Assessing Electrocardiogram and Respiratory Signal Quality of a Wearable Device (SensEcho): Semisupervised Machine Learning-Based Validation Study

Abstract

Background With the development and promotion of wearable devices and their mobile health (mHealth) apps, physiological signals have become a research hotspot. However, noise is complex in signals obtained from daily lives, making it difficult to analyze the signals automatically and resulting in a high false alarm rate. At present, screening out the high-quality segments of the signals from huge-volume data with few labels remains a problem. Signal quality assessment (SQA) is essential and is able to advance the valuable information mining of signals. Objective The aims of this study were to design an SQA algorithm based on the unsupervised isolation forest model to classify the signal quality into 3 grades: good, acceptable, and unacceptable; validate the algorithm on labeled data sets; and apply the algorithm on real-world data to evaluate its efficacy. Methods Data used in this study were collected by a wearable device (SensEcho) from healthy individuals and patients. The observation windows for electrocardiogram (ECG) and respiratory signals were 10 and 30 seconds, respectively. In the experimental procedure, the unlabeled training set was used to train the models. The validation and test sets were labeled according to preset criteria and used to evaluate the classification performance quantitatively. The validation set consisted of 3460 and 2086 windows of ECG and respiratory signals, respectively, whereas the test set was made up of 4686 and 3341 windows of signals, respectively. The algorithm was also compared with self-organizing maps (SOMs) and 4 classic supervised models (logistic regression, random forest, support vector machine, and extreme gradient boosting). One case validation was illustrated to show the application effect. The algorithm was then applied to 1144 cases of ECG signals collected from patients and the detected arrhythmia false alarms were calculated. Results The quantitative results showed that the ECG SQA model achieved 94.97% and 95.58% accuracy on the validation and test sets, respectively, whereas the respiratory SQA model achieved 81.06% and 86.20% accuracy on the validation and test sets, respectively. The algorithm was superior to SOM and achieved moderate performance when compared with the supervised models. The example case showed that the algorithm was able to correctly classify the signal quality even when there were complex pathological changes in the signals. The algorithm application results indicated that some specific types of arrhythmia false alarms such as tachycardia, atrial premature beat, and ventricular premature beat could be significantly reduced with the help of the algorithm. Conclusions This study verified the feasibility of applying the anomaly detection unsupervised model to SQA. The application scenarios include reducing the false alarm rate of the device and selecting signal segments that can be used for further research.

Automatic ECG Quality Assessment Techniques: A Systematic Review

“…Less predictable sources of EMG interference are more difficult to remove and can be the reason the ECG recording is rejected. For example, this can be caused by muscle contractions that produce EMG signals, or vibrations caused by speaking [ 9 , 12 , 23 ].…”

Modulation Spectral Signal Representation for Quality Measurement and Enhancement of Wearable Device Data: A Technical Note

“…Methods can rely on human intervention [27] or be (semi)automated. Representative examples of the latter include methods that rely on data statistics (e.g., [28,29]), spectral/connectivity profiles (e.g., [30][31][32]), blind source separation (e.g., [33,34]), adaptive filtering (e.g., [35,36]), and, more recently, on machine and deep learning approaches (e.g., [37][38][39][40]). Combinations of multiple such approaches have also been proposed (e.g., [41,42]).…”

Wearable Electrocardiogram Quality Assessment Using Wavelet Scattering and LSTM

“…Poor electrocardiographic signal quality can result in misinterpretation and inappropriate results, hazard the correct diagnosis information ( Andrea et al, 2018 ), increases the risk of false alerts ( Liu et al, 2011 ), which may lead to unnecessary medical referrals and testing ( Ip, 2019 ), and increase the workload of physicians ( Zhao and Zhang, 2018 ). Consequently, it is quite urgent to evaluate the quality of wearable dynamic ECG signals, to eliminate signals with serious noise pollution, to distinguish between clean signals that can be used for disease diagnosis and mildly contaminated signals that can only be used for heart rate extraction, which can effectively reduce false alarm and avoid interference with CVD diagnosis ( Xu et al, 2021 ).…”

“…Also, most SQA methods graded the dynamic ECG signal quality into two groups: acceptable versus unacceptable (or good versus bad). In fact, in some wearable ECG signals only R wave could be detected, other waves such as P or ST were drowned out by the noise ( Xu et al, 2021 ). These signals cannot be used for some CVD detection, but they also cannot be abandoned as heart rate information can be obtained.…”