Related Experiment Videos
Explainable hybrid deep learning framework with Grad-CAM for heartbeat-level arrhythmia classification
Sureshkumar Sundaramoorthy1, Govardhan Karunanidhi1
1School of Electronics Engineering, Vellore Institute of Technology, Vellore, Tamilnadu, India.
Insights
This study introduces an explainable deep learning model for accurate electrocardiogram (ECG) arrhythmia classification. The advanced framework achieves high performance, offering a scalable solution for real-time cardiac monitoring.
Area of Science:
- Cardiology
- Artificial Intelligence
- Biomedical Engineering
Background:
- Cardiac arrhythmia is a major cause of death globally.
- Early detection of ECG arrhythmias is crucial for patient outcomes.
- Current diagnostic methods require timely and accurate classification.
Purpose of the Study:
- To develop an explainable hybrid deep learning framework for automated ECG cardiac arrhythmia classification.
- To improve the accuracy and interpretability of arrhythmia detection.
- To create a robust and scalable solution for clinical application.
Main Methods:
- Integration of 1D-CNN for local morphological features and GRU for temporal dependencies.
- Application of channel attention and Grad-CAM for enhanced feature extraction and interpretability.
- Evaluation on three benchmark ECG datasets (MIT-BIH Arrhythmia, INCART, SVDB).
Main Results:
- Achieved high classification accuracy (up to 99.73%) and macro-F1 scores (up to 97.21%).
- Demonstrated performance improvement of 2%-5% over state-of-the-art methods.
- Showcased effective integration of morphological and temporal feature analysis.
Conclusions:
- The proposed framework offers a robust and scalable solution for ECG arrhythmia classification.
- Explainability through Grad-CAM enhances clinical trust and understanding.
- Computational efficiency and single-lead ECG use enable real-time deployment in diverse settings.
Abstract:
Cardiac arrhythmia, a common sign of cardiovascular disease, is a leading cause of global mortality and morbidity. Timely and accurate detection of electrocardiogram (ECG) cardiac arrhythmia is essential for effective clinical intervention. Here, we present an explainable hybrid deep learning framework for automated ECG cardiac arrhythmia classification. The proposed model integrates one-dimensional convolutional neural network (1D-CNN) for local morphological features, a gated recurrent unit (GRU) to extract temporal dependencies in sequential ECG signals, and the channel attention technique to emphasize clinically important patterns. In addition, a gradient-weighted class activation mapping (Grad-CAM) module is integrated to enhance interpretability by highlighting complex portions of the ECG signals that influence model decision making. The proposed framework is evaluated on three benchmark datasets: Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia, St. Petersburg INCART, and the MIT-BIH Supraventricular Arrhythmia Database (SVDB). The model achieves classification accuracy values of 99.69%, 99.73%, and 98.77% along with macro-F1 scores of 95.75%, 97.21%, and 94.58% and specificity values of 99.53%, 99.54%, and 98.63%, respectively. The experimental results demonstrated performance improvement of approximately 2%-5% over recent state-of-the-art techniques in terms of key performance metrics. These findings indicate that the proposed framework effectively integrates local morphological feature extraction with temporal modeling, providing a robust and scalable solution for ECG arrhythmia classification. Moreover, its computational efficiency and its use of single-lead ECG signals make it suitable for real-time deployment in wearable devices, remote monitoring systems, and resource-limited clinical settings.