Coronary disease & ACSSecondary analysis
Artificial intelligence-guided quantitative coronary CT assessment to rule-in or rule-out myocardial ischaemia
- post-hoc, vessel-level analysis
Authors' conclusion
A simplified framework incorporating AI-QCT parameters including diameter stenosis, PAV (>14.7%), and ALA (<3.9 mm2), stratifies myocardial ischaemia risk. Most non-obstructive lesions can be ruled-out, while most stenoses >70% are reliably ruled-in. This practical approach enhances the diagnostic utility of CCTA and streamlines clinical decision-making.
Study context
- Population
- Patients with suspected coronary artery disease who underwent CCTA and invasive fractional flow reserve (FFR)patients and vessels from the CREDENCE and PACIFIC-1 studies · CREDENCE patients 612 · CREDENCE vessels 1,727 · PACIFIC-1 patients 208 · PACIFIC-1 vessels 612
- Comparison
- AI-QCT parameters (diameter stenosis, percent atheroma volume (PAV) and average lumen area (ALA)) to rule-in or rule-out ischaemia against invasive fractional flow reserve (FFR)
- CREDENCEn = 612 patients; 1,727 vessels
- PACIFIC-1n = 208 patients; 612 vessels
Primary result
As reported in the abstract
Vessels with 1-24% stenosis ruled-out
- In CREDENCE, all vessels with 1-24% stenosis were ruled-out
Further findings
Vessels with 25-49% stenosis
- met rule-out criteria
- 74%
- intermediate risk, characterized by large PAV and small ALA
- 26%
- CREDENCE
Vessels with 50-69% stenosis
- classified as intermediate risk
Vessels with 70-99% stenosis
- met rule-in criteria, except a small subset with small PAV and large ALA
- 93%
Validation in PACIFIC-1
- vessels with <50% stenosis ruled-out
- 86%
- of those with 50-99% stenosis ruled-in
- 61%
Median thresholds derived from CREDENCE
- PAV
- 14.7%
- ALA
- 3.9 mm²
- validated in PACIFIC-1
Original publication
Artificial intelligence-guided quantitative coronary CT assessment to rule-in or rule-out myocardial ischaemia. Eur Heart J Cardiovasc Imaging. Published 13 April 2026. doi:10.1093/ehjci/jeag094
Summarised from the published abstract; every number is checked against it