Related Experiment Video
Updated: Mar 6, 2026
08:10
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
2.2K
Association between deep learning-based atrial fibrillation burden and in-hospital mortality
Yongseop Lee1, Yujee Chang2, Jihoon Seo2
1Division of Infectious Diseases, Department of Internal Medicine and AIDS Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea.
PLOS Digital Health
|March 4, 2026
Summary
High atrial fibrillation (AF) burden in critically ill patients is linked to increased in-hospital mortality. This dynamic AF burden metric can predict patient outcomes and clinical deterioration in intensive care units.
Area of Science:
- Critical Care Medicine
- Cardiology
- Medical Informatics
Background:
- Atrial fibrillation (AF) is common in critically ill patients, but its role as a dynamic predictor of adverse outcomes is understudied.
- Existing research lacks real-time assessment of AF burden in intensive care unit (ICU) settings.
Purpose of the Study:
- To investigate the association between high AF burden and in-hospital mortality in critically ill patients.
- To evaluate AF burden as a dynamic, real-time predictor of mortality and clinical deterioration.
Main Methods:
- Utilized deep learning models to analyze electrocardiogram (ECG) waveform data for AF burden calculation.
- Included adult ICU patients from MIMIC-III and Yongin Severance Hospital databases.
- Defined high AF burden as ≥7.0% of AF waveforms during ICU admission; employed logistic regression and machine learning for analysis.
Main Results:
- High AF burden (median 22.5%) was significantly associated with increased in-hospital mortality (18.1% vs. 8.6%, P<0.001).
- AF burden independently predicted mortality (adjusted OR, 1.63; 95% CI, 1.36-1.95; P<0.001).
- Machine learning models showed AF burden significantly contributes to mortality prediction (AUC=0.86).
Conclusions:
- High AF burden is an independent risk factor for in-hospital mortality in critically ill patients.
- AF burden can serve as a dynamic marker for real-time clinical deterioration alerts.
- AF burden aids in risk stratification for critically ill patients, improving outcome prediction.
