Related Experiment Video
Updated: Dec 28, 2025
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
Published on: April 26, 2024
A Multi-Task Group Bi-LSTM Networks Application on Electrocardiogram Classification
Qiu-Jie Lv1, Hsin-Yi Chen1, Wei-Bin Zhong1
11Artificial Intelligence Medical Center, School of Intelligent Systems EngineeringSun Yat-sen UniversityShenzhen510275China.
Insights
A new multi-task group bidirectional long short-term memory (MTGBi-LSTM) framework effectively recognizes cardiovascular diseases (CVD) from electrocardiogram (ECG) signals. This AI tool offers reliable computer-aided diagnosis for CVD, improving patient outcomes.
Area of Science:
- Artificial Intelligence
- Biomedical Engineering
- Cardiology
Background:
- Cardiovascular diseases (CVD) represent a significant global health burden, being the primary cause of mortality worldwide.
- Electrocardiogram (ECG) analysis is a crucial, efficient method for assessing various CVDs.
- Accurate and timely diagnosis of CVDs remains a critical challenge in clinical practice.
Purpose of the Study:
- To introduce a novel Multi-Task Group Bidirectional Long Short-Term Memory (MTGBi-LSTM) framework for intelligent recognition of multiple CVDs.
- To leverage multi-lead ECG signals for enhanced CVD detection and diagnosis.
- To develop an effective tool for computer-aided diagnosis (CAD) of cardiovascular diseases.
Main Methods:
- The proposed MTGBi-LSTM framework integrates Group Bi-LSTM (GBi-LSTM) and Residual Group Convolutional Neural Network (Res-GCNN) for dual feature extraction from ECG spatial and time-series data.
- GBi-LSTM incorporates Global and Intra-Group Bi-LSTM components to analyze individual ECG lead features and inter-lead relationships.
- An attention mechanism integrates multi-lead ECG information, enhancing feature discriminability, while multi-task learning and a dynamic weighted loss function address disease associations and class imbalance.
Main Results:
- The MTGBi-LSTM model was evaluated on over 170,000 clinical 12-lead ECG analyses.
- The framework achieved high performance metrics: 88.86% accuracy, 90.67% precision, 94.19% recall, and 92.39% F1-score.
- These results demonstrate the reliable ECG analysis capabilities of the MTGBi-LSTM method.
Conclusions:
- The MTGBi-LSTM framework provides a robust and effective approach for the computer-aided diagnosis of cardiovascular diseases using ECG signals.
- The study highlights the potential of deep learning models in improving the efficiency and accuracy of CVD detection.
- The developed tool offers a promising solution for enhancing clinical decision-making in cardiology.
Background:
Cardiovascular diseases (CVD) are the leading cause of death globally. Electrocardiogram (ECG) analysis can provide thoroughly assessment for different CVDs efficiently. We propose a multi-task group bidirectional long short-term memory (MTGBi-LSTM) framework to intelligent recognize multiple CVDs based on multi-lead ECG signals.
Methods:
This model employs a Group Bi-LSTM (GBi-LSTM) and Residual Group Convolutional Neural Network (Res-GCNN) to learn the dual feature representation of ECG space and time series. GBi-LSTM is divided into Global Bi-LSTM and Intra-Group Bi-LSTM, which can learn the features of each ECG lead and the relationship between leads. Then, through attention mechanism, the different lead information of ECG is integrated to make the model to possess the powerful feature discriminability. Through multi-task learning, the model can fully mine the association information between diseases and obtain more accurate diagnostic results. In addition, we propose a dynamic weighted loss function to better quantify the loss to overcome the imbalance between classes.
Results:
Based on more than 170,000 clinical 12-lead ECG analysis, the MTGBi-LSTM method achieved accuracy, precision, recall and F1 of 88.86%, 90.67%, 94.19% and 92.39%, respectively. The experimental results show that the proposed MTGBi-LSTM method can reliably realize ECG analysis and provide an effective tool for computer-aided diagnosis of CVD.
Related Concept Videos
01:29Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
01:25Correlation between ECG and Cardiac Cycle
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...