Related Experiment Video
Updated: Jul 11, 2025
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Automated atrial fibrillation and ventricular fibrillation recognition using a multi-angle dual-channel fusion
Weiyi Yang1, Di Wang2, Wei Fan3
1School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, China.
Insights
A new multi-angle dual-channel fusion network (MDF-Net) accurately detects atrial fibrillation (AFIB) and ventricular fibrillation (VFIB) from ECGs. This AI tool offers faster training and reliable diagnosis, even with noisy or imbalanced data.
Area of Science:
- Cardiovascular Medicine and Artificial Intelligence
- Biomedical Signal Processing
Background:
- Atrial fibrillation (AFIB) and ventricular fibrillation (VFIB) are leading causes of global mortality.
- Electrocardiograms (ECGs) are crucial for diagnosing AFIB and VFIB, but subtle changes challenge visual interpretation.
- Automated diagnostic tools are needed to improve accuracy and efficiency in detecting these arrhythmias.
Purpose of the Study:
- To develop and validate a novel deep learning model for the automatic recognition of AFIB and VFIB heartbeats.
- To enhance diagnostic accuracy by fusing multi-angle features extracted from two-lead ECG signals.
- To create a computationally efficient diagnostic tool for clinical application.
Main Methods:
- Proposed a multi-angle dual-channel fusion network (MDF-Net) integrating task-related component analysis (TRCA)-principal component analysis (PCA) and canonical correlation analysis (CCA)-PCA networks.
- Employed TRPC-Net and CPC-Net for deep feature extraction from two-lead ECGs, enabling multi-angle feature-level fusion.
- Utilized linear support vector machine-weighted softmax with average (LS-WSA) for decision-level fusion and classification.
Main Results:
- Achieved high diagnostic accuracies of 99.39% in intra-patient and 97.17% in inter-patient experiments for distinguishing AFIB and VFIB.
- Demonstrated robust performance on noisy ECG data, maintaining accuracy despite signal interference.
- Showcased effectiveness on extremely imbalanced datasets, accurately identifying rare abnormal heartbeats.
Conclusions:
- The proposed MDF-Net offers a highly accurate and efficient method for automated AFIB and VFIB detection from ECGs.
- The fusion strategy effectively addresses challenges posed by subtle ECG variations and noisy data.
- MDF-Net shows significant potential as a clinical diagnostic tool for improving cardiovascular disease management.
Abstract:
Atrial fibrillation (AFIB) and ventricular fibrillation (VFIB) are two common cardiovascular diseases that cause numerous deaths worldwide. Medical staff usually adopt long-term ECGs as a tool to diagnose AFIB and VFIB. However, since ECG changes are occasionally subtle and similar, visual observation of ECG changes is challenging. To address this issue, we proposed a multi-angle dual-channel fusion network (MDF-Net) to automatically recognize AFIB and VFIB heartbeats in this work. MDF-Net can be seen as the fusion of a task-related component analysis (TRCA)-principal component analysis (PCA) network (TRPC-Net), a canonical correlation analysis (CCA)-PCA network (CPC-Net), and the linear support vector machine-weighted softmax with average (LS-WSA) method. TRPC-Net and CPC-Net are employed to extract deep task-related and correlation features, respectively, from two-lead ECGs, by which multi-angle feature-level information fusion is realized. Since the convolution kernels of the above methods can be directly extracted through TRCA, CCA and PCA technologies, their training time is faster than that of convolutional neural networks. Finally, LS-WSA is employed to fuse the above features at the decision level, by which the classification results are obtained. In distinguishing AFIB and VFIB heartbeats, the proposed method achieved accuracies of 99.39 % and 97.17 % in intra- and inter-patient experiments, respectively. In addition, this method performed well on noisy data and extremely imbalanced data, in which abnormal heatbeats are much less than normal heartbeats. Our proposed method has the potential to be used as a diagnostic tool in the clinic.
More Related Videos
09:17High-Resolution Endocardial and Epicardial Optical Mapping in a Sheep Model of Stretch-Induced Atrial Fibrillation
Published on: July 29, 2011
16:40A New Single Chamber Implantable Defibrillator with Atrial Sensing: A Practical Demonstration of Sensing and Ease of Implantation
Published on: February 28, 2012
