Heart failure & cardiomyopathiesCohort study
CONFIDENT-HFpEF: a machine learning-based risk stratification for mortality and hospitalization using multimodal real-world data
- observational, multi-cohort study
- three centres in Europe and the USA
- machine learning-based prognostic models
- external validation cohort
Authors' conclusion
CONFIDENT prognostic models for all-cause mortality and HF hospitalization using routinely collected variables can reliably predict outcomes and potentially facilitate personalized care and trial recruitment strategies in HFpEF.
Study context
- Population
- Patients with heart failure with preserved ejection fraction (HFpEF) according to the HFA-PEFF criteria, with ≥ 2 years of follow-up, included from 2013 to 2022patients included in the study
- Participants
- 1,208 patients
- Exposure
- Model performance was compared to the validated risk score and validated in an external cohort.
Main finding
As reported in the abstract
Risk of HF hospitalization and all-cause mortality · 2 years
Heart failure (HF) hospitalization, range
13 to 44%
All-cause mortality, range
9 to 19%
Observational data: associations, not effects.
Further findings
| Outcome | CONFIDENT prognostic models | PREDICT-HFpEF score | MAGGIC | MAGGIC+ natriuretic peptide |
|---|---|---|---|---|
| All-cause mortality model discrimination (C-index) | ||||
| training cohorts | 0.68 [95% CI 0.62-0.74] | 0.66 [95% CI 0.54-0.72], P-value = .006 | Not reported in the abstract | Not reported in the abstract |
| validation cohort | 0.72 [95% CI 0.65-0.78] | 0.67 [95% CI 0.59-0.73], P-value = .036 | Not reported in the abstract | Not reported in the abstract |
- All-cause mortality model discrimination (C-index): fair discrimination in training cohorts; good discrimination in validation cohort
All-cause mortality model discrimination (C-index)
- Model performed better than the PREDICT-HFpEF score
All-cause mortality model vs MAGGIC
- Similar results were observed when compared to MAGGIC
HF hospitalization model discrimination
- The HF hospitalization model also outperformed both comparators, including MAGGIC+ natriuretic peptide
Baseline characteristics
- Mean age
- 72 ± 12
- Mean body mass index
- 32 ± 9 kg/m²
Original publication
CONFIDENT-HFpEF: a machine learning-based risk stratification for mortality and hospitalization using multimodal real-world data. ESC Heart Fail. Published 7 April 2026. doi:10.1093/eschf/xvag097
Summarised from the published abstract; every number is checked against it