AI-QCT, CT-FFR, and physician visual interpretation in the per-vessel prediction of abnormal invasive adenosine FFR
Andrew Chiou, Melody Hermel, Rajbir Sidhu, Eric Hu, Alexander van Rosendael, Samantha Bagsic, Emem Udoh, Ricardo Kosturakis, Mohammad Aziz, Christina Rodriguez Ruiz, Shawn Newlander, Bahram Khadivi, Jason Parker Brown, Martin L Charlat, Paul S Teirstein, Curtiss T Stinis, Richard Schatz, Matthew J Price, Jeffrey Cavendish, Michael Salerno, Austin Robinson, Sanjeev Bhavnani, Jorge Gonzalez, George E WesbeyAbstract
Background
A comparison of diagnostic performance comparing AI-QCTISCHEMIA, 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.
Methods
In a single center, 43-month retrospective review of 442 patients referred for CCTA 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.
Results
The mean age of the study population was 65 years, 76.9% were male, and the median CAC was 623. When analyzing the per vessel ischemia prediction, AI-QCTISCHEMIA had greater specificity, PPV, diagnostic accuracy, and AUC vs. CT- FFR and physician visual interpretation CAD-RADS. The AUC for AI-QCTISCHEMIA was 0.91 vs. 0.76 for CT-FFR and 0.62 for CADRADS ≥3. Plaque characteristics that were different in false positive vs true positive cases for AI-QCTISCHEMIA was max stenosis diameter (50 vs 70%, p = 0.03); for CT-FFR were maximum stenosis diameter (40 vs 70%, p < 0.001), total noncalcified plaque (9 vs 13%, p = 0.02); and for physician visual interpretation CADRADS ≥3 were total noncalcified plaque (8 vs 12%, p = 0.01), lumen volume (681 vs 510mm3, p = 0.03), maximum stenosis diameter (40 vs 60%, p < 0.001), total plaque (19 vs 33%, p = 0.006, total calcified plaque (11 vs 22%, p = 0.008).
Conclusion
Regarding per-vessel prediction of FFR ≤ 0.8, AI-QCTISCHEMIA revealed greater specificity, PPV, accuracy, and AUC vs. CT-FFR and physician visual interpretation CADRADS ≥3.