Prognostic value of a novel artificial intelligence-based coronary CTA-derived ischemia algorithm among patients with normal or abnormal myocardial perfusion

Sarah Bär; Teemu Maaniitty; Takeru Nabeta; Jeroen J Bax; James P Earls; James K Min; Antti Saraste; Juhani Knuuti

doi:10.1016/j.jcct.2024.04.001

Prognostic value of a novel artificial intelligence-based coronary CTA-derived ischemia algorithm among patients with normal or abnormal myocardial perfusion

J Cardiovasc Comput Tomogr. 2024 Apr 24:S1934-5925(24)00075-3. doi: 10.1016/j.jcct.2024.04.001. Online ahead of print.

Authors

Sarah Bär¹, Teemu Maaniitty², Takeru Nabeta³, Jeroen J Bax³, James P Earls⁴, James K Min⁴, Antti Saraste⁵, Juhani Knuuti⁶

Affiliations

¹ Turku PET Centre, Turku University Hospital and University of Turku, Turku, Finland; Department of Cardiology, Bern University Hospital Inselspital, Bern, Switzerland.
² Turku PET Centre, Turku University Hospital and University of Turku, Turku, Finland; Department of Clinical Physiology, Nuclear Medicine, and PET, Turku University Hospital, Turku, Finland.
³ Department of Cardiology, Leiden University Medical Center, Leiden, The Netherlands.
⁴ Cleerly inc., New York, United States.
⁵ Turku PET Centre, Turku University Hospital and University of Turku, Turku, Finland; Heart Center, Turku University Hospital and University of Turku, Turku, Finland.
⁶ Turku PET Centre, Turku University Hospital and University of Turku, Turku, Finland; Department of Clinical Physiology, Nuclear Medicine, and PET, Turku University Hospital, Turku, Finland. Electronic address: juhani.knuuti@utu.fi.

PMID: 38664074
DOI: 10.1016/j.jcct.2024.04.001

Abstract

Background: Among patients with obstructive coronary artery disease (CAD) on coronary computed tomography angiography (CTA), downstream positron emission tomography (PET) perfusion imaging can be performed to assess the presence of myocardial ischemia. A novel artificial-intelligence-guided quantitative computed tomography ischemia algorithm (AI-QCT_ischemia) aims to predict ischemia directly from coronary CTA images. We aimed to study the prognostic value of AI-QCT_ischemia among patients with obstructive CAD on coronary CTA and normal or abnormal downstream PET perfusion.

Methods: AI-QCT_ischemia was calculated by blinded analysts among patients from the retrospective coronary CTA cohort at Turku University Hospital, Finland, with obstructive CAD on initial visual reading (diameter stenosis ≥50%) being referred for downstream ¹⁵O-H₂O-PET adenosine stress perfusion imaging. All coronary arteries with their side branches were assessed by AI-QCT_ischemia. Absolute stress myocardial blood flow ≤2.3 ml/g/min in ≥2 adjacent segments was considered abnormal. The primary endpoint was death, myocardial infarction, or unstable angina pectoris. The median follow-up was 6.2 [IQR 4.4-8.3] years.

Results: 662 of 768 (86%) patients had conclusive AI-QCT_ischemia result. In patients with normal ¹⁵O-H₂O-PET perfusion, an abnormal AI-QCT_ischemia result (n = 147/331) vs. normal AI-QCT_ischemia result (n = 184/331) was associated with a significantly higher crude and adjusted rates of the primary endpoint (adjusted HR 2.47, 95% CI 1.17-5.21, p = 0.018). This did not pertain to patients with abnormal ¹⁵O-H₂O-PET perfusion (abnormal AI-QCT_ischemia result (n = 269/331) vs. normal AI-QCT_ischemia result (n = 62/331); adjusted HR 1.09, 95% CI 0.58-2.02, p = 0.794) (p-interaction = 0.039).

Conclusion: Among patients with obstructive CAD on coronary CTA referred for downstream ¹⁵O-H₂O-PET perfusion imaging, AI-QCT_ischemia showed incremental prognostic value among patients with preserved perfusion by ¹⁵O-H₂O-PET imaging, but not among those with reduced perfusion.

Keywords: Artificial intelligence; Coronary computed tomography angiography; Ischemia; Positron emission tomography; Prognosis.