Classification of carotid plaque vulnerability by neurosurgical residents using ultrasonography in the clinical field

Doyoung Na1, Junmo Kim1, Kyungmin Chung1, Seunghun Han1, Gihyeok Yun1, Jinseo Yang1, Hyukjai Choi1, Heung Cheol Kim2, Yongjun Cho1, Jin Pyeong Jeon1

DOI: https://doi.org/10.51638/jksgn.2022.00094

Objective: We aimed to evaluate the accuracy of the classification of carotid plaque vulnerability (unstable vs. stable plaques) by neurosurgical residents based on carotid ultrasonography (US) images.

Methods: A total of 405 subjects with 995 images were included in the study. Using a neuroradiologist’s decision as the reference value, the classification results of five reviewers were analyzed. The sensitivity, specificity, and overall accuracy were estimated. Then, a pairwise comparison of the receiver operating characteristic (ROC) curve and precision-recall curve was performed to compare the

reviewers’ classification accuracy.

Results: The mean age of the subjects was 70.5 years (range, 44–91 years) and 223 (55.1%) were female. The number of unstable and stable plaques was 236 (24.7%) and 749 (75.3%), respectively. The best-balanced classification performance of plaque vulnerability was a sensitivity of 83.7% (95% confidence interval [CI], 78.5%–88.1%), specificity of 69.0% (95% CI, 65.6%–72.3%), and

overall accuracy of 72.7% (95% CI, 69.8%–75.4%). The best ROC performance was an area under the curve (AUC) of 0.583 (95% CI, 0.552–0.614). The precision-recall curve also showed low classification accuracy among the reviewers (AUC difference: 0.028; 95% bootstrap CI, 0.007–0.048).

Conclusion: The classification accuracy of neurosurgical residents to discriminate plaque vulnerability seen on carotid US images

was low in a real-world clinical setting. Thus, it is necessary to develop systems that help to educate and automatically interpret

plaque stability. 

https://www.jksgn.org/journal/view.php?doi=10.51638/jksgn.2022.00094