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

Autor: van Dalen JA; Department of Medical Physics, Isala Hospital, PO Box 10400, 8000 GK, Zwolle, The Netherlands. jo.van.dalen@isala.nl., Koenders SS; Department of Nuclear Medicine, Isala Hospital, Zwolle, The Netherlands.; Technical Medical Centre, University of Twente, Enschede, The Netherlands., Metselaar RJ; Department of Nuclear Medicine, Isala Hospital, Zwolle, The Netherlands.; Technical Medical Centre, University of Twente, Enschede, The Netherlands., Vendel BN; Department of Nuclear Medicine, Isala Hospital, Zwolle, The Netherlands., Slotman DJ; Department of Radiology, Isala Hospital, Zwolle, The Netherlands., Mouden M; Department of Cardiology, Isala Hospital, Zwolle, The Netherlands., Slump CH; Technical Medical Centre, University of Twente, Enschede, The Netherlands., van Dijk JD; Department of Nuclear Medicine, Isala Hospital, Zwolle, The Netherlands.
Jazyk: angličtina
Zdroj: Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology [J Nucl Cardiol] 2023 Aug; Vol. 30 (4), pp. 1504-1513. Date of Electronic Publication: 2023 Jan 09.
DOI: 10.1007/s12350-022-03166-3
Abstrakt: Introduction: 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).
Method: 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).
Results: 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%).
Conclusion: 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.
(© 2023. The Author(s) under exclusive licence to American Society of Nuclear Cardiology.)
Databáze: MEDLINE
Externí odkaz: