AI-Defined Cardiac Anatomy Improves Risk Stratification of Hybrid Perfusion Imaging
Main finding · MACEResult — go to the resultHazard ratio 1.46 to 3.31Authors' conclusion
AI can automatically derive LV mass and cardiac chamber volumes from CT attenuation imaging, significantly improving cardiovascular risk assessment for hybrid perfusion imaging.
Study context
- Population
- Patients without known CAD undergoing SPECT/CT myocardial perfusion imaging
- Participants
- 7,613 patients
- Exposure
- Highest vs lowest quartile of artificial intelligence (AI)-derived LV mass and chamber volumes from computed tomography attenuation correction (CTAC)
- Outcome
- MACE:
- Death
- MI
- Unstable angina
- Revascularization
- Follow-up
- Median 2.4 years
Methodological details3 centres, consecutive patients
- 3 centres
- Consecutive patients
Main finding
MACE · median 2.4 years (IQR: 1.3-3.4 years)
Hazard ratio
1.46 to 3.31
As reported in the abstract
- MACE occurred
- 1,045 (13.7%)
- Addition of all CT-based volumes and LV mass improved continuous net reclassification index
- 23.1%
Observational data: associations, not effects.
Further findings
Fully automated AI processing time
- Coronary artery calcium (CAC)
- 6.2 ± 0.2 seconds
- Cardiac volumes and LV mass
- 15.8 ± 3.2 seconds
- Average
Original publication
AI-Defined Cardiac Anatomy Improves Risk Stratification of Hybrid Perfusion Imaging. JACC Cardiovasc Imaging. Published 6 March 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →