Assessing Electrocardiogram and Respiratory Signal Quality of a Wearable Device (SensEcho): Semisupervised Machine Learning-Based Validation Study
BackgroundWith 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 automatica...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2021-08-01
|
| Series: | JMIR mHealth and uHealth |
| Online Access: | https://mhealth.jmir.org/2021/8/e25415 |
| _version_ | 1797735784536604672 |
|---|---|
| author | Haoran Xu Wei Yan Ke Lan Chenbin Ma Di Wu Anshuo Wu Zhicheng Yang Jiachen Wang Yaning Zang Muyang Yan Zhengbo Zhang |
| author_facet | Haoran Xu Wei Yan Ke Lan Chenbin Ma Di Wu Anshuo Wu Zhicheng Yang Jiachen Wang Yaning Zang Muyang Yan Zhengbo Zhang |
| author_sort | Haoran Xu |
| collection | DOAJ |
| description |
BackgroundWith 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.
ObjectiveThe 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.
MethodsData 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.
ResultsThe 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.
ConclusionsThis 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. |
| first_indexed | 2024-03-12T13:04:06Z |
| format | Article |
| id | doaj.art-2586def62df143269ce919593436d8d2 |
| institution | Directory Open Access Journal |
| issn | 2291-5222 |
| language | English |
| last_indexed | 2024-03-12T13:04:06Z |
| publishDate | 2021-08-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR mHealth and uHealth |
| spelling | doaj.art-2586def62df143269ce919593436d8d22023-08-28T18:30:24ZengJMIR PublicationsJMIR mHealth and uHealth2291-52222021-08-0198e2541510.2196/25415Assessing Electrocardiogram and Respiratory Signal Quality of a Wearable Device (SensEcho): Semisupervised Machine Learning-Based Validation StudyHaoran Xuhttps://orcid.org/0000-0003-4953-2473Wei Yanhttps://orcid.org/0000-0001-5059-8694Ke Lanhttps://orcid.org/0000-0003-0423-5520Chenbin Mahttps://orcid.org/0000-0003-1945-9332Di Wuhttps://orcid.org/0000-0002-6870-443XAnshuo Wuhttps://orcid.org/0000-0002-9219-9197Zhicheng Yanghttps://orcid.org/0000-0001-5868-9814Jiachen Wanghttps://orcid.org/0000-0003-3888-1387Yaning Zanghttps://orcid.org/0000-0002-7655-7070Muyang Yanhttps://orcid.org/0000-0001-6978-1472Zhengbo Zhanghttps://orcid.org/0000-0001-9218-5644 BackgroundWith 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. ObjectiveThe 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. MethodsData 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. ResultsThe 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. ConclusionsThis 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.https://mhealth.jmir.org/2021/8/e25415 |
| spellingShingle | Haoran Xu Wei Yan Ke Lan Chenbin Ma Di Wu Anshuo Wu Zhicheng Yang Jiachen Wang Yaning Zang Muyang Yan Zhengbo Zhang Assessing Electrocardiogram and Respiratory Signal Quality of a Wearable Device (SensEcho): Semisupervised Machine Learning-Based Validation Study JMIR mHealth and uHealth |
| title | Assessing Electrocardiogram and Respiratory Signal Quality of a Wearable Device (SensEcho): Semisupervised Machine Learning-Based Validation Study |
| title_full | Assessing Electrocardiogram and Respiratory Signal Quality of a Wearable Device (SensEcho): Semisupervised Machine Learning-Based Validation Study |
| title_fullStr | Assessing Electrocardiogram and Respiratory Signal Quality of a Wearable Device (SensEcho): Semisupervised Machine Learning-Based Validation Study |
| title_full_unstemmed | Assessing Electrocardiogram and Respiratory Signal Quality of a Wearable Device (SensEcho): Semisupervised Machine Learning-Based Validation Study |
| title_short | Assessing Electrocardiogram and Respiratory Signal Quality of a Wearable Device (SensEcho): Semisupervised Machine Learning-Based Validation Study |
| title_sort | assessing electrocardiogram and respiratory signal quality of a wearable device sensecho semisupervised machine learning based validation study |
| url | https://mhealth.jmir.org/2021/8/e25415 |
| work_keys_str_mv | AT haoranxu assessingelectrocardiogramandrespiratorysignalqualityofawearabledevicesensechosemisupervisedmachinelearningbasedvalidationstudy AT weiyan assessingelectrocardiogramandrespiratorysignalqualityofawearabledevicesensechosemisupervisedmachinelearningbasedvalidationstudy AT kelan assessingelectrocardiogramandrespiratorysignalqualityofawearabledevicesensechosemisupervisedmachinelearningbasedvalidationstudy AT chenbinma assessingelectrocardiogramandrespiratorysignalqualityofawearabledevicesensechosemisupervisedmachinelearningbasedvalidationstudy AT diwu assessingelectrocardiogramandrespiratorysignalqualityofawearabledevicesensechosemisupervisedmachinelearningbasedvalidationstudy AT anshuowu assessingelectrocardiogramandrespiratorysignalqualityofawearabledevicesensechosemisupervisedmachinelearningbasedvalidationstudy AT zhichengyang assessingelectrocardiogramandrespiratorysignalqualityofawearabledevicesensechosemisupervisedmachinelearningbasedvalidationstudy AT jiachenwang assessingelectrocardiogramandrespiratorysignalqualityofawearabledevicesensechosemisupervisedmachinelearningbasedvalidationstudy AT yaningzang assessingelectrocardiogramandrespiratorysignalqualityofawearabledevicesensechosemisupervisedmachinelearningbasedvalidationstudy AT muyangyan assessingelectrocardiogramandrespiratorysignalqualityofawearabledevicesensechosemisupervisedmachinelearningbasedvalidationstudy AT zhengbozhang assessingelectrocardiogramandrespiratorysignalqualityofawearabledevicesensechosemisupervisedmachinelearningbasedvalidationstudy |