Navin Cooray1, Fernando Andreotti2, Christine Lo3, Mkael Symmonds4, Michele T M Hu3, Maarten De Vos2. 1. University of Oxford, Institute of Biomedical Engineering, Dept. Engineering Sciences, Oxford, UK. Electronic address: navin.cooray@eng.ox.ac.uk. 2. University of Oxford, Institute of Biomedical Engineering, Dept. Engineering Sciences, Oxford, UK. 3. Nuffield Department of Clinical Neurosciences, Oxford Parkinson's Disease Centre (OPDC), University of Oxford, UK. 4. Department of Clinical Neurophysiology, Oxford University Hospitals, John Radcliffe Hospital, University of Oxford, UK.
Abstract
OBJECTIVE: 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. METHODS: 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. RESULTS: 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. CONCLUSIONS: 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. SIGNIFICANCE: This study validates a tractable, fully-automated, and sensitive pipeline for RBD identification that could be translated to wearable take-home technology.
OBJECTIVE: 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. METHODS: 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. RESULTS: 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. CONCLUSIONS: 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. SIGNIFICANCE: This study validates a tractable, fully-automated, and sensitive pipeline for RBD identification that could be translated to wearable take-home technology.
Authors: Huy Phan; Fernando Andreotti; Navin Cooray; Oliver Y Chen; Maarten De Vos Journal: IEEE Trans Neural Syst Rehabil Eng Date: 2019-01-31 Impact factor: 3.802
Authors: Navin Cooray; Fernando Andreotti; Christine Lo; Mkael Symmonds; Michele T M Hu; Maarten De Vos Journal: Clin Neurophysiol Date: 2021-02-03 Impact factor: 3.708
Authors: Mo H Modarres; Jonathan E Elliott; Kristianna B Weymann; Dennis Pleshakov; Donald L Bliwise; Miranda M Lim Journal: Sensors (Basel) Date: 2021-12-22 Impact factor: 3.576
Authors: Mitchell G Miglis; Charles H Adler; Elena Antelmi; Dario Arnaldi; Luca Baldelli; Bradley F Boeve; Matteo Cesari; Irene Dall'Antonia; Nico J Diederich; Kathrin Doppler; Petr Dušek; Raffaele Ferri; Jean-François Gagnon; Ziv Gan-Or; Wiebke Hermann; Birgit Högl; Michele T Hu; Alex Iranzo; Annette Janzen; Anastasia Kuzkina; Jee-Young Lee; Klaus L Leenders; Simon J G Lewis; Claudio Liguori; Jun Liu; Christine Lo; Kaylena A Ehgoetz Martens; Jiri Nepozitek; Giuseppe Plazzi; Federica Provini; Monica Puligheddu; Michal Rolinski; Jan Rusz; Ambra Stefani; Rebekah L S Summers; Dallah Yoo; Jennifer Zitser; Wolfgang H Oertel Journal: Lancet Neurol Date: 2021-08 Impact factor: 44.182