Key result
Novel 2D CNN DenseNet model achieves ~100% accuracy for detecting cardiac arrhythmias.
Why the study?
Automatic ECG arrhythmia diagnosis relieves doctors' workload and improves diagnostic effectiveness and efficiency, but methods are needed to accurately address arrhythmia recognition on imbalanced datasets.
Does a 2D CNN DenseNet model improve arrhythmia recognition accuracy in imbalanced ECG datasets?
Does a 2D CNN DenseNet model improve arrhythmia recognition accuracy in imbalanced ECG datasets?
The proposed 2D CNN DenseNet model provides highly accurate automatic recognition of cardiac arrhythmias from ECG signals, effectively handling imbalanced datasets.
High-accuracy 2D CNN DenseNet supports automated arrhythmia detection on benchmarks; leaves open prospective clinical validation before practice change.
Electrocardiography (ECG) is a well-known noninvasive technique in medical science that provides information about the heart’s rhythm and current conditions. Automatic ECG arrhythmia diagnosis relieves doctors’ workload and improves diagnosis effectiveness and efficiency. This study proposes an automatic end-to-end 2D CNN (two-dimensional convolution neural networks) deep learning method with an effective DenseNet model for addressing arrhythmias recognition. To begin, the proposed model is trained and evaluated on the 97720 and 141404 beat images extracted from the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia and St. Petersburg Institute of Cardiological Technics (INCART) datasets (both are imbalanced class datasets) using a stratified 5-fold evaluation strategy. The data is classified into four groups: N (normal), V (ventricular ectopic), S (supraventricular ectopic), and F (fusion), based on the Association for the Advancement of Medical Instrumentation® (AAMI). The experimental results show that the proposed model outperforms state-of-the-art models for recognizing arrhythmias, with the accuracy of 99.80% and 99.63%, precision of 98.34% and 98.94%, and F1-score of 98.91% and 98.91% on the MIT-BIH arrhythmia and INCART datasets, respectively. Using a transfer learning mechanism, the proposed model is also evaluated with only five individuals of supraventricular MIT-BIH arrhythmia and five individuals of European ST-T datasets (both of which are also class imbalanced) and achieved satisfactory results. So, the proposed model is more generalized and could be a prosperous solution for arrhythmias recognition from class imbalance datasets in real-life applications.
No takes yet. Share an insight, caveat, or question.
Ullah et al. (2022) studied Cardiac arrhythmia (n=239,124). 2D CNN with DenseNet model vs. State-of-the-art models was evaluated on Arrhythmia recognition accuracy. The proposed 2D CNN DenseNet model achieved an accuracy of 99.80% and 99.63% on the MIT-BIH and INCART datasets, respectively, for recognizing cardiac arrhythmias.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: