Diagnostic accuracy of artificial intelligence-enhanced coronary CT angiography for detecting functionally significant coronary artery disease: A systematic review and meta-analysis.
Clin ImagingJul 21, 2026 (epub)
Maurice Tiotsop, Douni O Roger, Utsab R Panta et al.
✦ AI-curated · Sources linked
In 30 seconds
This systematic review and meta-analysis evaluated the diagnostic accuracy of artificial intelligence-enhanced coronary CT angiography (CCTA) for detecting functionally significant coronary artery disease (CAD) in approximately 8400 participants. The study found a pooled sensitivity of 0.823 and specificity of 0.820 when using invasive fractional flow reserve (FFR) ≤ 0.80 as the reference standard.
Key findings
- Pooled sensitivity for AI-enhanced CCTA was 0.823 (95% CI, 0.761-0.872).
- Pooled specificity was 0.820 (95% CI, 0.732-0.883).
- Diagnostic performance remained consistent across various sensitivity analyses.
- Exploratory subgroup analyses showed generally consistent accuracy across different AI methodologies.
Why it matters
The findings suggest that AI-enhanced CCTA could serve as an effective noninvasive tool for assessing functionally significant CAD, potentially reducing unnecessary invasive procedures. This could improve patient management and resource allocation in cardiology.