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

Abstract

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. Key Points • The availability of on-site CT-FFR in the diagnostic evaluation of patients with obstructive CAD on CCTA would have significantly reduced the number of patients requiring additional testing compared with CCTA alone. • The implementation of on-site CT-FFR would have changed the initial management strategy significantly in the patients with obstructive CAD on CCTA. • Restricting ICA to patients with a positive CT-FFR would have significantly reduced the ICA rate in patients with obstructive CAD on CCTA.

The use of lesion-specific calcium morphology to guide the appropriate use of dynamic CT myocardial perfusion imaging and CT fractional flow reserve

“…If the above diagnostic strategy had been applied to the current cohort, dynamic CT-MPI could have been avoided in 33.9% of patients while maintaining uncompromised diagnostic accuracy, leading to a 27.0% and 33.9% reduction in radiation dose and contrast medium usage, respectively. Furthermore, previous studies have demonstrated that CT-FFR may improve downstream clinical management in patients with an intermediateto-high pretest probability of CAD (29,30). The current findings also confirmed the value of CT-FFR in guiding clinical decisions, especially when integrated with dynamic CT-MPI.…”

Functional Coronary Artery Assessment: a Systematic Literature Review

“…FFR is based on a proportional linear relationship between coronary blood flow and perfusion pressure during maximal vasodilation [55] and has been widely validated [30]. However, its cost, availability, vasodilator need [10,61], and poor hemodynamic correlation [50,66] makes its use for physiological assessment meet the current guideline indicators in only 50% of the cases [19]. FFR importance is questioned [66] as well as hyperemia is suggested not to be essential to the correct diagnose [7].…”

“…From 2018 onwards, coronary computed tomography angiography (CCTA) has also been indicated to exclude significant coronary artery diseases in patients with low-to-intermediate lesions due its sensitivity and negative predictive value [9,28,34,37,40,50]. CCTA provides geometrical characteristics such as diameter and area of the lesion and is based in visual assessment [73], but similar to CCA, it is insufficient to provide lesion hemodynamic information [37].…”

“…In the scope of Machine Learning-based (ML) techniques, the major part of recent studies use CCTA characteristics as reference [3,5,21,28,34,39,45,52], but most of them also were evaluated with a reduced number of patients and arteries [5,21,28,33,34,42,50]. These researches use geometrical lesion data [3,21,28,39,42,45,52], clinical risk scores [39] and anatomical descriptors [34].…”

Assessment of Non-Invasive Diagnostic Imaging Modalities Efficiency for Detecting Myocardial Ischemia in Patients Suspected of Having Stable Angina

“…However, CCTA generates exclusively morphological information about coronary arteries. To diagnose the presence of myocardial ischemia irrespective of the presence coronary artery stenosis, it is recommended that myocardial perfusion should be assessed with another modality [8][9][10]. Studies that have detected myocardial ischemia by diagnostic imaging on stable angina primarily use sensitivity and speci city as indices, thus indicating their ability.…”