Key result
The proposed WaveletCNN Autoencoder and ConvLSTM machine learning pipeline performed 3 standard deviations better than state-of-the-art QRS complex detection algorithms in terms of F1 score for very noisy environments.
Why the study?
Detecting QRS complexes in very noisy wearable ECG devices remains challenging due to electrode contact noise, instrumentation noise, and motion artifacts.
Does the proposed WaveletCNN Autoencoder and ConvLSTM pipeline improve QRS complex detection in noisy ECG signals compared to state-of-the-art algorithms?
Does the proposed WaveletCNN Autoencoder and ConvLSTM pipeline improve QRS complex detection in noisy ECG signals compared to state-of-the-art algorithms?
The proposed WaveletCNN Autoencoder and ConvLSTM pipeline significantly improves QRS complex detection accuracy in highly noisy ECG signals, facilitating better automated analysis of wearable ECG data.
May enhance noisy wearable ECG analysis; hypothesis-generating pending prospective clinical validation.
In this paper, we propose a novel machine learning pipeline to detect QRS complexes in very noisy wearable electrocardiogram (ECG) devices. The machine learning pipeline consists of a Butterworth filter, two wavelet convolutional neural networks (WaveletCNNs) autoencoders, an optional QRS complex inverter, a Monte Carlo k-nearest neighbours (k-NN), and a convolutional long short-term memory (ConvLSTM). WaveletCNN autoencoders filter out electrode contact noise, instrumentation noise, and motion artifact noise by using the advantages of wavelet filters and convolutional neural networks. The QRS complex inverter flips inverted QRS complexes. Monte Carlo k-NN performs automatic gain control on the ECG signals in order to normalize it. The ConvLSTM executes the final QRS complex detection by using the power of a convolutional neural network and a long short-term memory. The MIT-BIH, the European ST-T, and the Long Term ST database Noise Stress Test databases provide the training and testing ECG recordings. The proposed machine learning pipeline performs 3 standard deviations better than the state of the art QRS complex detection algorithms in terms of F 1 score for very noisy environments.
No takes yet. Share an insight, caveat, or question.
Yuen et al. (2020) studied Noisy ECG signals. WaveletCNN Autoencoder and ConvLSTM pipeline vs. Other QRS complex detection algorithms (Pan and Tompkins, GQRS, Wavedet, Xiang et al., Chandra et al.) was evaluated on F1 score for QRS complex detection. The proposed WaveletCNN Autoencoder and ConvLSTM machine learning pipeline performed 3 standard deviations better than state-of-the-art QRS complex detection algorithms in terms of F1 score for very noisy environments.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: