Key result
Automatic diagnosis of heart disease using convolutional neural networks and ECG signals achieved an average classification accuracy of about 93% for 2-second signals and 100% with post-processing.
Why the study?
Mortality from cardiovascular diseases has steadily increased, prompting the development of innovative techniques for automatic heart disease detection.
Does a CNN-based automatic diagnosis system accurately classify heart disease from ECG signals?
Does a CNN-based automatic diagnosis system accurately classify heart disease from ECG signals?
A deep learning approach using CNNs can achieve near-perfect accuracy in classifying heart diseases from ECG signals when combined with a post-processing filter.
May aid automated ECG diagnosis; leaves open prospective clinical validation.
Mortality caused by cardiovascular diseases (CVDs) has been steadily increasing over the years. For this reason, numerous studies have addressed this issue, introducing innovative techniques for automatic detection of heart disease using ECG/PCG signals and convolutional neural networks (CNNs). The present paper proposes a system for automatic diagnosis of heart disease (five pathology classes) using electrocardiogram (ECG) signals and CNNs. Specifically, ECG signals are passed directly to an appropriately trained CNN network. The database comprises a combination of two public datasets: MIT-BIH Arrhythmia and MIT-BIH Atrial Fibrillation database. The results obtained from testing the network show average classification accuracy of about 93% when a 2second ECG signal is fed to the network; conversely, applying a post-processing filter results in about 100% accuracy after around 38 seconds.
No takes yet. Share an insight, caveat, or question.
Avanzato et al. (2022) studied Cardiovascular diseases. Convolutional neural networks (CNNs) for ECG signal analysis was evaluated on Classification accuracy. Automatic diagnosis of heart disease using convolutional neural networks and ECG signals achieved an average classification accuracy of about 93% for 2-second signals and 100% with post-processing.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: