Key result
Modified EfficientNet algorithm achieves ~99.5% accuracy in classifying eight arrhythmia types.
Why the study?
Existing arrhythmia classification methods use only the time-domain features of one-dimensional ECG signals, whereas two-dimensional image classification can capture spatiotemporal characteristics.
An improved deep learning architecture effectively classifies arrhythmias from ECG signals converted into 2D images, demonstrating potential for highly accurate automated diagnostics.
May aid AI-driven arrhythmia detection from ECG images; leaves open prospective clinical validation before practice change.
The classification and identification of arrhythmias using electrocardiogram (ECG) signals are of great practical significance in the early prevention and diagnosis of cardiovascular diseases. In this study, we propose an arrhythmia classification algorithm based on two-dimensional (2D) images and modified EfficientNet. First, we developed a method for converting original one-dimensional (1D) ECG signals into 2D image signals. In contrast with the existing classification method that uses only the time-domain features of a 1D ECG signal, the classification of 2D images can consider the spatiotemporal characteristics of the signal. Then, to better assign feature weights, we introduced an attention feature fusion module (AFF) into the EfficientNet network to replace the addition operation in the mobile inverted bottleneck convolution (MBConv) structure of the network. We selected EfficientNet for modification because, compared with most convolutional neural networks (CNNs), EfficientNet does not require manual adjustment of parameters, which improves the accuracy and speed of the network. Finally, we combined the 2D images and the improved EfficientNet network and tested its performance as an arrhythmia classification method. Our experimental results show that the network training of the proposed method requires less equipment and training time, and this method can effectively distinguish eight types of heartbeats in the MIT-BIH arrhythmia database, with a classification accuracy of 99.54%. Thus, the model has a good classification effect.
No takes yet. Share an insight, caveat, or question.
Zhao et al. (2022) studied Arrhythmia (n=107,620). Modified EfficientNet algorithm based on 2D images with Attention Feature Fusion (AFF) vs. Other classification algorithms and standard EfficientNet was evaluated on Classification accuracy. The modified EfficientNet algorithm based on 2D images successfully distinguished eight types of arrhythmias with a classification accuracy of 99.54%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: