Neural architecture search for real-time quality assessment of wearable multi-lead ECG on mobile devices

Robustness of Deep Learning models in electrocardiogram noise detection and classification

BACKGROUND AND OBJECTIVE

Automatic electrocardiogram (ECG) signal analysis for heart disease detection has gained significant attention due to busy lifestyles. However, ECG signals are susceptible to noise, which adversely affects the performance of ECG signal analysers. Traditional blind filtering methods use predefined noise frequency and filter order, but they alter ECG biomarkers. Several Deep Learning-based ECG noise detection and classification methods exist, but no study compares recurrent neural network (RNN) and convolutional neural network (CNN) architectures and their complexity.

METHODS

This paper introduces a knowledge-based ECG filtering system using Deep Learning to classify ECG noise types and compare popular computer vision model architectures in a practical Internet of Medical Things (IoMT) framework. Experimental results demonstrate that the CNN-based ECG noise classifier outperforms the RNN-based model in terms of performance and training time.

RESULTS

The study shows that AlexNet, visual geometry group (VGG), and residual network (ResNet) achieved over 70% accuracy, specificity, sensitivity, and F1 score across six datasets. VGG and ResNet performances were comparable, but VGG was more complex than ResNet, with only a 4.57% less F1 score.

CONCLUSIONS

This paper introduces a Deep Learning (DL) based ECG noise classifier for a knowledge-driven ECG filtering system, offering selective filtering to reduce signal distortion. Evaluation of various CNN and RNN-based models reveals VGG and Resnet outperform. Further, the VGG model is superior in terms of performance. But Resnet performs comparably to VGG with less model complexity.

FGSQA-Net: A Weakly Supervised Approach to Fine-Grained Electrocardiogram Signal Quality Assessment

OBJECTIVE

Due to the lack of fine-grained labels, current research can only evaluate the signal quality at a coarse scale. This article proposes a weakly supervised fine-grained electrocardiogram (ECG) signal quality assessment method, which can produce continuous segment-level quality scores with only coarse labels.

METHODS

A novel network architecture, i.e. FGSQA-Net, is developed for signal quality assessment, which consists of a feature shrinking module and a feature aggregation module. Multiple feature shrinking blocks, which combine residual CNN block and max pooling layer, are stacked to produce a feature map corresponding to continuous segments along the spatial dimension. Segment-level quality scores are obtained by feature aggregation along the channel dimension.

RESULTS

The proposed method was evaluated on two real-world ECG databases and one synthetic dataset. Our method produced an average AUC value of 0.975, which outperforms the state-of-the-art beat-by-beat quality assessment method. The results are visualized for 12-lead and single-lead signals over a granularity from 0.64 to 1.7 seconds, demonstrating that high-quality and low-quality segments can be effectively distinguished at a fine scale.

CONCLUSION

FGSQA-Net is flexible and effective for fine-grained quality assessment for various ECG recordings and is suitable for ECG monitoring using wearable devices.

SIGNIFICANCE

This is the first study on fine-grained ECG quality assessment using weak labels and can be generalized to similar tasks for other physiological signals.

Practical intelligent diagnostic algorithm for wearable 12-lead ECG via self-supervised learning on large-scale dataset

Cardiovascular disease is a major global public health problem, and intelligent diagnostic approaches play an increasingly important role in the analysis of electrocardiograms (ECGs). Convenient wearable ECG devices enable the detection of transient arrhythmias and improve patient health by making it possible to seek intervention during continuous monitoring. We collected 658,486 wearable 12-lead ECGs, among which 164,538 were annotated, and the remaining 493,948 were without diagnostic. We present four data augmentation operations and a self-supervised learning classification framework that can recognize 60 ECG diagnostic terms. Our model achieves an average area under the receiver-operating characteristic curve (AUROC) and average F1 score on the offline test of 0.975 and 0.575. The average sensitivity, specificity and F1-score during the 2-month online test are 0.736, 0.954 and 0.468, respectively. This approach offers real-time intelligent diagnosis, and detects abnormal segments in long-term ECG monitoring in the clinical setting for further diagnosis by cardiologists.

[Application of wearable 12-lead electrocardiogram devices in pre-hospital diagnosis of acute ST segment elevation myocardial infarction]

OBJECTIVE

To assess the value of wearable 12-lead electrocardiogram (ECG) devices in pre-hospital diagnosis of acute ST segment elevation myocardial infarction (STEMI).

METHODS

This analysis was conducted among 441 patients selected from the''National ECG Network'', who used wearable 12-lead ECG device with critical situation warning of ST change between January 2019, and August, 2021.The general characteristics, response time and complaints of the patients with STEMI were analyzed.The accuracy of pre-hospital diagnosis of STEMI was compared between clinician's interpretation of ECGs and AI diagnosis by the wearable ECG device.

RESULTS

In 89 of the patients, a pre-hospital diagnosis of STEMI was made by physicians based on ECGs from the wearable devices, and 58 of them sought medical attention after online warning, with a referral rate of 65.17%.The average time for diagnostic assessment of the ECGs was 153.02 s, and the average time for confirmation of the diagnosis was 178.06 s.The sensitivity for pre-hospital diagnosis of STEMI by clinician's interpretation of the ECGs and by AI diagnosis was 100% and 88.37%, respectively, with a specificity of 95.40% and 79.31%, respectively.The pre-hospital diagnosis by clinicians and AI diagnosis of STEMI both showed a high consistency with the subsequent definite clinical diagnosis of STEMI.

CONCLUSION

Wearable 12-lead ECG devices can accurately record ECG characteristics of STEMI patients outside the hospital and allow immediate data uploading for an early diagnosis.The diagnoses of STEMI made based on AI technology are highly consistent with those by clinicians, demonstrating excellent clinical performance of the wearable ECG devices.