Multicenter evaluation of interpretable AI for coronary artery disease diagnosis from PET biomarkers.
Authors
Affiliations (12)
Affiliations (12)
- Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
- School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China.
- Department of Interventional Cardiology and Angiology, Institute of Cardiology, Warsaw, Poland.
- Signal and Image Processing Institute, Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA.
- Department of Cardiac Sciences, University of Calgary, Calgary, AB, Canada.
- Department of Anesthesiology and Intensive Care, Medical University of Warsaw, Warsaw, Poland.
- Department of Radiology, Division of Nuclear Medicine and Molecular Imaging, Brigham and Women's Hospital, Boston, MA, USA.
- Division of Cardiology, Department of Medicine, and Department of Radiology, Columbia University Irving Medical Center/New York-Presbyterian Hospital, New York, NY, USA.
- Intermountain Medical Center Heart Institute, Intermountain Healthcare, Murray, UT, USA.
- Department of Advanced Biomedical Sciences, University of Naples Federico II, Naples, Italy.
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.
- Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA, USA. [email protected].
Abstract
Positron emission tomography (PET)/computed tomography (CT) for myocardial perfusion imaging (MPI) provides multiple imaging biomarkers, often evaluated separately. We developed an artificial intelligence (AI) model integrating key clinical PET MPI parameters to improve the diagnosis of obstructive coronary artery disease (CAD). From 17,348 patients undergoing cardiac PET/CT across four sites, 1664 with invasive coronary angiography and no prior CAD were retrospectively analyzed. Coronary artery calcium (CAC) scores were derived from CT attenuation correction maps, and XGBoost model was trained on one site using 10 image-derived parameters: CAC, stress/rest left ventricular ejection fraction, stress myocardial blood flow (MBF), myocardial flow reserve (MFR), ischemic and stress total perfusion deficit (TPD), transient ischemic dilation ratio, rate pressure product, and sex. External validation was performed across three independent sites. In the testing cohort (n = 1278; CAD prevalence 53%), the AI model achieved an area under the receiver operating characteristic curve (AUC) of 0.83 (95% CI: 0.81-0.85), outperforming experienced physicians (0.80, p = 0.02) and individual biomarkers such as ischemic TPD (0.79, p < 0.001) and MFR (0.75, p < 0.001). Performance was consistent across sex, body mass index, and age. AI integrating perfusion, flow, and CAC scoring improves PET MPI diagnostic accuracy, offering automated and interpretable predictions for CAD diagnosis.