Does data augmentation improve the performance of deep neural network models in diagnosing abnormalities from ECGs?
ECG data from the PTB-XL dataset, a large publicly available electrocardiography dataset
Data augmentation (DA) applied to a deep neural network (DNN) model
DNN model without data augmentation or with different augmentations
Model performance evaluated using the F1 metricsurrogate
Applying carefully selected data augmentations to deep neural networks trained on ECG data significantly improves their diagnostic accuracy.
The electrocardiogram (ECG) is a crucial tool for identifying heart abnormalities in a non-invasive way. As the technology has advanced, it is now a digital tool that can integrate algorithms to support abnormality diagnostics. Deep neural networks (DNN) have, in the past few years, shown their potential and success in classification problems, and studies have shown that a DNN can outperform a cardiologist in diagnosing abnormalities from ECG. In this study, we investigate whether data augmentation (DA) can improve model performance. Using a DNN model trained on PTB-XL, a large publicly available electrocardiography dataset, we aim to apply different augmentations and evaluate DAs effect on model performance using the F1 metric. The results show that combinations of carefully selected DA can improve model accuracy with a significant result.
Building similarity graph...
Analyzing shared references across papers
Loading...
Amjad Alakrami
Kent Tieu
Building similarity graph...
Analyzing shared references across papers
Loading...
Alakrami et al. (Wed,) studied this question.