Heart failure & cardiomyopathies
An Individual Treatment Effect Approach to Predict Response to Mineralocorticoid Receptor Antagonists in Patients with Heart Failure and Reduced Ejection Fraction
Authors' conclusion
In HFrEF across various clinical settings, our simple ITE model predicted individual responses to MRA therapy.
Study context
- Population
- Patients with HFrEF (derivation: RALES and EMPHASIS-HF); validation: LV systolic dysfunction and/or heart failure (HF) after MI (EPHESUS)derivation
- Participants
- 3,887 patients
- Comparison
- MRA vs placebo
- Primary endpoint
- CV death or HF hospitalization
- Follow-up
- 2-year period
Methodological detailsprediction model development and validation, counterfactual random forest, linear regression individual treatment effect (ITE) prediction model, external validation in EPHESUS
- Prediction model development and validation
- Counterfactual random forest
- Linear regression ITE prediction model
- External validation in EPHESUS
Primary result
As reported in the abstract
CV death or HF hospitalization: MRA treatment effect by ITE score (RALES and EMPHASIS-HF, n = 3887) · 2 years
Each group vs placeboHazard ratio (95% CI)
ITE score 5
0.82(0.67–1.02)
ITE score 20
0.47(0.35–0.63)
Further findings
Validation in EPHESUS
- Similar pattern: greater treatment effects with higher ITE scores
- p for interaction = 0.007
Original publication
An Individual Treatment Effect Approach to Predict Response to Mineralocorticoid Receptor Antagonists in Patients with Heart Failure and Reduced Ejection Fraction. Eur J Heart Fail. Published 16 September 2025. doi:10.
Summarised from the published abstract; every number is checked against it