Heart failure & cardiomyopathiesDiagnostic or prognostic study
Independent external validation of the LIFE-HF clinical prediction model using the GUIDE-IT trial
- external validation
- independent
- patient-level data from the GUIDE-IT trial
- multiple imputation
Authors' conclusion
In a contemporary, high-risk North American HF with reduced ejection fraction cohort, the LIFE-HF models showed good discrimination but systematically underpredicted 1-year risk. The mortality model may support risk-informed decision-making, whereas the composite model requires further validation.
Study context
- Population
- Contemporary, high-risk North American heart failure (HF) with reduced ejection fraction cohort (GUIDE-IT trial participants)validation cohort (median age 64 years, 69% male)
- Participants
- 801 participants
- Comparison
- LIFE-HF models for 1-year all-cause death and the composite of death or HF hospitalization, externally validated using patient-level data from the GUIDE-IT trial
Further findings
- Mortality model performance (1-year all-cause death)
- 0.77, 95% confidence interval (CI): 0.72-0.82 · AUROC · O/E 1.28, 95% CI: 1.01-1.54 · calibration slope 1.58, 95% CI: 1.20-1.95
- Composite model performance (death or HF hospitalization) · 1-year
- 0.69, 95% CI: 0.64-0.73 · AUROC · O/E 1.40, 95% CI: 1.25-1.54 · calibration slope 0.82, 95% CI: 0.63-1.00
Mortality model performance (1-year all-cause death)
- good discrimination
- underprediction
- underfitting
Composite model performance (death or HF hospitalization) · 1-year
- moderate discrimination
- underprediction
- overfitting
Decision curve analysis (net clinical benefit)
- Net clinical benefit for the mortality model, but not the composite model, over a broad range of risk thresholds
Original publication
Independent external validation of the LIFE-HF clinical prediction model using the GUIDE-IT trial. ESC Heart Fail. Published 13 January 2026. doi:10.1093/eschf/xvag007
Summarised from the published abstract; every number is checked against it