators concluded that AI-QCT plaque staging strongly predicts future heart events and outperforms traditional risk factors and imaging techniques.

Source: jacc.org/doi/10.1016/j.jcmg.2023.05.020