Key result
DenseNet-161 classifies cardiovascular diseases from ECGs with ~96% accuracy, outperforming ResNet-50 and VGG-16.
Why the study?
Cardiovascular disease causes sudden death from blood vessel blockages, making early diagnosis and treatment essential to reduce disease severity.
Does the DenseNet-161 deep learning model improve the accuracy of classifying cardiovascular disorders from ECG images compared to ResNet-50 and VGG-16?
Does the DenseNet-161 deep learning model improve the accuracy of classifying cardiovascular disorders from ECG images compared to ResNet-50 and VGG-16?
Absolute Event Rate: 95.74% vs 94.71%
A DenseNet-161 deep learning model can accurately classify cardiovascular disorders from ECG images with 93.33% accuracy.
Hypothesis-generating for AI-ECG classification; leaves open prospective validation before clinical adoption.
Cardiovascular disease is the primary reason of death within a short period because of a sudden blockage in blood vessels. Therefore, early diagnosis and treatments are necessary to reduce the disease severity. In this study, Image augmentation concepts are used for balancing the ECG images dataset classes. The balanced dataset contains 6322 images from five different classes are Normal, Abnormal Heartbeat, Myocardial Infraction (MI), Previous History of MI, and Covid-19 ECG images. The pre-trained models VGG-16, ResNet-50, and DenseNet-161 are used to train on ECG balanced dataset. The use of hyper-parameters will increase the accuracy of classifying cardiovascular disorders which includes learning rate, optimizer, and dropout. The mentioned pre-trained models reported the highest accuracy at learning rate = 0.00001 and dropout=0.3 with Adam optimizer. DenseNet model achieved 93.33% accuracy, 94.23% precision, 93.33% recall, and 93.30% F1-Score, which is higher in performance compared to ResNet-50 and VGG-16 pre-trained models.
No takes yet. Share an insight, caveat, or question.
A et al. (2023) studied Cardiovascular diseases (Abnormal Heartbeat, Covid-19, Myocardial Infarction, History of MI, Normal) (n=3,034). DenseNet-161 deep learning model vs. ResNet-50 and VGG-16 models was evaluated on Multi-class classification accuracy. The DenseNet-161 deep learning model achieved 95.74% accuracy in the multi-class classification of cardiovascular diseases from ECG images, outperforming ResNet-50 and VGG-16 models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: