Real-time prediction of atrial fibrillation in intensive care unit: a meta-learning approach
JAMIA Open · 07.07.2026 · 9 (4)
DOI: 10.1093/jamiaopen/ooag110 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 11.07.2026. Verfasst von Mehran Moazeni und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Methodology and Statistics, Utrecht University, Padualaan 14, 3584 CH Utrecht, The Netherlands. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Dutch national e-infrastructure Research Cloud, Dutch Research Council.
Themen: Intensivpflege
Abstract (Originalsprache)
Objective
Atrial fibrillation (AF) is a common arrhythmia affecting a large fraction of patients in intensive care units (ICUs). Predicting patients at risk of AF in the ICU is a challenging task and is not commonly practiced but could have clinical implications considering that AF is a proxy for poorer outcomes. Our goal is to develop a real-time AF prediction model using ICU numerical data to improve alarm quality, helping clinicians to identify at-risk patients and intervene before AF onset, thereby potentially improving clinical outcomes.
Methods
We employed AmsterdamUMCdb, Europe’s first openly accessible ICU dataset. The dataset includes static features, including demographics, as well as dynamic bedside monitoring data, like blood pressure and respiratory rate, along with detailed records of medication and fluid administration. To enhance generalizability across diverse ICU patients, we trained a long short-term memory (LSTM) model combined with a Model-Agnostic Meta-Learning (MAML) approach. Model performance was tested on an imbalanced test set, reflective of the real-world ratio of AF to non-AF patients. Direct external validation was performed using the MIMIC-IV database to test generalizability across different clinical settings.
Results
The LSTM-MAML model achieved an AUC of 0.92, accuracy of 0.89, and precision of 0.29 on the internal validation set. In external validation with MIMIC-IV, it showed near-equivalent performance with an AUC of 0.89, accuracy of 0.85, and precision of 0.18.
Conclusions
The real-time prediction model demonstrated predictive value for AF and has potential for future clinical benefits. However, for clinical implementation, further refinement is necessary to improve its performance in identifying patients at risk for AF.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Methodology and Statistics, Utrecht University, Padualaan 14, 3584 CH Utrecht, The Netherlands.
- Department of Cardiology, University Medical Centre Utrecht, Utrecht University, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands.
- Computational Imaging Group for MRI Therapy & Diagnostics, University Medical Centre Utrecht, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands.
- Department of Intensive Care Medicine, Center for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam Public Health, Amsterdam Institute for Immunity and Infectious Diseases, Amsterdam Ca…
- The National Institute for Health and Care Research (NIHR), University College London Biomedical Research Centre (BRC), University College London, Gower Street, London, WC1E 6BT, United Kingdom.
- Health Data Research United Kingdom and Institute of Health Informatics, University College London, 222 Euston Road, London, NW1 2DA, United Kingdom.
ORCID-Profile: Mehran Moazeni, Sebastian Mildiner Moraga, Paul Elbers, Patrick Thoral, Linda Wilhelmina Van Laake, Folkert Wouter Asselbergs, Emmeke Aarts
Förderung
- Dutch national e-infrastructure Research Cloud
- Dutch Research Council
Zitieren
APA
Moazeni, M., Moraga, S. M., Wösten, M., Elbers, P., Thoral, P., Van Laake, L. W., Asselbergs, F. W., & Aarts, E. (2026). Real-time prediction of atrial fibrillation in intensive care unit: a meta-learning approach. JAMIA Open, 9(4). https://doi.org/10.1093/jamiaopen/ooag110
Vancouver
Moazeni M, Moraga SM, Wösten M, Elbers P, Thoral P, Van Laake LW, et al. Real-time prediction of atrial fibrillation in intensive care unit: a meta-learning approach. JAMIA Open. 2026;9(4). doi:10.1093/jamiaopen/ooag110
BibTeX
@article{Moazeni2026,
author = {Moazeni, Mehran and Moraga, Sebastian Mildiner and Wösten, Maaike and Elbers, Paul and Thoral, Patrick and Van Laake, Linda Wilhelmina and Asselbergs, Folkert Wouter and Aarts, Emmeke},
title = {Real-time prediction of atrial fibrillation in intensive care unit: a meta-learning approach},
journal = {JAMIA Open},
year = {2026},
volume = {9},
number = {4},
doi = {10.1093/jamiaopen/ooag110}
}
EUVIMED