Validation Study on Automated Sleep Stage Scoring Using a Deep Learning Algorithm
<i>Background and Objectives:</i> Polysomnography is manually scored by sleep experts. However, manual scoring is a time-consuming and labor-intensive task. The goal of this study was to verify the accuracy of automated sleep-stage scoring based on a deep learning algorithm compared to m...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Medicina |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1648-9144/58/6/779 |
| _version_ | 1827658584834441216 |
|---|---|
| author | Jae Hoon Cho Ji Ho Choi Ji Eun Moon Young Jun Lee Ho Dong Lee Tae Kyoung Ha |
| author_facet | Jae Hoon Cho Ji Ho Choi Ji Eun Moon Young Jun Lee Ho Dong Lee Tae Kyoung Ha |
| author_sort | Jae Hoon Cho |
| collection | DOAJ |
| description | <i>Background and Objectives:</i> Polysomnography is manually scored by sleep experts. However, manual scoring is a time-consuming and labor-intensive task. The goal of this study was to verify the accuracy of automated sleep-stage scoring based on a deep learning algorithm compared to manual sleep-stage scoring. <i>Materials and Methods:</i> A total of 602 polysomnography datasets from subjects (Male:Female = 397:205) aged 19 to 65 years (mean age, 43.8, standard deviation = 12.2) were included in the study. The performance of the proposed model was evaluated based on kappa value and bootstrapped point-estimate of median percent agreement with a 95% bootstrap confidence interval and R = 1000. The proposed model was trained using 482 datasets and validated using 48 datasets. For testing, 72 datasets were selected randomly. <i>Results:</i> The proposed model exhibited good concordance rates with manual scoring for stages W (94%), N1 (83.9%), N2 (89%), N3 (92%), and R (93%). The average kappa value was 0.84. For the bootstrap method, high overall agreement between the automated deep learning algorithm and manual scoring was observed in stages W (98%), N1 (94%), N2 (92%), N3 (99%), and R (98%) and total (96%). <i>Conclusions:</i> Automated sleep-stage scoring using the proposed model may be a reliable method for sleep-stage classification. |
| first_indexed | 2024-03-09T23:06:43Z |
| format | Article |
| id | doaj.art-3e5185c323c24a4390edbcb433837f09 |
| institution | Directory Open Access Journal |
| issn | 1010-660X 1648-9144 |
| language | English |
| last_indexed | 2024-03-09T23:06:43Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Medicina |
| spelling | doaj.art-3e5185c323c24a4390edbcb433837f092023-11-23T17:52:27ZengMDPI AGMedicina1010-660X1648-91442022-06-0158677910.3390/medicina58060779Validation Study on Automated Sleep Stage Scoring Using a Deep Learning AlgorithmJae Hoon Cho0Ji Ho Choi1Ji Eun Moon2Young Jun Lee3Ho Dong Lee4Tae Kyoung Ha5Department of Otorhinolaryngology-Head and Neck Surgery, Konkuk University School of Medicine, 120-1, Neungdong-ro, Gwangjin-gu, Seoul 05030, KoreaDepartment of Otorhinolaryngology-Head and Neck Surgery, Soonchunhyang University College of Medicine, Bucheon Hospital, 170, Jomaru-ro, Bucheon 14584, KoreaDepartment of Biostatistics, Clinical Trial Center, Soonchunhyang University Bucheon Hospital, 170, Jomaru-ro, Bucheon 14584, KoreaHoneynaps Research and Development Center, Honeynaps Co., Ltd., 4F, 529, Nonhyeon-ro, Gangnam-gu, Seoul 06126, KoreaHoneynaps Research and Development Center, Honeynaps Co., Ltd., 4F, 529, Nonhyeon-ro, Gangnam-gu, Seoul 06126, KoreaHoneynaps Research and Development Center, Honeynaps Co., Ltd., 4F, 529, Nonhyeon-ro, Gangnam-gu, Seoul 06126, Korea<i>Background and Objectives:</i> Polysomnography is manually scored by sleep experts. However, manual scoring is a time-consuming and labor-intensive task. The goal of this study was to verify the accuracy of automated sleep-stage scoring based on a deep learning algorithm compared to manual sleep-stage scoring. <i>Materials and Methods:</i> A total of 602 polysomnography datasets from subjects (Male:Female = 397:205) aged 19 to 65 years (mean age, 43.8, standard deviation = 12.2) were included in the study. The performance of the proposed model was evaluated based on kappa value and bootstrapped point-estimate of median percent agreement with a 95% bootstrap confidence interval and R = 1000. The proposed model was trained using 482 datasets and validated using 48 datasets. For testing, 72 datasets were selected randomly. <i>Results:</i> The proposed model exhibited good concordance rates with manual scoring for stages W (94%), N1 (83.9%), N2 (89%), N3 (92%), and R (93%). The average kappa value was 0.84. For the bootstrap method, high overall agreement between the automated deep learning algorithm and manual scoring was observed in stages W (98%), N1 (94%), N2 (92%), N3 (99%), and R (98%) and total (96%). <i>Conclusions:</i> Automated sleep-stage scoring using the proposed model may be a reliable method for sleep-stage classification.https://www.mdpi.com/1648-9144/58/6/779polysomnographysleep stagesdeep learningalgorithms |
| spellingShingle | Jae Hoon Cho Ji Ho Choi Ji Eun Moon Young Jun Lee Ho Dong Lee Tae Kyoung Ha Validation Study on Automated Sleep Stage Scoring Using a Deep Learning Algorithm Medicina polysomnography sleep stages deep learning algorithms |
| title | Validation Study on Automated Sleep Stage Scoring Using a Deep Learning Algorithm |
| title_full | Validation Study on Automated Sleep Stage Scoring Using a Deep Learning Algorithm |
| title_fullStr | Validation Study on Automated Sleep Stage Scoring Using a Deep Learning Algorithm |
| title_full_unstemmed | Validation Study on Automated Sleep Stage Scoring Using a Deep Learning Algorithm |
| title_short | Validation Study on Automated Sleep Stage Scoring Using a Deep Learning Algorithm |
| title_sort | validation study on automated sleep stage scoring using a deep learning algorithm |
| topic | polysomnography sleep stages deep learning algorithms |
| url | https://www.mdpi.com/1648-9144/58/6/779 |
| work_keys_str_mv | AT jaehooncho validationstudyonautomatedsleepstagescoringusingadeeplearningalgorithm AT jihochoi validationstudyonautomatedsleepstagescoringusingadeeplearningalgorithm AT jieunmoon validationstudyonautomatedsleepstagescoringusingadeeplearningalgorithm AT youngjunlee validationstudyonautomatedsleepstagescoringusingadeeplearningalgorithm AT hodonglee validationstudyonautomatedsleepstagescoringusingadeeplearningalgorithm AT taekyoungha validationstudyonautomatedsleepstagescoringusingadeeplearningalgorithm |