Heart failure & cardiomyopathies
A Machine Learning-Derived Echocardiographic Algorithm Identifies People at Risk of Heart Failure with Distinct Cardiac Structure, Function, and Response to Spironolactone: Findings from the HOMAGE Trial
Authors' conclusion
In the HOMAGE trial, the e'VM algorithm identified echocardiographic phenotypes with distinct responses to spironolactone as assessed by changes in E/e' and BNP.
Study context
- Population
- People at high risk of developing heart failure (HF) (mean age 74 ± 7 years, 25% women) with available echocardiographic variables
- Participants
- 416 people
- Comparison
- Spironolactone vs placebo across e'VM echocardiographic phenotypes
- Primary endpoint
- Effects of spironolactone on changes in echocardiographic and biomarker variables across e'VM phenotypes
- Follow-up
- 9 months
Methodological detailsmachine-learning-derived echocardiographic algorithm, external validation
- Machine-learning-derived echocardiographic algorithm
- External validation
Primary result
As reported in the abstract
E/e' and BNP, by e'VM phenotype (subgroup analysis)
- Spironolactone significantly reduced E/e' and BNP in the D/S phenotype
- p < 0.01
- No significant reduction in other phenotypes
- p > 0.10
- Interaction for E/e' and BNP
- pinteraction <0.05 for both
Further findings
Phenotype distribution and characteristics
- Majority had 'diastolic changes' (D) or 'diastolic changes with structural remodelling' (D/S) phenotype
- >80%
- D/S phenotype had highest LVMi, left atrial volume, E/e', natriuretic peptide and troponin levels
- all p < 0.05
Original publication
A Machine Learning-Derived Echocardiographic Algorithm Identifies People at Risk of Heart Failure with Distinct Cardiac Structure, Function, and Response to Spironolactone: Findings from the HOMAGE Trial. Eur J Heart Fail. Published 26 April 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →