Key result
The CS-CNN model achieved F1 scores between 88.17% and 96.25% for atrial fibrillation screening under 10% to 90% compression ratios, processing 24-hour ECGs in approximately 1 second.
Why the study?
Compressed sensing is a low-complexity compression technology applicable to long-term ECG monitoring using wearable devices, prompting the proposal of an automatic screening method for AF based on lossy compression.
Does a CS-CNN model improve computational efficiency and maintain prediction accuracy for atrial fibrillation screening compared to standard CNN architectures?
Does a CS-CNN model improve computational efficiency and maintain prediction accuracy for atrial fibrillation screening compared to standard CNN architectures?
The proposed CS-CNN model offers high computational efficiency and accuracy for atrial fibrillation screening, making it a promising approach for wearable ECG monitoring devices.
May enable efficient long-term AF screening on wearables; leaves open prospective clinical validation.
OBJECTIVE: Compressed sensing (CS) is a low-complexity compression technology that has recently been proposed. It can be applied to long-term electrocardiogram (ECG) monitoring using wearable devices. In this study, an automatic screening method for atrial fibrillation (AF) based on lossy compression of the electrocardiogram signal is proposed. APPROACH: The proposed method combines the CS with the convolutional neural network (CNN). The sparse binary sensing matrix is first used to project the raw ECG signal randomly, transforming the raw ECG data from high-dimensional space to low-dimensional space to complete compression, and then using CNN to classify the compressed ECG signal involving AF. Our proposed model is validated on the MIT-BIH atrial fibrillation database. MAIN RESULTS: The experimental results show that the model only needs about 1 s to complete the 24 h ECG recording of AF, which is 3.41%, 69.84% and 67.56% less than the time required by AlexNet, VGGNet and GoogLeNet, respectively. Under different compression ratios of 10% to 90%, the maximum and minimum F1 scores reach 96.25% and 88.17%, respectively. SIGNIFICANCE: The CS-CNN (compressed sensing convolutional neural network) model has high computational efficiency while ensuring prediction accuracy, and is a promising method for AF screening in wearable application scenarios.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2020) studied Atrial fibrillation. CS-CNN (compressed sensing convolutional neural network) model vs. AlexNet, VGGNet, and GoogLeNet was evaluated on F1 score for AF classification under different compression ratios (10% to 90%). The CS-CNN model achieved F1 scores between 88.17% and 96.25% for atrial fibrillation screening under 10% to 90% compression ratios, processing 24-hour ECGs in approximately 1 second.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: