The best predictor of ischemic coronary stenosis: subtended myocardial volume, machine learning–based FFRCT, or high-risk plaque features?

Objectives The present study aimed to compare the diagnostic performance of a machine learning (ML)–based FFR CT algorithm, quantified subtended myocardial volume, and high-risk plaque features for predicting if a coronary stenosis is hemodynamically significant, with reference to FFR ICA . Methods Patients who underwent both CCTA and FFR ICA measurement within 2 weeks were retrospectively included. ML-based FFR CT , volume of subtended myocardium (V sub ), percentage of subtended myocardium volume versus total myocardium volume (V ratio ), high-risk plaque features, minimal lumen diameter (MLD), and minimal lumen area (MLA) along with other parameters were recorded. Lesions with FFR ICA ≤ 0.8 were considered to be functionally significant. Results One hundred eighty patients with 208 lesions were included. The lesion length (LL), diameter stenosis, area stenosis, plaque burden, V sub , V ratio , V ratio /MLD, V ratio /MLA, and LL/MLD 4 were all significantly longer or larger in the group of FFR ICA ≤ 0.8 while smaller minimal lumen area, MLD, and FFR CT value were noted. The AUC of FFR CT + V ratio /MLD was significantly better than that of FFR CT alone (0.935 versus 0.873, p