A machine-learning model for accurate diuresis prediction in acute heart failure (DRC-AHF)
ESC Heart Failure · 2026
DOI: 10.1093/eschf/xvag185 ↗Kurz gefasst
Fachartikel in der Zeitschrift ESC Heart Failure, 2026. Verfasst von Gracjan Iwanek und 9 weiteren Autor:innen. Beteiligte Einrichtung: Clinical Department of Intensive Cardiac Care, Institute of Heart Diseases, Department of Cardiology, Faculty of Medicine, Wroclaw Medical University…. Hauptthemen laut MEDLINE: Heart Failure, Diuresis, Machine Learning, Glomerular Filtration Rate. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Institute of Heart Diseases, Wroclaw Medical University, Development Strategy of the Wroclaw Medical University.
Themen: Herzinsuffizienz
Abstract (Originalsprache)
Introduction
We aimed to develop a machine learning-based tool for accurate quantitative prediction of diuretic response in acute heart failure (AHF).
Methods
We prospectively enrolled 296 AHF patients (20% female, mean age 68 ± 13 years, mean estimated glomerular filtration rate (eGFR) 62 ± 30 ml/min/1.73m2, median NT-proBNP 7112 [4082–14 400] pg/ml) in a single-centre derivation/validation study. A random forest regression model was developed using derivation (n = 50) and optimization (n = 246) cohorts and externally validated in an independent cohort (n = 50; mean age 69 ± 14 years, mean eGFR 56 ± 27 ml/min/1.73m2). Predictors were eGFR, spot urine sodium (uNa), and urine creatinine (uCr) obtained 2 h after intravenous furosemide.
Results
In the validation cohort (n = 50), the median observed 6 h urine output was 1220 [950–1750] ml vs model-estimated 1446 [957–1749] ml (P = .480). Observed and estimated values showed a strong positive correlation (r = 0.90, 95% CI: 0.83–0.94, P < .0001), with a mean absolute error of 413 ml and a mean bias of 67 ± 383 ml on the Bland–Altman analysis. The model correctly classified 44/50 patients (88%) into predefined diuresis categories (≤900, 900–1800, and ≥1800 ml), compared with 58% for the reference natriuretic response prediction equation. Mean absolute error decreased progressively by approximately 200 ml per 100 additional patients, confirming data-driven performance improvement.
Conclusions
A three-variable machine learning model (eGFR, uNa, and uCr at 2 h post-diuretic) predicted 6 h urine output with high accuracy in AHF and demonstrated adaptive improvement with expanding training data. The calculator is freely available at https://diuresis.umw.edu.pl.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Clinical Department of Intensive Cardiac Care, Institute of Heart Diseases, Department of Cardiology, Faculty of Medicine, Wroclaw Medical University, Wroclaw, Poland.
- Jan Mikulicz Radecki University Hospital in Wroclaw, Poland.
- Office of the Institute of Heart Diseases, Institute of Heart Diseases, Faculty of Medicine, Wroclaw, Poland.
- Ikar Software, Wroclaw, Poland.
- Department of Drug Form Technology, Faculty of Pharmacy, Wroclaw Medical University, Wroclaw, Poland.
- Institute of Cardiology, Asst Spedali Civili, Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia, Italy.
ORCID-Profile: Gracjan Iwanek, Mateusz Guzik, Matteo Pagnesi, Jan Biegus
Förderung
- Institute of Heart Diseases
- Wroclaw Medical University
- Development Strategy of the Wroclaw Medical University
- 'UMW in the Light of Scientific Excellence 2024-2026'
Zitieren
APA
Iwanek, G., Guzik, M., Oleszczak, A., Karbowiak, I., Marciniak, D., Pagnesi, M., Nuñez, J., Zymliński, R., Ponikowski, P., & Biegus, J. (2026). A machine-learning model for accurate diuresis prediction in acute heart failure (DRC-AHF). ESC Heart Failure. https://doi.org/10.1093/eschf/xvag185
Vancouver
Iwanek G, Guzik M, Oleszczak A, Karbowiak I, Marciniak D, Pagnesi M, et al. A machine-learning model for accurate diuresis prediction in acute heart failure (DRC-AHF). ESC Heart Failure. 2026. doi:10.1093/eschf/xvag185
BibTeX
@article{Iwanek2026,
author = {Iwanek, Gracjan and Guzik, Mateusz and Oleszczak, Amadeusz and Karbowiak, Iga and Marciniak, Dominik and Pagnesi, Matteo and Nuñez, Julio and Zymliński, Robert and Ponikowski, Piotr and Biegus, Jan},
title = {A machine-learning model for accurate diuresis prediction in acute heart failure (DRC-AHF)},
journal = {ESC Heart Failure},
year = {2026},
doi = {10.1093/eschf/xvag185}
}
EUVIMED