Key result
A new attention learning method based on neural architecture search performed better than state-of-the-art methods for detecting eight different cardiovascular diseases in 12-lead ECGs.
Why the study?
Existing convolutional neural networks and attention mechanisms for ECG classification require manual hyper-parameter adjustment, limiting their ability to learn temporal and channel information.
Does an attention learning method based on neural architecture search improve the detection of cardiac abnormalities in 12-lead ECGs compared to state-of-the-art methods?
Does an attention learning method based on neural architecture search improve the detection of cardiac abnormalities in 12-lead ECGs compared to state-of-the-art methods?
A novel neural architecture search-based attention learning method improves automated detection of cardiac abnormalities from 12-lead ECGs.
In this paper, a new attention learning method based on neural architecture search (NAS) is introduced to detect cardiovascular diseases (CVDs). Cardiac abnormalities are a series of CVDs that threaten human health. Electrocardiography (ECG) is a useful tool to express the status of cardiac activity and detect cardiac abnormalities. In recent years, the convolutional neural network and attention mechanism have been applied in ECG classification with good feature-learning ability. However, there are a large number of hyper-parameters that must be be manually adjusted, so that they have limited ability to learn temporal and channel information from feature maps in network. Therefore, in this paper, a new attention learning method based on NAS is proposed, so that the network can better learn the temporal and channel information in the ECG and perform better than artificially designed architectures. The results were verified using the 12-lead ECG dataset of China Physiological Signal Challenge (CPSC) 2018 which contains eight different CVDs and the proposed method performs better than state-of-the-art methods.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2021) studied Cardiovascular diseases (cardiac abnormalities). Attention learning method based on neural architecture search (NAS) vs. State-of-the-art methods and artificially designed architectures was evaluated on Detection of cardiac abnormality in 12-lead ECG. A new attention learning method based on neural architecture search performed better than state-of-the-art methods for detecting eight different cardiovascular diseases in 12-lead ECGs.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: