Machine learning and computational fluid dynamics derived FFRCT demonstrate comparable diagnostic performance in patients with coronary artery disease; A Systematic Review and Meta-Analysis.

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. It was hypothesized that ML-based FFRCT (FFRCT) has comparable diagnostic performance with CFD-based FFRCT (FFRCT). We used invasive FFR as the reference test to evaluate the diagnostic performance of FFRCT vs. FFRCT.

METHODS

We searched PubMed, Cochrane Library, EMBASE, WOS, and Scopus for articles published until March 2024. We analyzed the synthesized sensitivity, specificity, and diagnostic odds ratio (DOR) of FFRCT vs FFRCT at both the patient and vessel levels. We generated summary receiver operating characteristic curves (SROC) and then calculated the area under the curve (AUC).

RESULTS

This meta-analysis included 23 studies reporting FFRCT diagnostic performance and 18 studies reporting FFRCT diagnostic performance. In the FFRCT group, 2501 patients and 3764 vessels or lesions were analyzed. In the FFRCT group, 1323 patients and 4194 vessels or lesions were analyzed. Our results showed that at the per-patient level, FFRCT and FFRCT had comparable pooled specificity (Z ​= ​-0.59, P ​= ​0.55) and AUC (P ​= ​0.5). At the per-vessel level, FFRCTCFD and FFRCTML also showed comparable specificity (Z ​= ​0.94, P ​= ​0.34), DOR (Z ​= ​0.7, P ​= ​0.48), and AUC (P ​= ​0.74). However, the sensitivity of FFRCT was significantly lower compared to FFRCT at both patient (Z ​= ​-3.85, P ​= ​0.0001) and vessel (Z ​= ​-2.05, P ​= ​0.04) levels.

CONCLUSION

The FFRCT technique was comparable to standard CFD approaches in terms of AUC and specificity. However, it did not achieve the same level of sensitivity as FFRCT.