Key result
Non-architectural improvements including patient metadata incorporation, signal denoising, and self-adaptive model training significantly increased the quality of ECG classification compared to baseline.
Why the study?
Although deep learning-based approaches to 12-lead ECG interpretation achieve diagnostic quality comparable to experts, techniques are needed to further improve ECG classification by deep neural networks.
Do non-architectural improvements (metadata incorporation, signal denoising, self-adaptive training) improve the quality of ECG classification by deep neural networks?
Do non-architectural improvements (metadata incorporation, signal denoising, self-adaptive training) improve the quality of ECG classification by deep neural networks?
Incorporating patient metadata, signal denoising, and self-adaptive model training significantly improves the performance of deep neural networks for ECG classification.
Due to the latest advances in machine learning algorithms new deep learning-based approaches to the interpretation of 12-lead electrocardiograms have been developed, demonstrating the quality of diagnostics comparable to the expert one. In this paper, we propose several techniques increasing the quality of ECG classification by a deep neural network. The techniques include patient metadata incorporation, signal denoising and self-adaptive model training. The experimental validation of the approaches was carried out on a novel dataset containing 64198 standard ECG recordings obtained during routine medical practice. The conducted experiments demonstrated statistically significant quality growth compared to the baseline, supporting the further application of our findings.
No takes yet. Share an insight, caveat, or question.
Andreev et al. (2020) studied ECG classification (n=64,198). Non-architectural improvements (patient metadata incorporation, signal denoising, self-adaptive model training) vs. Baseline deep neural network model was evaluated on Quality of ECG classification. Non-architectural improvements including patient metadata incorporation, signal denoising, and self-adaptive model training significantly increased the quality of ECG classification compared to baseline.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: