A new deep neural network model for ECG heartbeat classification achieved 98.5% accuracy on the MIT-BIH dataset and an 86.71% F1-score, outperforming state-of-the-art models.
Does a new deep neural network model improve ECG heartbeat classification accuracy compared to state-of-the-art models on standard datasets?
A novel deep neural network model demonstrates high accuracy and F1-scores for ECG heartbeat classification, outperforming existing state-of-the-art models on standard datasets.
An electrocardiogram (ECG) is a basic and quick test for evaluating cardiac disorders and is crucial for remote patient monitoring equipment. An accurate ECG signal classification is critical for real-time measurement, analysis, archiving, and transmission of clinical data. Numerous studies have focused on accurate heartbeat classification, and deep neural networks have been suggested for better accuracy and simplicity. We investigated a new model for ECG heartbeat classification and found that it surpasses state-of-the-art models, achieving remarkable accuracy scores of 98.5% on the Physionet MIT-BIH dataset and 98.28% on the PTB database. Furthermore, our model achieves an impressive F1-score of approximately 86.71%, outperforming other models, such as MINA, CRNN, and EXpertRF on the PhysioNet Challenge 2017 dataset.
Pham et al. (Thu,) conducted a other in Arrhythmias and Myocardial Infarction. Deep neural network model for ECG heartbeat classification vs. State-of-the-art models (MINA, CRNN, EXpertRF) was evaluated on Accuracy and F1-score for ECG heartbeat classification. A new deep neural network model for ECG heartbeat classification achieved 98.5% accuracy on the MIT-BIH dataset and an 86.71% F1-score, outperforming state-of-the-art models.