Diagnostic Performance of General Practitioners in Carotid Plaque Detection Using AI-Enhanced Point-of-Care Ultrasound After Systematic Training - Report - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Evaluating the Diagnostic Accuracy of General Practitioners in Identifying Carotid Plaque with AI-Enhanced Point-of-Care Ultrasound Following Comprehensive Training

  • By

  • Xiaochuan Liu

  • Sichen Yao

  • Hua Yang

  • Zhigang Pan

  • May 1, 2026

Share

Clinical Report: Diagnostic Accuracy of GPs in Carotid Plaque Detection

Overview

This study evaluates the diagnostic performance of general practitioners (GPs) in detecting carotid plaque using AI-enhanced point-of-care ultrasound (POCUS) after systematic training. The results indicate high sensitivity and specificity.

Background

Carotid plaque is a significant risk factor for atherosclerotic cardiovascular disease (ASCVD), making early detection crucial for timely intervention. While POCUS has been adopted in various countries, its application by Chinese GPs remains underexplored.

Data Highlights

MetricValue95% CI
Sensitivity0.870.80-0.95
Specificity0.910.86-0.97
Positive Predictive Value0.890.82-0.96
Negative Predictive Value0.890.83-0.96
κ Statistic0.780.69-0.88

Key Findings

  • Seven GPs underwent systematic training in AI-enhanced POCUS for carotid plaque detection.
  • The study included 169 patients with a mean age of 69.6 years.
  • At the per-patient level, sensitivity was 0.87 and specificity was 0.91.
  • Positive and negative predictive values were both 0.89.
  • The κ statistic indicated high agreement with the gold standard at 0.78.
  • Diagnostic performance at the per-vessel level was comparable to the per-patient level.

Clinical Implications

The findings indicate the potential for GPs to utilize AI-enhanced POCUS for carotid plaque screening.

Conclusion

The study demonstrates that GPs, after receiving systematic training, can accurately perform carotid plaque screening using AI-enhanced POCUS.

Related Resources & Content

  1. Author(s)/Org, Source, Year -- Title
  2. Author(s)/Org, Source, Year -- Title
  3. Author(s)/Org, Source, Year -- Title
  4. Author(s)/Org, Source, Year -- Title
  5. Recommendation: Asymptomatic Carotid Artery Stenosis: Screening | United States Preventive Services Taskforce
  6. Author(s)/Org, Source, Year -- Title
  7. Author(s)/Org, Source, Year -- Title
  8. Recommendation: Asymptomatic Carotid Artery Stenosis: Screening | United States Preventive Services Taskforce
  9. Machine learning models for carotid artery plaque detection: A systematic review of ultrasound-based diagnostic performance - ScienceDirect
  10. General practitioners’ scanning competence following tailored ultrasound training: a hybrid effectiveness-implementation study | BMC Medical Education | Springer Nature Link

Original Source(s)

Related Content