Related Experiment Video
Updated: Nov 19, 2025
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Attention-based multi-scale features fusion for unobtrusive atrial fibrillation detection using ballistocardiogram
Fangfang Jiang1, Chuhang Hong2, Tianqing Cheng2
1College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China. jiangff@bmie.neu.edu.cn.
Insights
This study introduces an innovative deep learning method using ballistocardiogram (BCG) signals for accurate atrial fibrillation (AF) detection. The novel approach enhances cardiovascular health screening through unobtrusive heart monitoring.
Area of Science:
- Cardiology
- Biomedical Engineering
- Artificial Intelligence
Background:
- Atrial fibrillation (AF) is a common arrhythmia increasing stroke risk.
- ECG is the standard for AF detection but requires electrodes.
- Ballistocardiogram (BCG) offers an unobtrusive alternative for heart monitoring.
Purpose of the Study:
- To develop a novel deep learning method for AF detection using BCG signals.
- To integrate multi-scale features from BCG for improved detection robustness.
- To address the lack of high-dimension representation and deep learning analysis in BCG-based AF diagnosis.
Main Methods:
- An attention-based multi-scale feature fusion method using BCG signals.
- Integration of 1-D morphology features (Bi-LSTM) and 2-D rhythm features (phase space) via CNN.
- Utilizing reconstructed phase space trajectory of BCG, a novel approach.
Main Results:
- The proposed method achieved superior AF detection performance compared to classical and state-of-the-art features.
- Achieved 0.947 accuracy, 0.935 specificity, 0.959 sensitivity, and 0.937 precision on a BCG dataset.
- Demonstrated that combined features and attention mechanisms enhance AF recognition.
Conclusions:
- The method offers an innovative solution for capturing diverse BCG scale descriptions.
- Deep learning methods can be effectively applied for accurate AF screening in routine life.
- This approach enables unobtrusive and convenient AF monitoring.
Background:
Atrial fibrillation (AF) represents the most common arrhythmia worldwide, related to increased risk of ischemic stroke or systemic embolism. It is critical to screen and diagnose AF for the benefits of better cardiovascular health in lifetime. The ECG-based AF detection, the gold standard in clinical care, has been restricted by the need to attach electrodes on the body surface. Recently, ballistocardiogram (BCG) has been investigated for AF diagnosis, which is an unobstructive and convenient technique to monitor heart activity in daily life. However, here is a lack of high-dimension representation and deep learning analysis of BCG.
Method:
Therefore, this paper proposes an attention-based multi-scale features fusion method by using BCG signal. The 1-D morphology feature extracted from Bi-LSTM network and 2-D rhythm feature extracted from reconstructed phase space are integrated by means of CNN network to improve the robustness of AF detection. To the best of our knowledge, this is the first study where the phase space trajectory of BCG is conducted.
Results:
2000 segments (AF and NAF) of BCG signals were collected from 59 volunteers suffering from paroxysmal AF in this survey. Compared to the classical time and frequency features and the state-of-the-art energy features with the popular machine learning classifiers, AF detection performance of the proposed method is superior, which has 0.947 accuracy, 0.935 specificity, 0.959 sensitivity, and 0.937 precision, for the same BCG dataset. The experimental results show that combined feature could excavate more potential characteristics, and the attention mechanism could enhance the pertinence for AF recognition.
Conclusions:
The proposed method can provide an innovative solution to capture the diverse scale descriptions of BCG and explore ways to involve the deep learning method to accurately screen AF in routine life.
