Value of Machine Learning-based Coronary CT Fractional Flow Reserve Applied to Triple-Rule-Out CT Angiography in Acute Chest Pain | JoVE Visualize

Value of Machine Learning-based Coronary CT Fractional Flow Reserve Applied to Triple-Rule-Out CT Angiography in Acute Chest Pain

Simon S Martin¹, Domenico Mastrodicasa¹, Marly van Assen¹

¹Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, Ashley River Tower, 25 Courtenay Dr, Charleston, SC 29425-2260 (S.S.M., D.M., M.v.A., C.N.D.C., R.R.B., C.T., A.V.S., A.M.F., B.E.J., L.P.G., U.J.S.); Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt, Germany (S.S.M., T.J.V.); Stanford University School of Medicine, Department of Radiology, Stanford, Calif (D.M.); Division of Cardiothoracic Imaging, Nuclear Medicine and Molecular Imaging, Department of Radiology and Imaging Sciences, Emory University, Atlanta, Ga (C.N.D.C.); Division of Cardiology, Department of Medicine, Medical University of South Carolina, Charleston, SC (R.R.B.); Department of Cardiology and Intensive Care Medicine, Heart Center Munich-Bogenhausen, Munich, Germany (C.T.); Department of Cardiology, Munich University Clinic, Ludwig-Maximilians-University, Munich, Germany (C.T.); Siemens Medical Solutions USA, Malvern, Pa (P.S.); and Department of Emergency Medicine, Medical University of South Carolina, Charleston, SC (A.J.M.).

Radiology. Cardiothoracic Imaging|March 29, 2021

View abstract on PubMed

Summary

Artificial intelligence (AI)-based CT-derived fractional flow reserve (CT FFR) from coronary CT angiography better predicts adverse outcomes in acute chest pain patients. This AI tool may reduce unnecessary downstream testing in the emergency department.

Area of Science:

Cardiology
Radiology
Artificial Intelligence in Medicine

Background:

Acute chest pain (ACP) is a common emergency department (ED) presentation.
Accurate diagnosis of coronary artery disease (CAD) is crucial for timely intervention.
Noninvasive imaging modalities are increasingly used to evaluate ACP.

Purpose of the Study:

To assess the added value of AI-based CT-derived fractional flow reserve (CT FFR) using triple-rule-out coronary CT angiography (TRO-CCTA).
To evaluate CT FFR's performance in patients with ACP in the ED setting.
To compare CT FFR with traditional stenosis assessment from TRO-CCTA.

Main Methods:

Retrospective analysis of 159 patients with ACP undergoing TRO-CCTA.
AI-based CT FFR calculation from TRO-CCTA datasets.
Assessed agreement between CT FFR (≤0.80) and ≥50% stenosis on TRO-CCTA.
Evaluated CT FFR's predictive value for revascularization and major adverse cardiac events (MACE) over 1-year.

Main Results:

CT FFR and TRO-CCTA showed agreement in CAD severity in 52% of cases.
CT FFR (≤0.80) was a superior predictor of revascularization and MACE compared to ≥50% stenosis on TRO-CCTA (OR 3.4 vs 2.2).
In a subgroup with additional testing, CT FFR showed higher agreement (55%) than TRO-CCTA (47%).

Conclusions:

AI-based CT FFR from TRO-CCTA is a better predictor of adverse cardiac events and revascularization than TRO-CCTA alone.
CT FFR demonstrates improved agreement with downstream diagnostic testing.
CT FFR may enhance specificity in identifying significant CAD in ACP patients, potentially reducing unnecessary testing.