Prognostic Value of a Coronary Computed Tomography Angiography-Derived Ischemia Algorithm: Comparison Against Hybrid Coronary Computed Tomography Angiography/Positron Emission Tomography Imaging.
Authors
Affiliations (6)
Affiliations (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.
- Department of Cardiology Bern University Hospital Inselspital Bern Switzerland.
- Department of Cardiology Leiden University Medical Center Leiden the Netherlands.
- Heart Center Turku University Hospital and University of Turku Turku Finland.
- Faculty of Medicine University of Turku Turku Finland.
Abstract
Artificial intelligence-guided quantitative computed tomography ischemia (AI-QCT<sub>ischemia</sub>) is a novel machine-learning method for predicting myocardial ischemia from coronary computed tomography angiography (CCTA). This observational cohort study aimed to compare the long-term prognostic value of AI-QCT<sub>ischemia</sub> with hybrid CCTA/positron emission tomography (PET) myocardial perfusion imaging in suspected coronary artery disease (CAD). Symptomatic patients with suspected CAD underwent CCTA with selective downstream PET to detect ischemic CAD. Blinded reanalysis of CCTA images was done using the AI-QCT<sub>ischemia</sub> algorithm, providing a binary result (normal versus abnormal). In the full analysis set (n=2271), hybrid CCTA/PET imaging was successful in 94% of the patients and AI-QCT<sub>ischemia</sub> evaluation was feasible in 83%, resulting in a per-protocol set of 1772 patients (19% with ischemic CAD on hybrid CCTA/PET and 25% with abnormal AI-QCT<sub>ischemia</sub>). There was moderate-to-substantial agreement between the methods (Cohen's κ=0.61). During a median follow-up of 7.0 years, 177 (10%) patients experienced the composite end point of all-cause death, myocardial infarction, or unstable angina. Ischemic CAD on hybrid CCTA/PET was predictive of the composite end point (hazard ratio [HR], 2.35 [95% CI, 1.62-3.40]; <i>P</i><0.001), after adjustment for clinical variables and early (6-month) myocardial revascularization. Similarly, an abnormal (ischemic) AI-QCT<sub>ischemia</sub> result was independently predictive of adverse outcomes (adjusted HR, 1.98 [95% CI, 1.39-2.80]; <i>P</i><0.001). The adjusted models, including either hybrid CCTA/PET or AI-QCT<sub>ischemia</sub>, demonstrated similar discriminative ability (C-index 0.734 versus 0.729; <i>P</i>=0.53). The AI-QCT<sub>ischemia</sub> algorithm demonstrated long-term prognostic value comparable to hybrid CCTA/PET perfusion imaging in suspected CAD.