Deep learning models based on coronary angiography and coronary CT angiography demonstrated an accuracy of 0.73 for detecting >50% coronary artery stenosis at the vessel level.
Meta-Analysis (n=3,568)
Do deep learning models based on CAG or CCTA images accurately detect the degree of coronary artery stenosis?
Deep learning models based on CAG and CCTA demonstrate relatively high accuracy in diagnosing varying degrees of coronary artery stenosis, though further improvement is needed for clinical application.
Effect estimate: Accuracy 0.73 (95% CI 0.58-0.88)
BACKGROUND: In recent years, as deep learning has received widespread attention in the field of heart disease, some studies have explored the potential of deep learning based on coronary angiography (CAG) or coronary CT angiography (CCTA) images in detecting the extent of coronary artery stenosis. However, there is still a lack of a systematic understanding of its diagnostic accuracy, impeding the advancement of intelligent diagnosis of coronary artery stenosis. Therefore, we conducted this study to review the accuracy of image-based deep learning in detecting coronary artery stenosis. METHODS: We retrieved PubMed, Cochrane, Embase, and Web of Science until April 11, 2023. The risk of bias in the included studies was appraised using the QUADAS-2 tool. We extracted the accuracy of deep learning in the test set and performed subgroup analyses by binary and multiclass classification scenarios. We performed a subgroup analysis based on different degrees of stenosis and applied a double arcsine transformation to process the data. The analysis was done by using R. RESULTS: Our systematic review finally included 18 studies, involving 3568 patients and 13,362 images. In the included studies, deep learning models were constructed based on CAG and CCTA. In binary classification tasks, the accuracy for detecting > 25%, > 50% and > 70% degrees of stenosis at the vessel level were 0.81 (95% CI: 0.71-0.85), 0.73 (95% CI: 0.58-0.88) and 0.61 (95% CI: 0.56-0.65), respectively. In multiclass classification tasks, the accuracy for detecting 0-25%, 25-50%, 50-70%, and 70-100% degrees of stenosis at the vessel level were 0.78 (95% CI: 0.73-0.84), 0.86 (95% CI: 0.78-0.93), 0.83 (95% CI: 0.70-0.97), and 0.70 (95% CI: 0.42-0.98), respectively. CONCLUSIONS: Our study shows that deep learning models based on CAG and CCTA appear to be relatively accurate in diagnosing different degrees of coronary artery stenosis. However, for various degrees of stenosis, their accuracy still needs to be further improved.
Tu et al. (Mon,) conducted a meta-analysis in Coronary artery stenosis (n=3,568). Deep learning models based on CAG and CCTA was evaluated on Accuracy for detecting > 50% degree of stenosis at the vessel level in binary classification tasks (Accuracy 0.73, 95% CI 0.58-0.88). Deep learning models based on coronary angiography and coronary CT angiography demonstrated an accuracy of 0.73 for detecting >50% coronary artery stenosis at the vessel level.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: