Deep Convolutional Recurrent Model for Automatic Scoring Sleep Stages Based on Single-Lead ECG Signal
Background: Sleep stage scoring, which is an essential step in the quantitative analysis of sleep monitoring, relies on human experts and is therefore subjective and time-consuming; thus, an easy and accurate method is needed for the automatic scoring of sleep stages. Methods: In this study, we cons...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/5/1235 |
| _version_ | 1797500422009651200 |
|---|---|
| author | Erdenebayar Urtnasan Jong-Uk Park Eun Yeon Joo Kyoung-Joung Lee |
| author_facet | Erdenebayar Urtnasan Jong-Uk Park Eun Yeon Joo Kyoung-Joung Lee |
| author_sort | Erdenebayar Urtnasan |
| collection | DOAJ |
| description | Background: Sleep stage scoring, which is an essential step in the quantitative analysis of sleep monitoring, relies on human experts and is therefore subjective and time-consuming; thus, an easy and accurate method is needed for the automatic scoring of sleep stages. Methods: In this study, we constructed a deep convolutional recurrent (DCR) model for the automatic scoring of sleep stages based on a raw single-lead electrocardiogram (ECG). The DCR model uses deep convolutional and recurrent neural networks to apply the complex and cyclic rhythms of human sleep. It consists of three convolutional and two recurrent layers and is optimized by dropout and batch normalization. The constructed DCR model was evaluated using multiclass classification, including five-class sleep stages (wake, N1, N2, N3, and rapid eye movement (REM)) and three-class sleep stages (wake, non-REM (NREM), and REM), using a raw single-lead ECG signal. The single-lead ECG signal was collected from 112 subjects in two groups: control (52 subjects) and sleep apnea (60 subjects). The single-lead ECG signal was preprocessed, segmented at a duration of 30 s, and divided into a training set of 89 subjects and test set of 23 subjects. Results: We achieved an overall accuracy of 74.2% for five classes and 86.4% for three classes. Conclusions: These results show the DCR model’s superior performance over those in the previous studies, highlighting that the model can be an alternative tool for sleep monitoring and sleep screening. |
| first_indexed | 2024-03-10T03:01:39Z |
| format | Article |
| id | doaj.art-294588ffc1d444db9ec882a9b06b1de6 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T03:01:39Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-294588ffc1d444db9ec882a9b06b1de62023-11-23T10:41:17ZengMDPI AGDiagnostics2075-44182022-05-01125123510.3390/diagnostics12051235Deep Convolutional Recurrent Model for Automatic Scoring Sleep Stages Based on Single-Lead ECG SignalErdenebayar Urtnasan0Jong-Uk Park1Eun Yeon Joo2Kyoung-Joung Lee3Artificial Intelligence Big Data Medical Center, Wonju College of Medicine, Yonsei University, Wonju 26417, KoreaDepartment of Medical Artificial Intelligence, Medical Engineering College, Konyang University, Daejeon 35365, KoreaDepartment of Neurology, Samsung Medical Center, School of Medicine, Sungkyunkwan University, Suwon 16419, KoreaDepartment of Biomedical Engineering, College of Health Science, Yonsei University, Wonju 26493, KoreaBackground: Sleep stage scoring, which is an essential step in the quantitative analysis of sleep monitoring, relies on human experts and is therefore subjective and time-consuming; thus, an easy and accurate method is needed for the automatic scoring of sleep stages. Methods: In this study, we constructed a deep convolutional recurrent (DCR) model for the automatic scoring of sleep stages based on a raw single-lead electrocardiogram (ECG). The DCR model uses deep convolutional and recurrent neural networks to apply the complex and cyclic rhythms of human sleep. It consists of three convolutional and two recurrent layers and is optimized by dropout and batch normalization. The constructed DCR model was evaluated using multiclass classification, including five-class sleep stages (wake, N1, N2, N3, and rapid eye movement (REM)) and three-class sleep stages (wake, non-REM (NREM), and REM), using a raw single-lead ECG signal. The single-lead ECG signal was collected from 112 subjects in two groups: control (52 subjects) and sleep apnea (60 subjects). The single-lead ECG signal was preprocessed, segmented at a duration of 30 s, and divided into a training set of 89 subjects and test set of 23 subjects. Results: We achieved an overall accuracy of 74.2% for five classes and 86.4% for three classes. Conclusions: These results show the DCR model’s superior performance over those in the previous studies, highlighting that the model can be an alternative tool for sleep monitoring and sleep screening.https://www.mdpi.com/2075-4418/12/5/1235electrocardiogramautomatic sleep scoringdeep learningconvolutional neural networkrecurrent neural networkdeep convolutional recurrent network |
| spellingShingle | Erdenebayar Urtnasan Jong-Uk Park Eun Yeon Joo Kyoung-Joung Lee Deep Convolutional Recurrent Model for Automatic Scoring Sleep Stages Based on Single-Lead ECG Signal Diagnostics electrocardiogram automatic sleep scoring deep learning convolutional neural network recurrent neural network deep convolutional recurrent network |
| title | Deep Convolutional Recurrent Model for Automatic Scoring Sleep Stages Based on Single-Lead ECG Signal |
| title_full | Deep Convolutional Recurrent Model for Automatic Scoring Sleep Stages Based on Single-Lead ECG Signal |
| title_fullStr | Deep Convolutional Recurrent Model for Automatic Scoring Sleep Stages Based on Single-Lead ECG Signal |
| title_full_unstemmed | Deep Convolutional Recurrent Model for Automatic Scoring Sleep Stages Based on Single-Lead ECG Signal |
| title_short | Deep Convolutional Recurrent Model for Automatic Scoring Sleep Stages Based on Single-Lead ECG Signal |
| title_sort | deep convolutional recurrent model for automatic scoring sleep stages based on single lead ecg signal |
| topic | electrocardiogram automatic sleep scoring deep learning convolutional neural network recurrent neural network deep convolutional recurrent network |
| url | https://www.mdpi.com/2075-4418/12/5/1235 |
| work_keys_str_mv | AT erdenebayarurtnasan deepconvolutionalrecurrentmodelforautomaticscoringsleepstagesbasedonsingleleadecgsignal AT jongukpark deepconvolutionalrecurrentmodelforautomaticscoringsleepstagesbasedonsingleleadecgsignal AT eunyeonjoo deepconvolutionalrecurrentmodelforautomaticscoringsleepstagesbasedonsingleleadecgsignal AT kyoungjounglee deepconvolutionalrecurrentmodelforautomaticscoringsleepstagesbasedonsingleleadecgsignal |