CONFIDENT-HFpEF: a machine learning-based risk stratification for mortality and hospitalization using multimodal real-world data
ESC Heart Failure · 04.07.2026 · 13 (4)
DOI: 10.1093/eschf/xvag097 ↗Kurz gefasst
Beobachtungsstudie in der Zeitschrift ESC Heart Failure, online erschienen am 07.04.2026. Verfasst von Marat Fudim und 20 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine, Duke University Medical Center Heart Center, 2301 Erwin Road, Durham, NC 27710, USA. Hauptthemen laut MEDLINE: Heart Failure, Hospitalization, Machine Learning, Stroke Volume. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Bristol Myers Squibb.
Abstract (Originalsprache)
Introduction
Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous condition with high morbidity and mortality. Accurate risk stratification is important for advancing drug development and improving clinical care.
Methods
CONFIDENT is an observational, multi-cohort study across three centres in Europe and the USA. Patients with HFpEF, according to the HFA-PEFF criteria, with ≥ 2 years of follow-up, were included from 2013 to 2022. Data include electronic health records, lab tests, echocardiography, and electrocardiography. We developed machine learning-based prognostic models to predict all-cause mortality and heart failure (HF) hospitalization. Model performance was compared to the validated risk score and validated in an external cohort.
Results
A total of 1208 patients were included in the study. The mean age was 72 ± 12, and the mean body mass index was 32 ± 9 kg/m2. The 2-year risk of HF hospitalization and all-cause mortality ranged from 13 to 44% and 9 to 19%, respectively. The all-cause mortality prognostic model achieved fair discrimination with a C-index of 0.68 [95% CI 0.62–0.74], and 0.71 [95% CI 0.64–0.78] in the training cohorts, and a good discrimination of 0.72 [95% CI 0.65–0.78] in the validation cohort but performed better than the PREDICT-HFpEF score (C-index: 0.66 [95% CI 0.54–0.72], P-value = .006; 0.65, [95% CI 0.55–0.72], P-value < .001 and 0.67 [95% CI 0.59–0.73], P-value = .036, respectively). Similar results were observed when compared to the Meta-Analysis Global Group In Chronic Heart Failure Risk Score (MAGGIC). The HF hospitalization model also outperformed both comparators, including MAGGIC+ natriuretic peptide.
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medicine, Duke University Medical Center Heart Center, 2301 Erwin Road, Durham, NC 27710, USA.
- Duke Clinical Research Institute, Durham, NC, USA.
- Department of Cardiology, Cardiovascular Research Institute Maastricht (CARIM), Maastricht University Medical Centre (MUMC+), Maastricht, The Netherlands.
- Owkin France, Paris, France.
- Duke Institute for Health Innovation, Durham, NC, USA.
- School of Medicine, Duke University, Durham, NC, USA.
ORCID-Profile: Vanessa Van Empel, Jerremy Weerts, Maxime Touzot
Förderung
- Bristol Myers Squibb
Zitieren
APA
Fudim, M., Van Empel, V., Zehnder, T., Sauty, B., Esposito, C., Balazard, F., Mayer, I., Hallal, M., Loiseau, N., Weerts, J., Patel, M., Balu, S., Hintze, B., Torres, F., Micsinai, M., Rigolli, M., Kessler, P., Touzot, M., Lund, L. H., …, & Butler, J. (2026). CONFIDENT-HFpEF: a machine learning-based risk stratification for mortality and hospitalization using multimodal real-world data. ESC Heart Failure, 13(4). https://doi.org/10.1093/eschf/xvag097
Vancouver
Fudim M, Van Empel V, Zehnder T, Sauty B, Esposito C, Balazard F, et al. CONFIDENT-HFpEF: a machine learning-based risk stratification for mortality and hospitalization using multimodal real-world data. ESC Heart Failure. 2026;13(4). doi:10.1093/eschf/xvag097
BibTeX
@article{Fudim2026,
author = {Fudim, Marat and Van Empel, Vanessa and Zehnder, Tobias and Sauty, Benoit and Esposito, Christian and Balazard, Félix and Mayer, Imke and Hallal, Mohammad and Loiseau, Nicolas and Weerts, Jerremy and Patel, Manesh and Balu, Suresh and Hintze, Bradley and Torres, Francisco and Micsinai, Mariann and Rigolli, Marzia and Kessler, Paul and Touzot, Maxime and Lund, Lars H and Pradhan, Aruna and Butler, Javed},
title = {CONFIDENT-HFpEF: a machine learning-based risk stratification for mortality and hospitalization using multimodal real-world data},
journal = {ESC Heart Failure},
year = {2026},
volume = {13},
number = {4},
doi = {10.1093/eschf/xvag097}
}
EUVIMED