Detection of REM sleep behaviour disorder by automated polysomnography analysis
<p><strong>Objective</strong> Evidence suggests Rapid-Eye-Movement (REM) Sleep Behaviour Disorder (RBD) is an early predictor of Parkinson’s disease. This study proposes a fully-automated framework for RBD detection consisting of automated sleep staging followed by RBD identificati...
| Príomhchruthaitheoirí: | , , , , , |
|---|---|
| Formáid: | Journal article |
| Teanga: | English |
| Foilsithe / Cruthaithe: |
Elsevier
2019
|
| _version_ | 1826285047346364416 |
|---|---|
| author | Cooray, N Andreotti, F Lo, C Symmonds, M Hu, M De Vos, M |
| author_facet | Cooray, N Andreotti, F Lo, C Symmonds, M Hu, M De Vos, M |
| author_sort | Cooray, N |
| collection | OXFORD |
| description | <p><strong>Objective</strong> Evidence suggests Rapid-Eye-Movement (REM) Sleep Behaviour Disorder (RBD) is an early predictor of Parkinson’s disease. This study proposes a fully-automated framework for RBD detection consisting of automated sleep staging followed by RBD identification.</p> <p><strong>Methods</strong> Analysis was assessed using a limited polysomnography montage from 53 participants with RBD and 53 age-matched healthy controls. Sleep stage classification was achieved using a Random Forest (RF) classifier and 156 features extracted from electroencephalogram (EEG), electrooculogram (EOG) and electromyogram (EMG) channels. For RBD detection, a RF classifier was trained combining established techniques to quantify muscle atonia with additional features that incorporate sleep architecture and the EMG fractal exponent.</p> <p><strong>Results</strong> Automated multi-state sleep staging achieved a 0.62 Cohen’s Kappa score. RBD detection accuracy improved from 86% to 96% (compared to individual established metrics) when using manually annotated sleep staging. Accuracy remained high (92%) when using automated sleep staging.</p> <p><strong>Conclusions</strong> This study outperforms established metrics and demonstrates that incorporating sleep architecture and sleep stage transitions can benefit RBD detection. This study also achieved automated sleep staging with a level of accuracy comparable to manual annotation.</p> <p><strong>Significance</strong> This study validates a tractable, fully-automated, and sensitive pipeline for RBD identification that could be translated to wearable take-home technology.</p> |
| first_indexed | 2024-03-07T01:23:00Z |
| format | Journal article |
| id | oxford-uuid:9100ce43-d5a6-4796-bdc7-92b9af2186f2 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T01:23:00Z |
| publishDate | 2019 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:9100ce43-d5a6-4796-bdc7-92b9af2186f22022-03-26T23:15:43ZDetection of REM sleep behaviour disorder by automated polysomnography analysisJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:9100ce43-d5a6-4796-bdc7-92b9af2186f2EnglishSymplectic Elements at OxfordElsevier2019Cooray, NAndreotti, FLo, CSymmonds, MHu, MDe Vos, M<p><strong>Objective</strong> Evidence suggests Rapid-Eye-Movement (REM) Sleep Behaviour Disorder (RBD) is an early predictor of Parkinson’s disease. This study proposes a fully-automated framework for RBD detection consisting of automated sleep staging followed by RBD identification.</p> <p><strong>Methods</strong> Analysis was assessed using a limited polysomnography montage from 53 participants with RBD and 53 age-matched healthy controls. Sleep stage classification was achieved using a Random Forest (RF) classifier and 156 features extracted from electroencephalogram (EEG), electrooculogram (EOG) and electromyogram (EMG) channels. For RBD detection, a RF classifier was trained combining established techniques to quantify muscle atonia with additional features that incorporate sleep architecture and the EMG fractal exponent.</p> <p><strong>Results</strong> Automated multi-state sleep staging achieved a 0.62 Cohen’s Kappa score. RBD detection accuracy improved from 86% to 96% (compared to individual established metrics) when using manually annotated sleep staging. Accuracy remained high (92%) when using automated sleep staging.</p> <p><strong>Conclusions</strong> This study outperforms established metrics and demonstrates that incorporating sleep architecture and sleep stage transitions can benefit RBD detection. This study also achieved automated sleep staging with a level of accuracy comparable to manual annotation.</p> <p><strong>Significance</strong> This study validates a tractable, fully-automated, and sensitive pipeline for RBD identification that could be translated to wearable take-home technology.</p> |
| spellingShingle | Cooray, N Andreotti, F Lo, C Symmonds, M Hu, M De Vos, M Detection of REM sleep behaviour disorder by automated polysomnography analysis |
| title | Detection of REM sleep behaviour disorder by automated polysomnography analysis |
| title_full | Detection of REM sleep behaviour disorder by automated polysomnography analysis |
| title_fullStr | Detection of REM sleep behaviour disorder by automated polysomnography analysis |
| title_full_unstemmed | Detection of REM sleep behaviour disorder by automated polysomnography analysis |
| title_short | Detection of REM sleep behaviour disorder by automated polysomnography analysis |
| title_sort | detection of rem sleep behaviour disorder by automated polysomnography analysis |
| work_keys_str_mv | AT coorayn detectionofremsleepbehaviourdisorderbyautomatedpolysomnographyanalysis AT andreottif detectionofremsleepbehaviourdisorderbyautomatedpolysomnographyanalysis AT loc detectionofremsleepbehaviourdisorderbyautomatedpolysomnographyanalysis AT symmondsm detectionofremsleepbehaviourdisorderbyautomatedpolysomnographyanalysis AT hum detectionofremsleepbehaviourdisorderbyautomatedpolysomnographyanalysis AT devosm detectionofremsleepbehaviourdisorderbyautomatedpolysomnographyanalysis |