Impact of Coronary Computerized Tomography Angiography-Derived Plaque Quantification and Machine-Learning...

This study investigated the impact of coronary CT angiography (cCTA)-derived plaque markers and machine-learning-based CT-derived fractional flow reserve (CT-FFR) to identify adverse cardiac outcome. Data of 82 patients (60 ± 11 years, 62% men) who underwent cCTA and invasive coronary angiography (ICA) were analyzed in this single-center retrospective, institutional review board-approved, HIPAA-compliant study. Follow-up was performed to record major adverse cardiac events (MACE). Plaque quantification of lesions responsible for MACE and control lesions was retrospectively performed semiautomatically from cCTA together with machine-learning based CT-FFR. The discriminatory value of plaque markers and CT-FFR to predict MACE was evaluated. After a median follow-up of 18.5 months (interquartile range 11.5 to 26.6 months), MACE was observed in 18 patients (21%). In a multivariate analysis the following markers were predictors of MACE (odds ratio [OR]): lesion length (OR 1.16, p = 0.018), low-attenuation plaque (<30 HU) (OR 4.59, p = 0.003), Napkin ring sign (OR 2.71, p = 0.034), stenosis ≥50% (OR 3.83, p 0.042), and CT-FFR ≤0.80 (OR 7.78, p = 0.001). Receiver operating characteristics analysis including stenosis ≥50%, plaque markers and CT-FFR ≤0.80 (Area under the curve 0.94) showed incremental discriminatory power over stenosis ≥50% alone (Area under the curve 0.60, p <0.0001) for the prediction of MACE. cCTA-derived plaque markers and machine-learning CT-FFR demonstrate predictive value to identify MACE. In conclusion, combining plaque markers with machine-learning CT-FFR shows incremental discriminatory power over cCTA stenosis grading alone.