Key result
Deep convolutional neural network classifies ECG arrhythmias with ~99.7% accuracy.
Why the study?
Holter monitors record ECG data that is extremely hard to analyze manually.
Does a Deep Convolutional Neural Network improve the classification of arrhythmias from ECG data compared to other state-of-the-art models?
Does a Deep Convolutional Neural Network improve the classification of arrhythmias from ECG data compared to other state-of-the-art models?
A novel Deep Convolutional Neural Network model achieved >99.6% accuracy, precision, and recall in classifying arrhythmias from the MIT-BIH dataset, outperforming existing models.
Holter monitors are used to record Electrocardiogram (ECG) data which is extremely hard to analyze manually. Convolutional Neural Network (CNN) are known to be efficient for classification of image data. Hence, in this study, we are using Deep Convolutional Neural Network to classify the ECG data into various types of Arrhythmias. Denoising, segmentation and data augmentation techniques are used for pre-processing of the data. The proposed model uses the MIT-BIH Arrhythmia Dataset for training and evaluation purpose this dataset has much imbalance which has been removed using data augmentation techniques. The proposed approach shows an overall accuracy 99.67% along with 99.68% precision and 99.66% recall. Further, we have also compared the state-of-the-art models like 2D CNN, genetic ensemble of classifiers, Long Short-Term Memory (LSTM) Networks, etc results with proposed model. And the introduced approach is outperforming when compared to these models.
No takes yet. Share an insight, caveat, or question.
Rathee et al. (2023) studied Arrhythmia. Deep Convolutional Neural Network vs. State-of-the-art models (2D CNN, genetic ensemble of classifiers, LSTM) was evaluated on Classification accuracy, precision, and recall. A Deep Convolutional Neural Network classified ECG data into various types of arrhythmias with an overall accuracy of 99.67%, precision of 99.68%, and recall of 99.66%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: