Key result
A combination of CNN and bi-directional LSTMs detected ECG beat types in 0.52 seconds, outperforming standard unidirectional LSTMs and other techniques in the literature.
Why the study?
Manual analysis of 24-48-hour ECG records is difficult, requiring intelligent automated tools, but deep learning methods face challenges in training data efficiency, complexity, and performance.
A proposed deep learning model combining CNN and Bi-LSTMs efficiently classifies ECG beats, outperforming existing techniques with a detection time of 0.52 seconds.
An electrocardiogram (ECG) is an important medical tool in diagnosing different cardiac disorders. In general, the length of long-term ECG records is 24–48 hours, and it is not easy to analyse these records manually. Therefore, an intelligent computer-based automated tool is required to analyse these records. Deep learning methods have recently improved in identifying arrhythmias in complex ECG readings. Efficient usage of training data, complexity, and performance are the major challenges with deep learning algorithms. A combination of convolutional neural network (CNN) and bi-directional LSTMs (Bi-LSTMs) is proposed in this work for efficient training and classification. Additional training is made possible by bi-directional LSTMs (Bi-LSTMs) since they traverse the input data twice. Bi-LSTMs outperform standard unidirectional LSTMs because of their fixed sequence-to-sequence prediction and increased training capacity. The proposed work is validated on a standard, publicly available Physionet arrhythmia database. The time required to detect the beat type by the proposed method is 0.52 (S). Experimental results reveal that the proposed method performs better than the techniques in the literature.
No takes yet. Share an insight, caveat, or question.
Prakash et al. (2022) studied Arrhythmias. Combination of convolutional neural network (CNN) and bi-directional LSTMs (Bi-LSTMs) vs. Standard unidirectional LSTMs and other techniques in the literature was evaluated on ECG beat classification / detection time. A combination of CNN and bi-directional LSTMs detected ECG beat types in 0.52 seconds, outperforming standard unidirectional LSTMs and other techniques in the literature.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: