What are the key findings of this study?

The FFR derived from machine learning algorithm (FFR ML ) showed similar performance to FFR CFD in detecting lesion-specific ischemia, both outperforming coronary CT angiography.

April 10, 2018

Coronary CT Angiography–derived Fractional Flow Reserve: Machine Learning Algorithm versus Computational Fluid Dynamics Modeling

Key Result

The FFR derived from machine learning algorithm (FFR<sub>ML</sub>) showed similar performance to FFR<sub>CFD</sub> in detecting lesion-specific ischemia, both outperforming coronary CT angiography.

Structured PICO

Does a machine learning algorithm for CT-derived FFR perform as well as computational fluid dynamics modeling in detecting lesion-specific ischemia?

Population

85 patients (mean age 62 ± 11 years, 62% men) who had undergone coronary CT angiography followed by invasive FFR in a single-center retrospective study.

Intervention

Fractional flow reserve derived from coronary CT angiography based on a machine learning algorithm (FFR_ML)

Comparator

Fractional flow reserve derived from coronary CT angiography based on computational fluid dynamics (FFR_CFD), visual stenosis grading at coronary CT angiography, and quantitative coronary angiography (QCA), with invasive FFR as the reference standard

Outcome

Diagnostic performance (sensitivity, specificity, and area under the receiver operating characteristics curve) for detecting lesion-specific ischemiasurrogate

A machine learning-based approach for CT-derived FFR provides equivalent diagnostic accuracy to computational fluid dynamics modeling for detecting lesion-specific ischemia, but with significantly shorter processing times.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Purpose To compare two technical approaches for determination of coronary computed tomography (CT) angiography-derived fractional flow reserve (FFR)-FFR derived from coronary CT angiography based on computational fluid dynamics (hereafter, FFRCFD) and FFR derived from coronary CT angiography based on machine learning algorithm (hereafter, FFRML)-against coronary CT angiography and quantitative coronary angiography (QCA). Materials and Methods A total of 85 patients (mean age, 62 years ± 11 standard deviation; 62% men) who had undergone coronary CT angiography followed by invasive FFR were included in this single-center retrospective study. FFR values were derived on-site from coronary CT angiography data sets by using both FFRCFD and FFRML. The performance of both techniques for detecting lesion-specific ischemia was compared against visual stenosis grading at coronary CT angiography, QCA, and invasive FFR as the reference standard. Results On a per-lesion and per-patient level, FFRML showed a sensitivity of 79% and 90% and a specificity of 94% and 95%, respectively, for detecting lesion-specific ischemia. Meanwhile, FFRCFD resulted in a sensitivity of 79% and 89% and a specificity of 93% and 93%, respectively, on a per-lesion and per-patient basis (P = .86 and P = .92). On a per-lesion level, the area under the receiver operating characteristics curve (AUC) of 0.89 for FFRML and 0.89 for FFRCFD showed significantly higher discriminatory power for detecting lesion-specific ischemia compared with that of coronary CT angiography (AUC, 0.61) and QCA (AUC, 0.69) (all P ML (AUC, 0.91) and FFRCFD (AUC, 0.91) performed significantly better than did coronary CT angiography (AUC, 0.65) and QCA (AUC, 0.68) (all P ML was significantly shorter compared with that of FFRCFD (40.5 minutes ± 6.3 vs 43.4 minutes ± 7.1; P = .042). Conclusion The FFRML algorithm performs equally in detecting lesion-specific ischemia when compared with the FFRCFD approach. Both methods outperform accuracy of coronary CT angiography and QCA in the detection of flow-limiting stenosis.

Bookmark