Deep Learning Application to Clinical Decision Support System in Sleep Stage Classification
Recently, deep learning for automated sleep stage classification has been introduced with promising results. However, as many challenges impede their routine application, automatic sleep scoring algorithms are not widely used. Typically, polysomnography (PSG) uses multiple channels for higher accura...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/12/2/136 |
| _version_ | 1797478908271001600 |
|---|---|
| author | Dongyoung Kim Jeonggun Lee Yunhee Woo Jaemin Jeong Chulho Kim Dong-Kyu Kim |
| author_facet | Dongyoung Kim Jeonggun Lee Yunhee Woo Jaemin Jeong Chulho Kim Dong-Kyu Kim |
| author_sort | Dongyoung Kim |
| collection | DOAJ |
| description | Recently, deep learning for automated sleep stage classification has been introduced with promising results. However, as many challenges impede their routine application, automatic sleep scoring algorithms are not widely used. Typically, polysomnography (PSG) uses multiple channels for higher accuracy; however, the disadvantages include a requirement for a patient to stay one or more nights in the lab wearing uncomfortable sensors and wires. To avoid the inconvenience caused by the multiple channels, we aimed to develop a deep learning model for use in clinical decision support systems (CDSSs) and combined convolutional neural networks and a transformer for the supervised learning of three classes of sleep stages only with single-channel EEG data (C4-M1). The data for training, validation, and test were derived from 1590, 341, and 343 polysomnography recordings, respectively. The developed model yielded an overall accuracy of 91.4%, comparable with that of human experts. Based on the severity of obstructive sleep apnea, the model’s accuracy was 94.3%, 91.9%, 91.9%, and 90.6% in normal, mild, moderate, and severe cases, respectively. Our deep learning model enables accurate and rapid delineation of three-class sleep staging and could be useful as a CDSS for application in real-world clinical practice. |
| first_indexed | 2024-03-09T21:38:18Z |
| format | Article |
| id | doaj.art-8797c1053ae241fc9ea6284d7b34476d |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-09T21:38:18Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-8797c1053ae241fc9ea6284d7b34476d2023-11-23T20:38:47ZengMDPI AGJournal of Personalized Medicine2075-44262022-01-0112213610.3390/jpm12020136Deep Learning Application to Clinical Decision Support System in Sleep Stage ClassificationDongyoung Kim0Jeonggun Lee1Yunhee Woo2Jaemin Jeong3Chulho Kim4Dong-Kyu Kim5Department of Computer Engineering, Hallym University, Chuncheon 24252, KoreaDepartment of Computer Engineering, Hallym University, Chuncheon 24252, KoreaDepartment of Computer Engineering, Hallym University, Chuncheon 24252, KoreaDepartment of Computer Engineering, Hallym University, Chuncheon 24252, KoreaDepartment of Neurology, Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon 24252, KoreaInstitute of New Frontier Research, Division of Big Data and Artificial Intelligence, Chuncheon Sacred Heart Hospital, Chuncheon 24252, KoreaRecently, deep learning for automated sleep stage classification has been introduced with promising results. However, as many challenges impede their routine application, automatic sleep scoring algorithms are not widely used. Typically, polysomnography (PSG) uses multiple channels for higher accuracy; however, the disadvantages include a requirement for a patient to stay one or more nights in the lab wearing uncomfortable sensors and wires. To avoid the inconvenience caused by the multiple channels, we aimed to develop a deep learning model for use in clinical decision support systems (CDSSs) and combined convolutional neural networks and a transformer for the supervised learning of three classes of sleep stages only with single-channel EEG data (C4-M1). The data for training, validation, and test were derived from 1590, 341, and 343 polysomnography recordings, respectively. The developed model yielded an overall accuracy of 91.4%, comparable with that of human experts. Based on the severity of obstructive sleep apnea, the model’s accuracy was 94.3%, 91.9%, 91.9%, and 90.6% in normal, mild, moderate, and severe cases, respectively. Our deep learning model enables accurate and rapid delineation of three-class sleep staging and could be useful as a CDSS for application in real-world clinical practice.https://www.mdpi.com/2075-4426/12/2/136deep learningsleep scoringneural networkEEGsleep staging |
| spellingShingle | Dongyoung Kim Jeonggun Lee Yunhee Woo Jaemin Jeong Chulho Kim Dong-Kyu Kim Deep Learning Application to Clinical Decision Support System in Sleep Stage Classification Journal of Personalized Medicine deep learning sleep scoring neural network EEG sleep staging |
| title | Deep Learning Application to Clinical Decision Support System in Sleep Stage Classification |
| title_full | Deep Learning Application to Clinical Decision Support System in Sleep Stage Classification |
| title_fullStr | Deep Learning Application to Clinical Decision Support System in Sleep Stage Classification |
| title_full_unstemmed | Deep Learning Application to Clinical Decision Support System in Sleep Stage Classification |
| title_short | Deep Learning Application to Clinical Decision Support System in Sleep Stage Classification |
| title_sort | deep learning application to clinical decision support system in sleep stage classification |
| topic | deep learning sleep scoring neural network EEG sleep staging |
| url | https://www.mdpi.com/2075-4426/12/2/136 |
| work_keys_str_mv | AT dongyoungkim deeplearningapplicationtoclinicaldecisionsupportsysteminsleepstageclassification AT jeonggunlee deeplearningapplicationtoclinicaldecisionsupportsysteminsleepstageclassification AT yunheewoo deeplearningapplicationtoclinicaldecisionsupportsysteminsleepstageclassification AT jaeminjeong deeplearningapplicationtoclinicaldecisionsupportsysteminsleepstageclassification AT chulhokim deeplearningapplicationtoclinicaldecisionsupportsysteminsleepstageclassification AT dongkyukim deeplearningapplicationtoclinicaldecisionsupportsysteminsleepstageclassification |