Opportunistic assessment of abdominal aortic calcification using artificial intelligence (AI) predicts coronary artery disease and cardiovascular events
Authors' conclusion
Using opportunistic abdominal CTs, assessment of AAC using a fully automated AI algorithm, predicted CAC and was independently associated with cardiovascular events.
Study context
- Population
- Patients who underwent both noncontrast abdominal computed tomography (CT) for routine care and cardiac CT for coronary artery calcification (CAC) assessment
- Participants
- 3,599 patients
- Exposure
- AI-quantified abdominal aortic calcification (AAC) on opportunistic abdominal CT as predictor of CAC and CV events
- Outcome
- Detection of any CAC
Main finding
As reported in the abstract
| Group | AUC |
|---|---|
| PREVENT | 0.701 [0.683-0.718] |
| PREVENT plus AAC | 0.782 [0.767-0.797] |
AUC
PREVENT0.701 [0.683-0.718]
PREVENT plus AAC0.782 [0.767-0.797]
- PREVENT plus AAC vs PREVENT: P < 0.001
- Correlation between presence and severity of AAC and CAC
- r = 0.56, P < .001
Observational data: associations, not effects.
Further findings
Major adverse cardiovascular events (MACE) (death, MI, ischemic stroke, coronary revascularization), adjusted for PREVENT score · median 36 months
- Presence of AAC associated with significant risk of MACE
- adjHR 2.26 (1.67-3.07), P < .001 (95% CI)
- Doubling of AAC score: increase in MACE risk
- 11%
- 324 MACE
Major coronary events (MCE) (MI or coronary revascularization), adjusted for PREVENT score · median 36 months
- Presence of AAC associated with significant risk of MCE
- adjHR 2.58 (1.80-3.71), P < .001 (95% CI)
- Doubling of AAC score: increase in MCE risk
- 13%
- 246 MCE
Original publication
Opportunistic assessment of abdominal aortic calcification using artificial intelligence (AI) predicts coronary artery disease and cardiovascular events. Am Heart J. Published 24 April 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →