Key result
1D-LBP+GRU deep learning achieves ~99% ECG beat classification accuracy, outperforming LSTM and 1D-CNN models.
Why the study?
Atrial arrhythmias are common cardiac disorders with detrimental health effects, making Computer-Assisted Diagnosis systems instrumental for early detection and diagnosis.
Does the CI-1D-LBP methodology combined with deep learning models improve the classification accuracy of ECG arrhythmias?
Does the CI-1D-LBP methodology combined with deep learning models improve the classification accuracy of ECG arrhythmias?
The CI-1D-LBP+GRU deep learning methodology achieves a high accuracy of 98.59% in classifying five types of ECG beats, offering a promising tool for computer-assisted diagnosis of arrhythmias.
May aid automated ECG arrhythmia detection; leaves open prospective clinical validation before practice adoption.
Atrial arrhythmias (ARR) are known as the most encountered cardiac disorders in today's world that have direct or indirect detrimental effect on human health. Therefore, Computer-Assisted Diagnosis (CAD) systems are instrumental in the early detection and diagnosis of diseases, serving a pivotal role in the initial assessment and identification process. In this study, ECG data belonging to four different types of arrhythmias, namely ventricular beat (VB), supraventricular beat (SVB), fusion beat (FB), and an unidentified arrhythmic beat (UB), as well as ECG data showing normal sinus rhythm (NSR) of healthy individuals were classified. The ECG data were sourced from the MIT-BIH database. The Center-Independent 1-Dimensional Local Binary Pattern (CI-1D-LBP), originated from the local binary pattern (LBP) method, proposed as a new approach for deriving the essential features needed for the classification of ECG signals. With this new approach, histograms are generated from the signals, and these histogram data are used as input for classification in 1D-CNN, LSTM, and GRU deep learning methods. The CI-1D-LBP+GRU methodology exhibited superior efficacy in classifying the five-labeled dataset (VB-SVB-FB-UB-NSR) relative to the other applied methods, attaining an impressive accuracy rate of 98.59%.
No takes yet. Share an insight, caveat, or question.
Tekin et al. (2024) studied Arrhythmia (n=113,382). CI-1D-LBP with GRU model vs. LSTM and 1D-CNN models was evaluated on Classification accuracy. The CI-1D-LBP+GRU deep learning methodology achieved an accuracy rate of 98.59% in classifying five types of ECG beats, outperforming LSTM and 1D-CNN models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: