Machine learning based model to diagnose obstructive coronary artery disease using calcium scoring, PET imaging, and clinical data

• Published in: Journal of nuclear cardiology Vol. 30; no. 4; pp. 1504 - 1513
• Main Authors: van Dalen, J.A., Koenders, S.S., Metselaar, R.J., Vendel, B.N., Slotman, D.J., Mouden, M., Slump, C.H., van Dijk, J.D.
• Format: Journal Article
• Language: English
• Published: Cham Elsevier Inc 01.08.2023; Springer International Publishing; Springer Nature B.V
• Subjects: Calcium; Cardiology; Cardiovascular disease; Computed Tomography Angiography - methods; Coronary Angiography - methods; Coronary Artery Disease; Coronary vessels; Datasets; Humans; Imaging; Machine Learning; Medicine; Medicine & Public Health; Nuclear Medicine; Original Article; PET myocardial perfusion imaging; Positron-Emission Tomography - methods; Predictive Value of Tests; Radiology; Retrospective Studies; Vein & artery diseases; ICA; MPI; Rb-82; PET myocardial perfusion imaging; Coronary artery disease; MBF; CACS; CT; Ocad; Machine learning; MFR; PET; ML
• ISSN: 1071-3581; 1532-6551
• DOI: 10.1007/s12350-022-03166-3

Accurate risk stratification in patients with suspected stable coronary artery disease is essential for choosing an appropriate treatment strategy. Our aim was to develop and validate a machine learning (ML) based model to diagnose obstructive CAD (oCAD). We retrospectively have included 1007 patients without a prior history of CAD who underwent CT-based calcium scoring (CACS) and a Rubidium-82 PET scan. The entire dataset was split 4:1 into a training and test dataset. An ML model was developed on the training set using fivefold stratified cross-validation. The test dataset was used to compare the performance of expert readers to the model. The primary endpoint was oCAD on invasive coronary angiography (ICA). ROC curve analysis showed an AUC of 0.92 (95% CI 0.90-0.94) for the training dataset and 0.89 (95% CI 0.84-0.93) for the test dataset. The ML model showed no significant differences as compared to the expert readers (p ≥ 0.03) in accuracy (89% vs. 88%), sensitivity (68% vs. 69%), and specificity (92% vs. 90%). The ML model resulted in a similar diagnostic performance as compared to expert readers, and may be deployed as a risk stratification tool for obstructive CAD. This study showed that utilization of ML is promising in the diagnosis of obstructive CAD.