Artificial intelligence algorithms demonstrated high diagnostic performance in distinguishing unstable from stable carotid plaques across medical imaging modalities, achieving a pooled AUC of 0.94.
Meta-Analysis
Does artificial intelligence improve diagnostic accuracy in identifying unstable carotid plaques in medical imaging?
AI algorithms demonstrate high diagnostic accuracy for identifying unstable carotid plaques on medical imaging, though clinical translation requires further external validation.
Effect estimate: AUC 0.94 (95% CI 0.91-0.95)
BACKGROUND: Atherosclerosis in the carotid artery significantly contributes to embolic events leading to ischemic stroke. Precise identification of unstable carotid plaques through non-invasive imaging, is pivotal for stroke prevention. Artificial intelligence (AI) has demonstrated promise in enhancing the accuracy of plaque risk stratification. This review aims to assess the diagnostic performance of AI algorithms in distinguishing unstable carotid plaques from stable plaques using medical imaging. METHODS: We conducted comprehensive searches in Medline, Embase, Web of Science, IEEE, PubMed, and the Cochrane Library up to June 6, 2023. Eligible studies included those that utilized AI algorithms for identifying unstable carotid plaques from medical images. Binary diagnostic accuracy metrics, including sensitivity, specificity, and Area Under the Curve (AUC), were extracted. QUADAS-AI was used to assess risk of bias of the included studies. RESULTS: > 90%). Subgroup analyses indicated performance variations based on factors such as sample size, type of AI algorithms (machine learning or deep learning), segmentation methods (manual or automatic), and publication year. Despite observed publication bias and study heterogeneity, the findings underscore the promise of AI-driven approaches in carotid plaque risk stratification. CONCLUSIONS: AI algorithms demonstrated favorable diagnostic performance in identifying unstable carotid plaques. Future research should focus on rigorous validation, ensuring generalizability, and enhancing the explainability of AI algorithms to facilitate their translational use. CLINICAL TRIAL NUMBER: Not applicable.
Feng et al. (Tue,) conducted a meta-analysis in Unstable carotid plaques. Artificial intelligence (AI) algorithms was evaluated on Diagnostic performance (Area Under the Curve) for identifying unstable carotid plaques (AUC 0.94, 95% CI 0.91-0.95). Artificial intelligence algorithms demonstrated high diagnostic performance in distinguishing unstable from stable carotid plaques across medical imaging modalities, achieving a pooled AUC of 0.94.