Back to the list
Congress: ECR25
Poster Number: C-19973
Type: Poster: EPOS Radiologist (scientific)
Authorblock: B. Liu1, J. Reis2; 1Shanghai/CN, 2Lisbon/PT
Disclosures:
Baiyun Liu: Employee: Medical
Joana Reis: Nothing to disclose
Keywords: Artificial Intelligence, Cardiac, Cardiovascular system, CAD, CT, CT-Angiography, CAD, Computer Applications-Detection, diagnosis, Efficacy studies, Calcifications / Calculi, Obstruction / Occlusion
Conclusion

This systematic review and meta-analysis evaluated existing evidence on the application of AI to non-invasive CAD imaging and the diagnostic performance of AI applications in CAD imaging. To our knowledge, this is the first meta-analysis to assess the diagnostic perfomance of AI applications for detection coronary arteries with ≥50% stenosis. We found that most studies were conducted in China and the USA, and the majority had sample sizes of 100–500 patients. AI applications demonstrated good diagnostic performance for detecting ≥50% stenosis in a meta-analysis using both patient-level and vessel-level data from patients with known or suspected CAD. A meta-analysis of plaque imaging studies was not undertaken due to variability in how AI was used to quantify plaques, highlighting the need for additional studies to assess the diagnostic performance of AI in plaque imaging. 

GALLERY