Heart failure & cardiomyopathies
Prognostic impact of artificial intelligence-based fully automated global circumferential strain in patients undergoing stress CMR
Authors' conclusion
Stress-GCS is not a predictor of MACE in patients with ischaemia, but has an incremental prognostic value in those with a normal CMR although the absolute event rate remains low.
Study context
- Population
- Consecutive patients undergoing vasodilator stress CMR, 2016–20181:1 matched
- Participants
- 2,152 patients
- Exposure
- Abnormal stress CMR vs normal stress CMR
- Normal CMRn = 1,076reference
- Abnormal CMRn = 1,076
- Outcome
- Major adverse clinical events (MACE):
- Cardiovascular (CV) mortality
- Nonfatal MI
- Follow-up
- Median 5.2 (4.8-5.5) years
Methodological detailspropensity-score matched, consecutive patients, Stress-GCS by fully automatic machine-learning feature-tracking algorithm on short-axis cine images
- Propensity-score matched
- Consecutive patients
- Stress-GCS by fully automatic machine-learning feature-tracking algorithm on short-axis cine images
Main finding
As reported in the abstract
Association of stress-GCS with MACE (adjusted)
Adjusted hazard ratio (95% CI)P value
Propensity-matched population
1.12(1.06–1.18)
P < 0.001Normal CMR
1.35(1.19–1.53)
P < 0.001Per stress-GCS, as printed
Observational data: associations, not effects.
Further findings
Incremental discrimination/reclassification of stress-GCS in normal CMR
- C-statistic improvement
- 0.14
- NRI
- 0.430
- IDI
- 0.089
- All P
- P < 0.001
- LR-test
- P < 0.001
Original publication
Prognostic impact of artificial intelligence-based fully automated global circumferential strain in patients undergoing stress CMR. Eur Heart J Cardiovasc Imaging. Published 9 May 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →