GAN-Based Data Imbalance Techniques for ECG Synthesis to Enhance Classification Using Deep Learning Techniques and Evaluation

Heart diseases such as cardiovascular and myocardial infarction are the foremost reasons of death in the world. The timely, accurate, and effective prediction of heart diseases is crucial for saving lives. Electrocardiography (ECG) is a primary non-invasive method to identify cardiac abnormalities. However, manual interpretation of ECG recordings for heart disease diagnosis is a time-consuming and inaccurate process. For the accurate and efficient detection of heart diseases from the 12-lead ECG dataset, we have proposed a hybrid residual/inception-based deeper model (HRIDM). In this study, we have utilized ECG datasets from various sources, which are multi-institutional large ECG datasets. The proposed model is trained on 12-lead ECG data from over 10,000 patients. We have compared the proposed model with several state-of-the-art (SOTA) models, such as LeNet-5, AlexNet, VGG-16, ResNet-50, Inception, and LSTM, on the same training and test datasets. To show the effectiveness of the computational efficiency of the proposed model, we have only trained over 20 epochs without GPU support and we achieved an accuracy of 50.87% on the test dataset for 27 categories of heart abnormalities. We found that our proposed model outperformed the previous studies which participated in the official PhysioNet/CinC Challenge 2020 and achieved fourth place as compared with the 41 official ranking teams. The result of this study indicates that the proposed model is an implying new method for predicting heart diseases using 12-lead ECGs.

show abstract

Denoising ECG Signals using Weighted Iterative UFIR Filtering

Lastre-Dominguez,

Jímenez-Ramos,

Azcaray-Rivera

et al. 2023

Wseas Transactions on Signal Processing

View full text Add to dashboard Cite

The electrocardiogram (ECG) holds paramount importance in diagnosing heart disease, and as it persists leading cause of global mortality. Over the past decades, diverse techniques have emerged for processing ECG signals, with denoising taking a prominent role in enhancing feature extraction. Nonetheless, achieving heightened accuracy remains an enduring challenge. In this study, we introduce an innovative approach involving the application of a weighted unbiased finite impulse response (UFIR) filter. Under the same noise conditions and in terms of the root mean square error (RMSE) and signal-to-noise ratio (SNR), our proposed method showcases worthy performance in comparison to the weighted Savitzky-Golay (SG) filter. This research contributes to the progressive evolution of ECG signal processing, offering the potential for more precise and dependable detection of cardiac diseases.

show abstract

GAN-Based Data Imbalance Techniques for ECG Synthesis to Enhance Classification Using Deep Learning Techniques and Evaluation

Cited by 4 publications

References 44 publications

ECG Monitor Design: From One to Three - Advancing ECG Monitoring with AI-Generated Lead Synthesis (GANs)

ECG Monitor Design: From One to Three - Advancing ECG Monitoring with AI-Generated Lead Synthesis (GANs)

HRIDM: Hybrid Residual/Inception-Based Deeper Model for Arrhythmia Detection from Large Sets of 12-Lead ECG Recordings

Denoising ECG Signals using Weighted Iterative UFIR Filtering

Contact Info

Product

Resources

About