Key result
Transfer learning using DenseNet architecture for multi-class ECG image classification achieved the best performance with an accuracy of 92% and an F1-score of 92%.
Why the study?
Automated ECG diagnosis typically relies on raw data that not all digital devices provide, making image-based ECG classification an alternative.
Answers are grounded in this paper and cite their sources.
A transfer learning approach using DenseNet architecture on ECG signal images achieved 92% accuracy and F1-score for multi-class heart abnormality detection.
The heart is one of the vital organs in the circulatory system. Regular checkups are very important to prevent heart disease. The most basic examination is blood pressure then further examination is related to the evaluation of the electrical activity of the heart using an electrocardiogram (ECG). The ECG carries important information regarding various abnormalities of heart function. Several automated classification techniques have been proposed to facilitate diagnosis. However, not all digital ECG devices provide raw data for analysis. ECG classification method based on images can be an alternative in classification. Therefore, in this study, it is proposed to classify ECG based on signal images. The proposed classification method uses transfer learning with VGG, AlexNet, and DenseNet architectures. The method used for the classification of multi-class ECG consists of normal, PVC, Atrial Fibrilation, AFL, Bigeminy, LBBB, and APB. The simulation results generate the best accuracy of 92% and F1-score of 92%. Best performance is achieved using DenseNet architecture at 60 epochs. This study is expected to be a new reference technique in the classification of ECG signals.
No takes yet. Share an insight, caveat, or question.
Hadiyoso et al. (2023) studied Heart abnormalities. Transfer learning (VGG, AlexNet, DenseNet) for ECG image classification was evaluated on Classification accuracy and F1-score. Transfer learning using DenseNet architecture for multi-class ECG image classification achieved the best performance with an accuracy of 92% and an F1-score of 92%.
Synapse has enriched 10 related papers. Consider them for comparative context: