Training convolutional neural networks on noisy ECG data limited the F1 score decrease to <0.05 when classifying clean data, compared to a decrease of up to 0.18 when trained only on clean data.
Does physiological ECG noise impact the classification performance of convolutional neural networks?
Physiological ECG noise significantly degrades the performance of deep learning classification models trained only on clean data, highlighting the need to include noisy signals in training datasets.
The electrocardiogram (ECG) is a widespread diagnostic tool in healthcare and supports the diagnosis of cardiovascular disorders. Deep learning methods are a successful and popular technique to detect indications of disorders from an ECG signal. However, there are open questions around the robustness of these methods to various factors, including physiological ECG noise. In this study, we generate clean and noisy versions of an ECG dataset before applying symmetric projection attractor reconstruction (SPAR) and scalogram image transformations. A convolutional neural network is used to classify these image transforms. For the clean ECG dataset, F1 scores for SPAR attractor and scalogram transforms were 0.70 and 0.79, respectively. Scores decreased by less than 0.05 for the noisy ECG datasets. Notably, when the network trained on clean data was used to classify the noisy datasets, performance decreases of up to 0.18 in F1 scores were seen. However, when the network trained on the noisy data was used to classify the clean dataset, the decrease was less than 0.05. We conclude that physiological ECG noise impacts classification using deep learning methods and careful consideration should be given to the inclusion of noisy ECG signals in the training data when developing supervised networks for ECG classification. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'.
Venton et al. (Mon,) conducted a other in Cardiovascular disorders. Convolutional neural network trained on noisy ECG data vs. Network trained on clean ECG data was evaluated on Classification performance (F1 score). Training convolutional neural networks on noisy ECG data limited the F1 score decrease to <0.05 when classifying clean data, compared to a decrease of up to 0.18 when trained only on clean data.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: