+1 Recommend
0 collections
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Machine‐learning‐derived sleep–wake staging from around‐the‐ear electroencephalogram outperforms manual scoring and actigraphy


      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.


          Quantification of sleep is important for the diagnosis of sleep disorders and sleep research. However, the only widely accepted method to obtain sleep staging is by visual analysis of polysomnography (PSG), which is expensive and time consuming. Here, we investigate automated sleep scoring based on a low‐cost, mobile electroencephalogram (EEG) platform consisting of a lightweight EEG amplifier combined with flex‐printed cEEGrid electrodes placed around the ear, which can be implemented as a fully self‐applicable sleep system. However, cEEGrid signals have different amplitude characteristics to normal scalp PSG signals, which might be challenging for visual scoring. Therefore, this study evaluates the potential of automatic scoring of cEEGrid signals using a machine learning classifier (“random forests”) and compares its performance with manual scoring of standard PSG. In addition, the automatic scoring of cEEGrid signals is compared with manual annotation of the cEEGrid recording and with simultaneous actigraphy. Acceptable recordings were obtained in 15 healthy volunteers (aged 35 ± 14.3 years) during an extended nocturnal sleep opportunity, which induced disrupted sleep with a large inter‐individual variation in sleep parameters. The results demonstrate that machine‐learning‐based scoring of around‐the‐ear EEG outperforms actigraphy with respect to sleep onset and total sleep time assessments. The automated scoring outperforms human scoring of cEEGrid by standard criteria. The accuracy of machine‐learning‐based automated scoring of cEEGrid sleep recordings compared with manual scoring of standard PSG was satisfactory. The findings show that cEEGrid recordings combined with machine‐learning‐based scoring holds promise for large‐scale sleep studies.

          Related collections

          Most cited references29

          • Record: found
          • Abstract: not found
          • Article: not found

          AASM Scoring Manual Updates for 2017 (Version 2.4)

            • Record: found
            • Abstract: found
            • Article: not found

            How about taking a low-cost, small, and wireless EEG for a walk?

            To build a low-cost, small, and wireless electroencephalogram (EEG) system suitable for field recordings, we merged consumer EEG hardware with an EEG electrode cap. Auditory oddball data were obtained while participants walked outdoors on university campus. Single-trial P300 classification with linear discriminant analysis revealed high classification accuracies for both indoor (77%) and outdoor (69%) recording conditions. We conclude that good quality, single-trial EEG data suitable for mobile brain-computer interfaces can be obtained with affordable hardware. Copyright © 2012 Society for Psychophysiological Research.
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              Unobtrusive ambulatory EEG using a smartphone and flexible printed electrodes around the ear

              This study presents first evidence that reliable EEG data can be recorded with a new cEEGrid electrode array, which consists of ten electrodes printed on flexible sheet and arranged in a c-shape to fit around the ear. Ten participants wore two cEEGrid systems for at least seven hours. Using a smartphone for stimulus delivery and signal acquisition, resting EEG and auditory oddball data were collected in the morning and in the afternoon six to seven hours apart. Analysis of resting EEG data confirmed well-known spectral differences between eyes open and eyes closed conditions. The ERP results confirmed the predicted condition effects with significantly larger P300 amplitudes for target compared to standard tones, and a high test-retest reliability of the P300 amplitude (r > = .74). Moreover, a linear classifier trained on data from the morning session revealed similar performance in classification accuracy for the morning and the afternoon sessions (both > 70%). These findings demonstrate the feasibility of concealed and comfortable brain activity acquisition over many hours.

                Author and article information

                J Sleep Res
                J Sleep Res
                Journal of Sleep Research
                John Wiley and Sons Inc. (Hoboken )
                13 November 2018
                April 2019
                : 28
                : 2 ( doiID: 10.1111/jsr.2019.28.issue-2 )
                : e12786
                [ 1 ] Institute of Biomedical Engineering University of Oxford Oxford UK
                [ 2 ] Department of Engineering Aarhus University Aarhus Denmark
                [ 3 ] School of Psychology University of Surrey Surrey UK
                [ 4 ] Surrey Sleep Research Centre University of Surrey Surrey UK
                [ 5 ] Surrey Clinical Research Centre University of Surrey Surrey UK
                [ 6 ] Cluster of Excellence Hearing4All Oldenburg Germany
                [ 7 ] Department of Psychology University of Oldenburg Oldenburg Germany
                Author notes
                [*] [* ] Correspondence

                Maarten de Vos, Institute of Biomedical Engineering, University of Oxford, Oxford, UK.

                Email: maarten.devos@ 123456eng.ox.ac.uk

                Author information
                © 2018 The Authors. Journal of Sleep Research published by John Wiley & Sons Ltd on behalf of European Sleep Research Society.

                This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

                : 01 April 2018
                : 23 September 2018
                : 05 October 2018
                Page count
                Figures: 7, Tables: 7, Pages: 0, Words: 10005
                Funded by: Wellcome Trust
                Funded by: Circadian Therapeutics
                Funded by: NIHR Oxford Biomedical Research Centre
                Funded by: EPSRC
                Award ID: EP/K503939/1
                Funded by: SCNi
                Award ID: 098461/Z/12/Z
                Regular Research Paper
                Methods in Sleep Research and Sleep Medicine
                Custom metadata
                April 2019
                Converter:WILEY_ML3GV2_TO_NLMPMC version: mode:remove_FC converted:03.04.2019

                automated sleep scoring,ear eeg,eeg,home eeg,mobile eeg
                automated sleep scoring, ear eeg, eeg, home eeg, mobile eeg


                Comment on this article