Related Experiment Video
Updated: Jul 19, 2025
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Diagnosis of atrial fibrillation based on unsupervised domain adaptation
Mingyu Du1, Yuan Yang1, Lin Zhang1
1Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine and Engineering, No.37 Xueyuan Road, Haidian District, Beijing, China; Key Laboratory of Big Data-Based Precision Medicine, Ministry of Industry and Information Technology, No.37 Xueyuan Road, Haidian District, Beijing, China; School of Automation Science and Electrical Engineering, Beihang University, No.37 Xueyuan Road, Haidian District, Beijing, China.
Insights
This study introduces a novel deep learning model for diagnosing atrial fibrillation using electrocardiograms (ECG). The model effectively trains on limited labeled and extensive unlabeled ECG data, achieving high diagnostic accuracy for this common elderly heart condition.
Area of Science:
- Cardiology and Medical Informatics
- Artificial Intelligence in Healthcare
- Signal Processing
Background:
- The global elderly population is increasing, leading to a rise in cardiovascular diseases.
- Atrial fibrillation is a prevalent and life-threatening arrhythmia in older adults.
- Accurate diagnosis of atrial fibrillation relies on electrocardiogram (ECG) signals, but large labeled datasets are scarce.
Purpose of the Study:
- To develop a high-precision atrial fibrillation classification model using deep learning.
- To address the challenge of limited labeled ECG data by leveraging unsupervised domain adaptation.
- To improve the efficiency and accuracy of AI-driven ECG analysis for arrhythmia detection.
Main Methods:
- A novel two-channel network model was designed to analyze ECG signals from multiple feature dimensions.
- An innovative feature queue technique, incorporating a global centroid, was developed for stable and rapid network updates.
- Unsupervised domain adaptation was employed, utilizing a small amount of labeled data with a large volume of unlabeled ECG data.
- An improved domain discrepancy metric and a false label credibility evaluation formula were introduced to enhance learning from unlabeled data.
Main Results:
- The two-channel network and feature queue technique enabled high-precision atrial fibrillation diagnosis with limited labeled data.
- The model demonstrated strong generalization capabilities, achieving high performance metrics.
- In the MIT-BIH Arrhythmia Database, the model reached 95.12% precision, 95.36% recall, 98.05% accuracy, and 95.23% F1 score.
- In the MIT-BIH Atrial Fibrillation Database, performance was even higher, with 98.9% precision, 99.03% recall, 99.13% accuracy, and 99.08% F1 score.
Conclusions:
- The proposed deep learning approach effectively diagnoses atrial fibrillation using ECG data.
- The combination of a two-channel network and feature queue technique overcomes data limitations in ECG analysis.
- This method offers a promising solution for accurate and efficient arrhythmia detection in clinical settings.
Abstract:
In recent years, the proportion of the elderly in the society is continuously increasing. Cardiovascular disease is a big problem that puzzles the health of the elderly. Among them, atrial fibrillation is one of the most common arrhythmia diseases in recent years, which poses a great threat to human life safety. At the same time, deep learning has become a powerful tool for medical and healthcare applications due to its high accuracy and fast detection speed. The diagnosis of atrial fibrillation is based on electrocardiogram, ECG) timing signals. At present, the scale of the open ECG data set is limited, and a large amount of labeled ECG data is needed to build a high-precision diagnostic model. In this study, a two-channel network model and a feature queue technique are proposed. A high-quality classification diagnosis model of atrial fibrillation is obtained by unsupervised domain adaptive technique, which uses a small amount of labeled data and a large amount of unlabeled data for training. The research content of this paper includes the following aspects: 1) Build a dual-channel network model, which can analyze ECG signals from different feature dimensions. At the same time, the dual-channel output also improves the reliability of the model's pseudo-label in the adaptive training stage and the accuracy of the output in the testing stage. 2) Innovative feature queue technology including global centroid is proposed to participate in the process of domain discrepancy metric calculation, which can use a small amount of labeled data and a large amount of unlabeled data to achieve a more stable and rapid update of the network. 3) Improved and innovated the domain discrepancy metric function, and introduced an evaluation formula for the credibility of false labels to improve the learning efficiency of unlabeled data. Finally, the experimental results show that the proposed two-channel network model and the feature queue technique with global centroid can achieve a high generalization and high precision depth network model by training with a small amount of labeled data and a large amount of unlabeled data. 4) The proposed model achieved a precision of 95.12%, a recall of 95.36%, an accuracy of 98.05%, and an F1 score of 95.23% in the MIT-BIH Arrhythmia Database. In the MIT-BIH Atrial Fibrillation Database, the model achieved a precision of 98.9%, a recall of 99.03%, an accuracy of 99.13%, and an F1 score of 99.08%.
