Heart failure & cardiomyopathies
Predicting Survival in Patients with Severe Heart Failure: Risk Score Validation in the HELP-HF Cohort
Authors' conclusion
Most of the scores used to predict the risk of mortality in HF performed poorly in real-world patients with severe HF and provided inaccurate estimate of the risk of 1-year mortality in patients at the highest risk. ML-based models did not significantly outperform the currently available risk scores and their use must be validated in large cohort of patients.
Study context
- Population
- Patients with severe heart failure (HF) in the HELP-HF cohort497 with complete data
- Participants
- 1,149 patients
- Comparison
- Risk scores and machine learning (ML)-based models for predicting 1-year mortality
- Outcome
- Prognostic accuracy for mortality
- Follow-up
- 1 year
Performance
As reported in the abstract
Prognostic accuracy (AUC) for 1-year mortality
| Test or model | AUC |
|---|---|
| MAGGIC | ≥0.70 |
| GWTG-HF | ≥0.70 |
| ADHF/NT-proBNP | ≥0.70 |
AUC
MAGGIC≥0.70
GWTG-HF≥0.70
ADHF/NT-proBNP≥0.70
Further findings
1-year mortality
- Deaths
- 265 patients (23.1%)
Original publication
Predicting Survival in Patients with Severe Heart Failure: Risk Score Validation in the HELP-HF Cohort. Eur J Heart Fail. Published 20 January 2025. doi:10.
Summarised from the published abstract; every number is checked against it