elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Evaluation of an automated pipeline for large-scale EEG spectral analysis: the National Sleep Research Resource

Mariani, S. and Tarokh, L. and Djonlagic, I. and Cade, B.E. and Morrical, M.G. and Yaffe, K. and Stone, K.L. and Loparo, K.A. and Purcell, S. and Redline, S. and Aeschbach, Daniel (2018) Evaluation of an automated pipeline for large-scale EEG spectral analysis: the National Sleep Research Resource. Sleep Medicine (47), pp. 126-136. Elsevier. DOI: 10.1016/j.sleep.2017.11.1128 ISSN 1389-9457

Full text not available from this repository.

Abstract

Study objectives: We present an automated sleep electroencephalogram (EEG) spectral analysis pipeline that includes an automated artifact detection step, and we test the hypothesis that spectral power density estimates computed with this pipeline are comparable to those computed with a commercial method preceded by visual artifact detection by a sleep expert (standard approach). Methods: EEG data were analyzed from the C3-A2 lead in a sample of polysomnograms from 161 older women participants in a community-based cohort study. We calculated the sensitivity, specificity, accuracy, and Cohen's kappa measures from epoch-by-epoch comparisons of automated to visual-based artifact detection results; then we computed the average EEG spectral power densities in six commonly used EEG frequency bands and compared results from the two methods using correlation analysis and BlandeAltman plots. Results: Assessment of automated artifact detection showed high specificity [96.8%e99.4% in non-rapid eye movement (NREM), 96.9%e99.1% in rapid eye movement (REM) sleep] but low sensitivity (26.7% e38.1% in NREM, 9.1e27.4% in REM sleep). However, large artifacts (total power > 99th percentile) were removed with sensitivity up to 87.7% in NREM and 90.9% in REM, with specificities of 96.9% and 96.6%, respectively. Mean power densities computed with the two approaches for all EEG frequency bands showed very high correlation (≥0.99). The automated pipeline allowed for a 100-fold reduction in analysis time with regard to the standard approach. Conclusion: Despite low sensitivity for artifact rejection, the automated pipeline generated results comparable to those obtained with a standard method that included manual artifact detection. Automated pipelines can enable practical analyses of recordings from thousands of individuals, allowing for use in genetics and epidemiological research requiring large samples.

Item URL in elib:https://elib.dlr.de/120151/
Document Type:Article
Title:Evaluation of an automated pipeline for large-scale EEG spectral analysis: the National Sleep Research Resource
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Mariani, S.UNSPECIFIEDUNSPECIFIED
Tarokh, L.UNSPECIFIEDUNSPECIFIED
Djonlagic, I.UNSPECIFIEDUNSPECIFIED
Cade, B.E.UNSPECIFIEDUNSPECIFIED
Morrical, M.G.UNSPECIFIEDUNSPECIFIED
Yaffe, K.UNSPECIFIEDUNSPECIFIED
Stone, K.L.UNSPECIFIEDUNSPECIFIED
Loparo, K.A.UNSPECIFIEDUNSPECIFIED
Purcell, S.UNSPECIFIEDUNSPECIFIED
Redline, S.UNSPECIFIEDUNSPECIFIED
Aeschbach, DanielDaniel.Aeschbach (at) dlr.deUNSPECIFIED
Date:2018
Journal or Publication Title:Sleep Medicine
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
DOI :10.1016/j.sleep.2017.11.1128
Page Range:pp. 126-136
Publisher:Elsevier
Series Name:Elsevier Sleep Medicine
ISSN:1389-9457
Status:Published
Keywords:Large-scale spectral Analysis, Sleep-EEG, artifact detection
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Aeronautics
HGF - Program Themes:air traffic management and operations
DLR - Research area:Aeronautics
DLR - Program:L AO - Air Traffic Management and Operation
DLR - Research theme (Project):L - Human factors and safety in Aeronautics
Location: Köln-Porz
Institutes and Institutions:Institute of Aerospace Medicine > Sleep and Human Factors Research
Deposited By: Meckes, Elke
Deposited On:05 Jun 2018 13:17
Last Modified:06 Sep 2019 15:20

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.