Key result
EfficientNet-V2 achieves ~96% accuracy in classifying cardiovascular diseases from ECGs, outperforming DenseNet and ResNet.
Why the study?
Cardiovascular disease is a leading cause of mortality, and timely identification and intervention are essential to minimize its impact.
Does EfficientNet-V2 improve the classification accuracy of ECG images compared to other pre-trained models?
Does EfficientNet-V2 improve the classification accuracy of ECG images compared to other pre-trained models?
EfficientNet-V2 provides high accuracy (96.22%) for classifying cardiovascular conditions from ECG images, outperforming other standard pre-trained models.
May advance automated ECG interpretation; extends RCT evidence for deep learning model comparisons in cardiovascular imaging.
Cardiovascular disease ranks among the top causes of mortality, frequently caused by sudden obstructions within blood vessels. Timely identification and intervention are essential for minimizing the impact of the disease. This research employs image augmentation techniques to correct class imbalance in an ECG image dataset divided into five categories: Normal, Abnormal Heartbeat, Myocardial Infarction, Previous History of Myocardial Infarction, and COVID-19. The balanced dataset includes 6,322 images. To improve classification accuracy for cardiovascular diseases, three pre-trained models visual Geometric Group, Residual, Dense, and Efficient Network with Version 2, were trained on the balanced ECG dataset. Critical hyper parameters were fine-tuned, yielding optimal performance with a learning rate set at 0.00001, a dropout rate of 0.3, and utilizing the Adam optimizer. EfficientNet-V2 outperformed the other models, reaching a level of accuracies of 96.22%, precision 96.34%, recall 96.31%, 95.89%, 94.75%, and an F1-Score of 96.33%, thus exceeding the performance of Densenet 161, Densenet 201, ResNet50 and VGG16.
No takes yet. Share an insight, caveat, or question.
Jothiaruna et al. (2024) studied Cardiovascular diseases (Myocardial Infarction, COVID-19, Abnormal Heartbeat) (n=3,034). EfficientNet-V2 vs. DenseNet 161, DenseNet 201, ResNet-50, VGG-16 was evaluated on Classification accuracy. EfficientNet-V2 achieved a classification accuracy of 96.22% in categorizing cardiovascular diseases from ECG images, outperforming other pre-trained models such as DenseNet and ResNet.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: