Impact of machine-learning CT-derived fractional flow reserve for the diagnosis and management of coronary artery disease in the randomized CRESCENT trials

Objective To determine the potential impact of on-site CT-derived fractional flow reserve (CT-FFR) on the diagnostic efficiency and effectiveness of coronary CT angiography (CCTA) in patients with obstructive coronary artery disease (CAD) on CCTA. Methods This observational cohort study included patients with suspected CAD who had been randomized to cardiac CT in the CRESCENT I and II trials. On-site CT-FFR was blindly performed in all patients with at least one >= 50% stenosis on CCTA and no exclusion criteria for CT-FFR. We retrospectively assessed the effect of adding CT-FFR to the CT protocol in patients with a stenosis >= 50% on CCTA in terms of diagnostic effectiveness, i.e., the number of additional tests required to determine the final diagnosis, reclassification of the initial management strategy, and invasive coronary angiography (ICA) efficiency, i.e., ICA rate without >= 50% CAD. Results Fifty-three patients out of the 372 patients (14%) had at least one >= 50% stenosis on CCTA of whom 42/53 patients (79%) had no exclusion criteria for CT-FFR. CT-FFR showed a hemodynamically significant stenosis (<= 0.80) in 27/53 patients (51%). The availability of CT-FFR would have reduced the number of patients requiring additional testing by 57%-points compared with CCTA alone (37/53 vs. 7/53,p < 0.001). The initial management strategy would have changed for 30 patients (57%,p < 0.001). Reserving ICA for patients with a CT-FFR <= 0.80 would have reduced the number of ICA following CCTA by 13%-points (p = 0.016). Conclusion Implementation of on-site CT-FFR may change management and improve diagnostic efficiency and effectiveness in patients with obstructive CAD on CCTA.