Robustness of convolutional neural networks to physiological ECG noise

TL;DR

This study evaluates how physiological ECG noise affects deep learning-based classification of ECG signals, highlighting the importance of including noisy data in training to improve robustness.

Contribution

It demonstrates the impact of physiological noise on ECG classification accuracy and emphasizes training with noisy data for better robustness in deep learning models.

Findings

Performance drops when models trained on clean data classify noisy ECGs.

Training on noisy data improves robustness to physiological noise.

Deep learning models are sensitive to ECG noise, affecting diagnostic accuracy.

Abstract

The electrocardiogram (ECG) is one of the most widespread diagnostic tools 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 pretrained convolutional neural network is trained using transfer learning 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, and the 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 performance 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.