Objective:

To explore the diagnostic performance of general practitioners (GPs) in carotid plaque detection using AI-enhanced point-of-care ultrasound (POCUS) after systematic training.

Approach:

• Study Design: A diagnostic accuracy trial conducted in Shanghai, involving 7 GPs who received systematic training and screened patients for carotid plaque.
• Evaluation Metrics: Diagnostic performance was evaluated using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and κ statistic for agreement.

Key Findings:

• 169 patients were included in the study, with a mean age of 69.6 years.
• At the per-patient level, sensitivity was 0.87, specificity was 0.91, PPV was 0.89, NPV was 0.89, and κ value was 0.78.
• Diagnostic performance at the per-vessel level was comparable to that at the per-patient level.

Interpretation:

Limitations:

• The study was conducted with a limited number of GPs and patients in a single location.
• The generalizability of the findings may be limited to similar healthcare settings.

Conclusion:

After systematic training, GPs can effectively utilize AI-enhanced POCUS for carotid plaque screening.