Artificial intelligence coronary computed tomography, coronary computed tomography angiography using fractional flow reserve, and physician visual interpretation in the per-vessel prediction of abnormal invasive adenosine fractional flow reserve

• Published in: European Heart Journal. Imaging Methods and Practice Vol. 2; no. 1; p. qyae035
• Main Authors: Chiou, Andrew, Hermel, Melody, Sidhu, Rajbir, Hu, Eric, van Rosendael, Alexander, Bagsic, Samantha, Udoh, Emem, Kosturakis, Ricardo, Aziz, Mohammad, Ruiz, Christina Rodriguez, Newlander, Shawn, Khadivi, Bahram, Brown, Jason Parker, Charlat, Martin L, Teirstein, Paul S, Stinis, Curtiss T, Schatz, Richard, Price, Matthew J, Cavendish, Jeffrey, Salerno, Michael, Robinson, Austin, Bhavnani, Sanjeev, Gonzalez, Jorge, Wesbey, George E
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 01-01-2024
• Subjects: Original; coronary artery disease; quantitative CT coronary angiography; CT-fractional flow reserve; comparative studies; artificial intelligence
• ISSN: 2755-9637; 2755-9637
• DOI: 10.1093/ehjimp/qyae035

A comparison of diagnostic performance comparing AI-QCT
, coronary computed tomography angiography using fractional flow reserve (CT-FFR), and physician visual interpretation on the prediction of invasive adenosine FFR have not been evaluated. Furthermore, the coronary plaque characteristics impacting these tests have not been assessed.
In a single centre, 43-month retrospective review of 442 patients referred for coronary computed tomography angiography and CT-FFR, 44 patients with CT-FFR had 54 vessels assessed using intracoronary adenosine FFR within 60 days. A comparison of the diagnostic performance among these three techniques for the prediction of FFR ≤ 0.80 was reported. The mean age of the study population was 65 years, 76.9% were male, and the median coronary artery calcium was 654. When analysing the per-vessel ischaemia prediction, AI-QCT
had greater specificity, positive predictive value (PPV), diagnostic accuracy, and area under the curve (AUC) vs. CT-FFR and physician visual interpretation CAD-RADS. The AUC for AI-QCT
was 0.91 vs. 0.76 for CT-FFR and 0.62 for CAD-RADS ≥ 3. Plaque characteristics that were different in false positive vs. true positive cases for AI-QCT
were max stenosis diameter % (54% vs. 67%,
); for CT-FFR were maximum stenosis diameter % (40% vs. 65%,
< 0.001), total non-calcified plaque (9% vs. 13%,
< 0.01); and for physician visual interpretation CAD-RADS ≥ 3 were total non-calcified plaque (8% vs. 12%,
< 0.01), lumen volume (681 vs. 510 mm
,
= 0.02), maximum stenosis diameter % (40% vs. 62%,
< 0.001), total plaque (19% vs. 33%,
= 0.002), and total calcified plaque (11% vs. 22%,
= 0.003).
Regarding per-vessel prediction of FFR ≤ 0.8, AI-QCT
revealed greater specificity, PPV, accuracy, and AUC vs. CT-FFR and physician visual interpretation CAD-RADS ≥ 3.