Abstract Body (Do not enter title and authors here): Background: As a new noninvasive diagnostic technique, computed tomography-derived fraction flow reserve (FFRCT) has been used to identify hemodynamically significant coronary artery stenosis. FFRCT can be calculated using computational fluid dynamics (CFD) or machine learning (ML) approaches.
Hypothesis: It was hypothesized that ML-based FFRCT (FFRCT_ML) has comparable diagnostic performance with CFD-based FFRCT (FFRCT_CFD)
Aim: We used invasive FFR as the reference test to evaluate the diagnostic performance of FFRCT_ML vs. FFRCT_CFD.
Methods: We searched PubMed, Cochrane Library, EMBASE, WOS, and Scopus for articles published until March 2024. We analyzed the synthesized sensitivity and specificity of FFRCT_ML vs FFRCT_CFD at both the patient and vessel levels. We generated a summary receiver operating characteristic curve (SROC) and then calculated the area under the curve (AUC).
Results: This meta-analysis included 23 studies reporting FFRCT_CFD diagnostic performance and 18 studies reporting FFRCT_ML diagnostic performance. In the FFRCT_CFD group, 2,501 patients and 3,764 vessels/lesions were analyzed. In the FFRCT_ML group, 1,323 patients and 4,194 vessels/lesions were analyzed. Our results show that at the per-patient level, FFRCT_CFD and FFRCT_ML had high pooled estimate sensitivity (91% and 83%) and specificity (88% and 85%) for detecting ischemic lesions, respectively. The results were constant for per-vessel in FFRCT_CFD and FFRCT_ML, with sensitivity of (88% and 81%) and specificity of (85% and 88%), respectively. The AUC of SROC for FFRCT_CFD and FFRCT_ML at per-vessel level were 0.94 and 0.93, respectively.
Conclusion: The FFRCT_ML exhibits high diagnostic performance on par with previous CFD approaches.