Importance of validation of accuracy of duplex ultrasonography in identifying moderate and severe carotid artery stenosis

Abstract

Background and purpose: The accuracy of carotid duplex ultrasonography (CDU) in detecting moderate and severe carotid artery disease was evaluated in comparison with arteriography.

Methods: Accuracy of CDU was correlated with arteriographic findings using North American Symptomatic Carotid Endarterectomy Trial (NASCET) criteria in 147 internal carotid arteries. The duplex measurements consisted of peak systolic velocities (PSVs), end diastolic velocities (EDVs), and internal carotid PSV to common carotid artery PSV ratios (ICA/CCA). Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and overall accuracy (OA) using the 3 parameters were determined. Receiver operating characteristic (ROC) curves were constructed from the ultrasonographic data for detection of 50% or greater stenosis (moderate disease) and 70% or greater stenosis (severe disease).

Results: CDU for detecting ≥ 50% stenosis had a sensitivity of 100%, specificity of 87.8%, and accuracy of 96.6%. The area under the ROC curves for PSV was 0.86 (95% confidence interval [CI] 0.80-0.93), for EDV was 0.86 (95% CI 0.80-0.92), and for ICA:CCA ratio was 0.95 (CI 0.91-0.99). CDU for detecting ≥ 70% stenosis had a sensitivity of 100%, specificity of 87.1%, and accuracy of 94.5%. The area under the ROC curves for PSV was 0.76 (95% CI 0.68-0.84), for EDV was 0.74 (95% CI of 0.65-0.82), and for ICA/CCA ratio was 0.89 (0.84-0.94).

Conclusions: We conclude that ≥ 50% stenosis and ≥ 70% stenosis can be reliably determined by CDU in our vascular laboratory. Each vascular laboratory must validate their own criteria against the current gold standard of carotid arteriography. A high degree of confidence in CDU is critical before any institution uses the test as the sole diagnostic method prior to carotid intervention.