Key result
The Negative-ResNet training scheme achieved an ECG classification accuracy of 91.0%, which was 6.2% higher than a normal training process with a standard ResNet model.
Why the study?
Data labelling quality and noisy labels can impair neural network training in medical signal processing, motivating a semi-supervised algorithm for noisy labels.
Does a semi-supervised algorithm using Positive and Negative Learning improve classification accuracy of noisy ambulatory ECG signals compared to standard ResNet training?
Does a semi-supervised algorithm using Positive and Negative Learning improve classification accuracy of noisy ambulatory ECG signals compared to standard ResNet training?
A novel semi-supervised learning algorithm (Negative-ResNet) improves the classification accuracy of noisy ambulatory ECG signals compared to standard ResNet training.
May improve automated analysis of noisy ambulatory ECGs; hypothesis-generating and requires prospective validation before clinical use.
With recently successful applications of deep learning in computer vision and general signal processing, deep learning has shown many unique advantages in medical signal processing. However, data labelling quality has become one of the most significant issues for AI applications, especially when it requires domain knowledge (e.g. medical image labelling). In addition, there might be noisy labels in practical datasets, which might impair the training process of neural networks. In this work, we propose a semi-supervised algorithm for training data samples with noisy labels by performing selected Positive Learning (PL) and Negative Learning (NL). To verify the effectiveness of the proposed scheme, we designed a portable ECG patch -- iRealCare -- and applied the algorithm on a real-life dataset. Our experimental results show that we can achieve an accuracy of 91.0 %, which is 6.2 % higher than a normal training process with ResNet. There are 65 patients in our dataset and we randomly picked 2 patients to perform validation.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2022) studied Arrhythmia (ECG signal classification) (n=65). Negative-ResNet (Negative Learning training scheme) vs. Normal positive training process with ResNet (Baseline Model) was evaluated on Classification accuracy (6.2% higher accuracy). The Negative-ResNet training scheme achieved an ECG classification accuracy of 91.0%, which was 6.2% higher than a normal training process with a standard ResNet model.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: