Improving the detection of sleep slow oscillations in electroencephalographic data
Study objectivesWe aimed to build a tool which facilitates manual labeling of sleep slow oscillations (SOs) and evaluate the performance of traditional sleep SO detection algorithms on such a manually labeled data set. We sought to develop improved methods for SO detection.MethodSOs in polysomnograp...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2024-02-01
|
Series: | Frontiers in Neuroinformatics |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fninf.2024.1338886/full |
_version_ | 1797324337863196672 |
---|---|
author | Cristiana Dimulescu Cristiana Dimulescu Leonhard Donle Caglar Cakan Caglar Cakan Thomas Goerttler Lilia Khakimova Julia Ladenbauer Agnes Flöel Agnes Flöel Klaus Obermayer Klaus Obermayer |
author_facet | Cristiana Dimulescu Cristiana Dimulescu Leonhard Donle Caglar Cakan Caglar Cakan Thomas Goerttler Lilia Khakimova Julia Ladenbauer Agnes Flöel Agnes Flöel Klaus Obermayer Klaus Obermayer |
author_sort | Cristiana Dimulescu |
collection | DOAJ |
description | Study objectivesWe aimed to build a tool which facilitates manual labeling of sleep slow oscillations (SOs) and evaluate the performance of traditional sleep SO detection algorithms on such a manually labeled data set. We sought to develop improved methods for SO detection.MethodSOs in polysomnographic recordings acquired during nap time from ten older adults were manually labeled using a custom built graphical user interface tool. Three automatic SO detection algorithms previously used in the literature were evaluated on this data set. Additional machine learning and deep learning algorithms were trained on the manually labeled data set.ResultsOur custom built tool significantly decreased the time needed for manual labeling, allowing us to manually inspect 96,277 potential SO events. The three automatic SO detection algorithms showed relatively low accuracy (max. 61.08%), but results were qualitatively similar, with SO density and amplitude increasing with sleep depth. The machine learning and deep learning algorithms showed higher accuracy (best: 99.20%) while maintaining a low prediction time.ConclusionsAccurate detection of SO events is important for investigating their role in memory consolidation. In this context, our tool and proposed methods can provide significant help in identifying these events. |
first_indexed | 2024-03-08T05:54:41Z |
format | Article |
id | doaj.art-691080a8a33e46fc9199bf29d98e246d |
institution | Directory Open Access Journal |
issn | 1662-5196 |
language | English |
last_indexed | 2024-03-08T05:54:41Z |
publishDate | 2024-02-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Neuroinformatics |
spelling | doaj.art-691080a8a33e46fc9199bf29d98e246d2024-02-05T04:34:45ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962024-02-011810.3389/fninf.2024.13388861338886Improving the detection of sleep slow oscillations in electroencephalographic dataCristiana Dimulescu0Cristiana Dimulescu1Leonhard Donle2Caglar Cakan3Caglar Cakan4Thomas Goerttler5Lilia Khakimova6Julia Ladenbauer7Agnes Flöel8Agnes Flöel9Klaus Obermayer10Klaus Obermayer11Department of Software Engineering and Theoretical Computer Science, Technical University Berlin, Berlin, GermanyBernstein Center for Computational Neuroscience Berlin, Berlin, GermanyDepartment of Software Engineering and Theoretical Computer Science, Technical University Berlin, Berlin, GermanyDepartment of Software Engineering and Theoretical Computer Science, Technical University Berlin, Berlin, GermanyBernstein Center for Computational Neuroscience Berlin, Berlin, GermanyDepartment of Software Engineering and Theoretical Computer Science, Technical University Berlin, Berlin, GermanyDepartment of Neurology, University Medicine, Greifswald, GermanyDepartment of Neurology, University Medicine, Greifswald, GermanyDepartment of Neurology, University Medicine, Greifswald, GermanyGerman Center for Neurodegenerative Diseases, Greifswald, GermanyDepartment of Software Engineering and Theoretical Computer Science, Technical University Berlin, Berlin, GermanyBernstein Center for Computational Neuroscience Berlin, Berlin, GermanyStudy objectivesWe aimed to build a tool which facilitates manual labeling of sleep slow oscillations (SOs) and evaluate the performance of traditional sleep SO detection algorithms on such a manually labeled data set. We sought to develop improved methods for SO detection.MethodSOs in polysomnographic recordings acquired during nap time from ten older adults were manually labeled using a custom built graphical user interface tool. Three automatic SO detection algorithms previously used in the literature were evaluated on this data set. Additional machine learning and deep learning algorithms were trained on the manually labeled data set.ResultsOur custom built tool significantly decreased the time needed for manual labeling, allowing us to manually inspect 96,277 potential SO events. The three automatic SO detection algorithms showed relatively low accuracy (max. 61.08%), but results were qualitatively similar, with SO density and amplitude increasing with sleep depth. The machine learning and deep learning algorithms showed higher accuracy (best: 99.20%) while maintaining a low prediction time.ConclusionsAccurate detection of SO events is important for investigating their role in memory consolidation. In this context, our tool and proposed methods can provide significant help in identifying these events.https://www.frontiersin.org/articles/10.3389/fninf.2024.1338886/fullelectroencephalographysleepslow oscillationsevent detectiondeep learning |
spellingShingle | Cristiana Dimulescu Cristiana Dimulescu Leonhard Donle Caglar Cakan Caglar Cakan Thomas Goerttler Lilia Khakimova Julia Ladenbauer Agnes Flöel Agnes Flöel Klaus Obermayer Klaus Obermayer Improving the detection of sleep slow oscillations in electroencephalographic data Frontiers in Neuroinformatics electroencephalography sleep slow oscillations event detection deep learning |
title | Improving the detection of sleep slow oscillations in electroencephalographic data |
title_full | Improving the detection of sleep slow oscillations in electroencephalographic data |
title_fullStr | Improving the detection of sleep slow oscillations in electroencephalographic data |
title_full_unstemmed | Improving the detection of sleep slow oscillations in electroencephalographic data |
title_short | Improving the detection of sleep slow oscillations in electroencephalographic data |
title_sort | improving the detection of sleep slow oscillations in electroencephalographic data |
topic | electroencephalography sleep slow oscillations event detection deep learning |
url | https://www.frontiersin.org/articles/10.3389/fninf.2024.1338886/full |
work_keys_str_mv | AT cristianadimulescu improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata AT cristianadimulescu improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata AT leonharddonle improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata AT caglarcakan improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata AT caglarcakan improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata AT thomasgoerttler improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata AT liliakhakimova improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata AT julialadenbauer improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata AT agnesfloel improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata AT agnesfloel improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata AT klausobermayer improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata AT klausobermayer improvingthedetectionofsleepslowoscillationsinelectroencephalographicdata |