A novel Convolutional Recurrent Neural Network architecture achieved an average F1 score of 0.89 for classifying 5 cardiac rhythms, performing comparably to state-of-the-art approaches.
Does a novel CNN-RNN deep learning architecture improve ECG cardiac rhythm classification compared to existing state-of-the-art approaches?
A novel CNN-RNN deep learning architecture achieves high accuracy in classifying cardiac rhythms from ECGs with fewer parameters than existing models.
This paper proposes a novel deep learning architecture involving combinations of Convolutional Neural Networks (CNN) layers and Recurrent neural networks (RNN) layers that can be used to perform segmentation and classification of 5 cardiac rhythms based on ECG recordings. The algorithm is developed in a sequence to sequence setting where the input is a sequence of five second ECG signal sliding windows and the output is a sequence of cardiac rhythm labels. The novel architecture processes as input both the spectrograms of the ECG signal as well as the heartbeats' signal waveform. Additionally, we are able to train the model in the presence of label noise. The model's performance and generalizability is verified on an external database different from the one we used to train. Experimental result shows this approach can achieve an average F1 scores of 0.89 (averaged across 5 classes). The proposed model also achieves comparable classification performance to existing state-of-the-art approach with considerably less number of training parameters.
Pokaprakarn et al. (Wed,) conducted a other in Cardiac arrhythmias. Convolutional Recurrent Neural Networks (CNN + RNN) architecture vs. existing state-of-the-art approach was evaluated on Average F1 score across 5 classes. A novel Convolutional Recurrent Neural Network architecture achieved an average F1 score of 0.89 for classifying 5 cardiac rhythms, performing comparably to state-of-the-art approaches.