Heart failure & cardiomyopathies
Artificial intelligence-based fully automated stress left ventricular ejection fraction as a prognostic marker in patients undergoing stress cardiovascular magnetic resonance
Main finding · All-cause deathResult — go to the resultAdjusted hazard ratio 0.84 95% CI 0.82–0.87Authors' conclusion
AI-based fully automated LVEF measured at stress is independently associated with the occurrence of death in patients undergoing stress CMR, with an additional prognostic value above traditional risk factors, inducible ischaemia and late gadolinium enhancement.
Study context
- Population
- Consecutive patients referred for vasodilator stress cardiovascular magnetic resonance (CMR), 2016–2018
- Participants
- 9,712 patients
- Exposure
- Stress artificial intelligence (AI)-based LVEF (left ventricular ejection fraction (LVEFAI)) as a prognostic marker vs traditional risk factors and CMR findings
- Outcome
- All-cause death (French National Registry of Death)
- Follow-up
- Median 4.5 (IQR 3.7-5.2) years
Methodological detailsconsecutive patients, longitudinal
- Consecutive patients
- Longitudinal
Main finding
All-cause death · median follow-up 4.5 (3.7-5.2) years
Adjusted hazard ratio
0.84
95% CI 0.82–0.87
P < 0.001
Stress LVEFAI (per 5% increment)
adjusted HR 0.84 (95% CI 0.82–0.87); P < 0.001
Per 5% increment, as printed
As reported in the abstract
Observational data: associations, not effects.
Further findings
Correlation of stress LVEFAI with expert-measured LVEF
- Correlation r
- 0.94
- P < 0.001
Incremental prognostic value over traditional risk factors and stress CMR findings
- C-statistic improvement
- 0.11
- Net reclassification improvement
- 0.250
- Integrative discrimination index
- 0.049
- Likelihood-ratio test
- P < 0.001
- All P < 0.001
- Incremental prognostic value over LVEFAI at rest
Original publication
Artificial intelligence-based fully automated stress left ventricular ejection fraction as a prognostic marker in patients undergoing stress cardiovascular magnetic resonance. Eur Heart J Cardiovasc Imaging. Published 10 July 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →