Key result
VAE data augmentation improves ECG classification accuracy to ~99% versus real data alone.
Why the study?
Imbalanced data distributions in real-life datasets negatively affect classification accuracy, prompting investigation into data augmentation methods to address this problem in ECG data.
Do data augmentation methods (GAN, SMOTE, VAE) improve classification accuracy of ECG signals in the MIT-BIH dataset?
Do data augmentation methods (GAN, SMOTE, VAE) improve classification accuracy of ECG signals in the MIT-BIH dataset?
Absolute Event Rate: 98.58% vs 96.53%
Data augmentation using VAE combined with real data improves ECG classification accuracy to 98.6% and balances class distribution.
VAE augmentation may boost ECG model performance; leaves open clinical validation and generalizability.
Classification is separating data into predefined categories by obtaining descriptive features. In the classification process, machine and deep learning algorithms assume that the class samples are evenly distributed. In particular, the dataset size used in deep learning is significant for classification success. However, obtaining balanced data distribution in real-life problems is very difficult. This negatively affects class-based accuracy. Various methods are used in the literature to overcome the unbalanced data problem. This study investigated the effects of GAN, SMOTE, and VAE methods on ECG data. For this purpose, the heartbeat signals in the MIT-BIH dataset were used. To test the performance of the methods, a performance comparison was made using real and synthetic data, and finally, the model trained with synthetic data was tested with real data. According to the results, 96.5% accuracy was obtained with the real data. The highest classification accuracy of 100.0% was obtained in VAE when using only synthetic data. In training with synthetic data and test results with real data, the highest classification success was 86.4% with SMOTE. When synthetic and real data sets are used together, the highest success rate is 98.6% with VAE. In addition, the accuracy of all classes is evenly distributed after data augmentation.
No takes yet. Share an insight, caveat, or question.
Turgut Özseven (2024) studied Arrhythmia (n=47). Data augmentation using VAE, GAN, and SMOTE vs. Real data without augmentation was evaluated on Overall classification accuracy. Data augmentation using Variational Autoencoders (VAE) combined with real data achieved the highest ECG classification accuracy of 98.6%, compared to 96.5% using real data alone.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: