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

European Heart Journal - Imaging Methods and Practice, vol. 2, pp. qyae035

Abstract

Abstract Aims A comparison of diagnostic performance comparing AI-QCTISCHEMIA, 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. Methods and results 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-QCTISCHEMIA 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-QCTISCHEMIA 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-QCTISCHEMIA were max stenosis diameter % (54% vs. 67%, P < 0.01); for CT-FFR were maximum stenosis diameter % (40% vs. 65%, P < 0.001), total non-calcified plaque (9% vs. 13%, P < 0.01); and for physician visual interpretation CAD-RADS ≥ 3 were total non-calcified plaque (8% vs. 12%, P < 0.01), lumen volume (681 vs. 510 mm3, P = 0.02), maximum stenosis diameter % (40% vs. 62%, P < 0.001), total plaque (19% vs. 33%, P = 0.002), and total calcified plaque (11% vs. 22%, P = 0.003). 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 CAD-RADS ≥ 3.

Authors 22

1. Andrew Chiou corresponding

   Scripps Clinic

   Affiliation as printed

   Department of Cardiology, Scripps Clinic , 9898 Genesee Avenue, AMP 400 , La Jolla, CA 92037, USA

2. Melody Hermel
   Affiliation as printed

   Department of Cardiology, United Medical Doctors , La Jolla, CA, USA

3. Rajbir Sidhu

   Sutter Health · Sutter Medical Center

   Affiliation as printed

   Department of Cardiology, Sutter East Bay Medical Group , Oakland, CA, USA

4. Eric Hu

   Scripps Health

   Affiliation as printed

   Department of Research & Development, Biostatistics, Scripps Health , La Jolla, CA, USA

5. Alexander van Rosendael Aachen Department of Cardiology, Leiden University Medical Center

   Leiden University Medical Center

   Affiliation as printed

   Department of Cardiology, Leiden University Medical Center , Leiden , The Netherlands

6. Samantha R. Spierling Bagsic

   Scripps Health

   Affiliation as printed

   Department of Research & Development, Biostatistics, Scripps Health , La Jolla, CA, USA

7. Emem Udoh
   Affiliation as printed

   Department of Internal Medicine, Bakersfield Memorial Hospital , Bakersfield, CA, USA

8. Ricardo Kosturakis
   Affiliation as printed

   Department of Cardiology, El Paso Cardiology Associates, El Paso, TX, USA

9. Christina Rodriguez Ruiz

   MemorialCare Long Beach Medical Center

   Affiliation as printed

   Department of Cardiology, MemorialCare Long Beach Medical Center , Long Beach, CA, USA

10. Shawn Newlander

    Scripps Health

    Affiliation as printed

    Department of Medical Physics , Scripps Health, La Jolla, CA, USA

11. Bahram Khadivi
    Affiliation as printed

    Department of Cardiology, Scripps Prebys Cardiovascular Institute , La Jolla, CA, USA

12. Jason Parker Brown
    Affiliation as printed

    Department of Cardiology, Scripps Prebys Cardiovascular Institute , La Jolla, CA, USA

13. Maxwell Charlat
    Affiliation as printed

    Department of Cardiology, Scripps Prebys Cardiovascular Institute , La Jolla, CA, USA

14. Paul S. Teirstein

    Scripps Clinic

    Affiliation as printed

    Department of Cardiology, Scripps Clinic , 9898 Genesee Avenue, AMP 400 , La Jolla, CA 92037, USA

15. Curtiss Stinis

    Scripps Clinic

    Affiliation as printed

    Department of Cardiology, Scripps Clinic , 9898 Genesee Avenue, AMP 400 , La Jolla, CA 92037, USA

16. Richard A. Schatz

    Scripps Clinic

    Affiliation as printed

    Department of Cardiology, Scripps Clinic , 9898 Genesee Avenue, AMP 400 , La Jolla, CA 92037, USA

17. Matthew J. Price

    Scripps Clinic

    Affiliation as printed

    Department of Cardiology, Scripps Clinic , 9898 Genesee Avenue, AMP 400 , La Jolla, CA 92037, USA

18. Jeffrey J. Cavendish
    Affiliation as printed

    Department of Cardiology, Scripps Prebys Cardiovascular Institute , La Jolla, CA, USA

19. Michael Salerno

    Stanford University

    Affiliation as printed

    Department of Cardiology, Stanford University , Palo Alto, CA, USA

20. Sanjeev P. Bhavnani

    Scripps Clinic

    Affiliation as printed

    Department of Cardiology, Scripps Clinic , 9898 Genesee Avenue, AMP 400 , La Jolla, CA 92037, USA

21. Jorge A. González

    Scripps Clinic

    Affiliation as printed

    Department of Cardiology, Scripps Clinic , 9898 Genesee Avenue, AMP 400 , La Jolla, CA 92037, USA

22. George E Wesbey

    Scripps Clinic

    Affiliation as printed

    Department of Cardiology, Scripps Clinic , 9898 Genesee Avenue, AMP 400 , La Jolla, CA 92037, USA

    Department of Radiology, Scripps Clinic , La Jolla, CA, USA