Related Experiment Video
Updated: Jun 24, 2025
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Arrhythmia classification based on multi-feature multi-path parallel deep convolutional neural networks and improved
Zhongnan Ran1, Mingfeng Jiang2, Yang Li2
1School of Information Science and Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China.
Insights
This study introduces a deep learning model for accurate arrhythmia classification from ECG signals. The method improves detection by addressing beat similarities and data imbalance, enhancing diagnostic capabilities.
Area of Science:
- Cardiology
- Biomedical Engineering
- Artificial Intelligence
Background:
- Early diagnosis of electrocardiogram (ECG) abnormalities is crucial for preventing and detecting arrhythmia diseases.
- Existing arrhythmia classification methods struggle with inter-patient assessment due to similar Normal (N) and Supraventricular Premature Beat (S) categories and imbalanced ECG data.
- These challenges lead to unsatisfactory classification results, necessitating improved diagnostic approaches.
Purpose of the Study:
- To propose a novel multi-path parallel deep convolutional neural network for enhanced arrhythmia classification.
- To address the classification challenges posed by similar N and S beat categories and imbalanced ECG data.
- To improve the accuracy and reliability of automated arrhythmia detection systems.
Main Methods:
- A multi-path parallel deep convolutional neural network architecture was developed for ECG signal classification.
- A global average RR interval feature was incorporated to differentiate between similar N and S beat categories.
- A weighted loss function, dynamically adjusted based on class proportions, was implemented to handle data imbalance.
Main Results:
- The proposed method demonstrated superior classification performance compared to existing approaches under both intra-patient and inter-patient evaluation paradigms.
- Under the intra-patient paradigm, the model achieved 98.73% accuracy, 94.89% average sensitivity, 89.38% average precision, and 98.24% average specificity.
- Under the inter-patient paradigm, the model achieved 91.22% accuracy, 89.91% average sensitivity, 68.23% average precision, and 95.23% average specificity.
Conclusions:
- The developed multi-path parallel deep convolutional neural network effectively classifies arrhythmia from ECG signals.
- The integration of global average RR interval and a weighted loss function successfully addresses challenges of beat similarity and data imbalance.
- The proposed method offers a significant advancement in automated arrhythmia detection, improving diagnostic accuracy in clinical settings.
Abstract:
Early diagnosis of abnormal electrocardiogram (ECG) signals can provide useful information for the prevention and detection of arrhythmia diseases. Due to the similarities in Normal beat (N) and Supraventricular Premature Beat (S) categories and imbalance of ECG categories, arrhythmia classification cannot achieve satisfactory classification results under the inter-patient assessment paradigm. In this paper, a multi-path parallel deep convolutional neural network was proposed for arrhythmia classification. Furthermore, a global average RR interval was introduced to address the issue of similarities between N vs. S categories, and a weighted loss function was developed to solve the imbalance problem using the dynamically adjusted weights based on the proportion of each class in the input batch. The MIT-BIH arrhythmia dataset was used to validate the classification performances of the proposed method. Experimental results under the intra-patient evaluation paradigm and inter-patient evaluation paradigm showed that the proposed method could achieve better classification results than other methods. Among them, the accuracy, average sensitivity, average precision, and average specificity under the intra-patient paradigm were 98.73%, 94.89%, 89.38%, and 98.24%, respectively. The accuracy, average sensitivity, average precision, and average specificity under the inter-patient paradigm were 91.22%, 89.91%, 68.23%, and 95.23%, respectively.
Related Concept Videos
01:28Disturbances in Heart Rhythm
Arrhythmias are categorized by their speed, rhythm, and origin. A slow...
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
01:28Mechanism of Cardiac Arrhythmias