Extracting Robust Biomarkers From Multichannel EEG Time Series Using Nonlinear Dimensionality Reduction Applied to Ordinal Pattern Statistics and Spectral Quantities
In this study, ordinal pattern analysis and classical frequency-based EEG analysis methods are used to differentiate between EEGs of different age groups as well as individuals. As characteristic features, functional connectivity as well as single-channel measures in both the time and frequency doma...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-02-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2020.614565/full |
| id |
doaj-c54a25756d8c4f7b9db0435265318854 |
|---|---|
| record_format |
Article |
| spelling |
doaj-c54a25756d8c4f7b9db04352653188542021-02-01T04:59:52ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2021-02-011110.3389/fphys.2020.614565614565Extracting Robust Biomarkers From Multichannel EEG Time Series Using Nonlinear Dimensionality Reduction Applied to Ordinal Pattern Statistics and Spectral QuantitiesInga Kottlarz0Inga Kottlarz1Sebastian Berg2Diana Toscano-Tejeida3Iris Steinmann4Mathias Bähr5Stefan Luther6Stefan Luther7Stefan Luther8Melanie Wilke9Melanie Wilke10Ulrich Parlitz11Ulrich Parlitz12Ulrich Parlitz13Alexander Schlemmer14Alexander Schlemmer15Max Planck Institute for Dynamics and Self-Organization, Göttingen, GermanyInstitute for the Dynamics of Complex Systems, Georg-August-Universität Göttingen, Göttingen, GermanyMax Planck Institute for Dynamics and Self-Organization, Göttingen, GermanyDepartment of Cognitive Neurology, University Medical Center Göttingen, Göttingen, GermanyDepartment of Cognitive Neurology, University Medical Center Göttingen, Göttingen, GermanyDepartment of Neurology, University Medical Center Göttingen, Göttingen, GermanyMax Planck Institute for Dynamics and Self-Organization, Göttingen, GermanyInstitute of Pharmacology and Toxicology, University Medical Center Göttingen, Göttingen, GermanyGerman Center for Cardiovascular Research (DZHK), Partner Site Göttingen, Göttingen, GermanyDepartment of Cognitive Neurology, University Medical Center Göttingen, Göttingen, GermanyGerman Primate Center, Leibniz Institute for Primate Research, Göttingen, GermanyMax Planck Institute for Dynamics and Self-Organization, Göttingen, GermanyInstitute for the Dynamics of Complex Systems, Georg-August-Universität Göttingen, Göttingen, GermanyGerman Center for Cardiovascular Research (DZHK), Partner Site Göttingen, Göttingen, GermanyMax Planck Institute for Dynamics and Self-Organization, Göttingen, GermanyGerman Center for Cardiovascular Research (DZHK), Partner Site Göttingen, Göttingen, GermanyIn this study, ordinal pattern analysis and classical frequency-based EEG analysis methods are used to differentiate between EEGs of different age groups as well as individuals. As characteristic features, functional connectivity as well as single-channel measures in both the time and frequency domain are considered. We compare the separation power of each feature set after nonlinear dimensionality reduction using t-distributed stochastic neighbor embedding and demonstrate that ordinal pattern-based measures yield results comparable to frequency-based measures applied to preprocessed data, and outperform them if applied to raw data. Our analysis yields no significant differences in performance between single-channel features and functional connectivity features regarding the question of age group separation.https://www.frontiersin.org/articles/10.3389/fphys.2020.614565/fullEEG - Electroencephalogramt-SNE (t-distributed stochastic neighbor embedding)ordinal pattern statisticsnonlinear dimensionality reductionbiomarkersfunctional connectivity |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Inga Kottlarz Inga Kottlarz Sebastian Berg Diana Toscano-Tejeida Iris Steinmann Mathias Bähr Stefan Luther Stefan Luther Stefan Luther Melanie Wilke Melanie Wilke Ulrich Parlitz Ulrich Parlitz Ulrich Parlitz Alexander Schlemmer Alexander Schlemmer |
| spellingShingle |
Inga Kottlarz Inga Kottlarz Sebastian Berg Diana Toscano-Tejeida Iris Steinmann Mathias Bähr Stefan Luther Stefan Luther Stefan Luther Melanie Wilke Melanie Wilke Ulrich Parlitz Ulrich Parlitz Ulrich Parlitz Alexander Schlemmer Alexander Schlemmer Extracting Robust Biomarkers From Multichannel EEG Time Series Using Nonlinear Dimensionality Reduction Applied to Ordinal Pattern Statistics and Spectral Quantities Frontiers in Physiology EEG - Electroencephalogram t-SNE (t-distributed stochastic neighbor embedding) ordinal pattern statistics nonlinear dimensionality reduction biomarkers functional connectivity |
| author_facet |
Inga Kottlarz Inga Kottlarz Sebastian Berg Diana Toscano-Tejeida Iris Steinmann Mathias Bähr Stefan Luther Stefan Luther Stefan Luther Melanie Wilke Melanie Wilke Ulrich Parlitz Ulrich Parlitz Ulrich Parlitz Alexander Schlemmer Alexander Schlemmer |
| author_sort |
Inga Kottlarz |
| title |
Extracting Robust Biomarkers From Multichannel EEG Time Series Using Nonlinear Dimensionality Reduction Applied to Ordinal Pattern Statistics and Spectral Quantities |
| title_short |
Extracting Robust Biomarkers From Multichannel EEG Time Series Using Nonlinear Dimensionality Reduction Applied to Ordinal Pattern Statistics and Spectral Quantities |
| title_full |
Extracting Robust Biomarkers From Multichannel EEG Time Series Using Nonlinear Dimensionality Reduction Applied to Ordinal Pattern Statistics and Spectral Quantities |
| title_fullStr |
Extracting Robust Biomarkers From Multichannel EEG Time Series Using Nonlinear Dimensionality Reduction Applied to Ordinal Pattern Statistics and Spectral Quantities |
| title_full_unstemmed |
Extracting Robust Biomarkers From Multichannel EEG Time Series Using Nonlinear Dimensionality Reduction Applied to Ordinal Pattern Statistics and Spectral Quantities |
| title_sort |
extracting robust biomarkers from multichannel eeg time series using nonlinear dimensionality reduction applied to ordinal pattern statistics and spectral quantities |
| publisher |
Frontiers Media S.A. |
| series |
Frontiers in Physiology |
| issn |
1664-042X |
| publishDate |
2021-02-01 |
| description |
In this study, ordinal pattern analysis and classical frequency-based EEG analysis methods are used to differentiate between EEGs of different age groups as well as individuals. As characteristic features, functional connectivity as well as single-channel measures in both the time and frequency domain are considered. We compare the separation power of each feature set after nonlinear dimensionality reduction using t-distributed stochastic neighbor embedding and demonstrate that ordinal pattern-based measures yield results comparable to frequency-based measures applied to preprocessed data, and outperform them if applied to raw data. Our analysis yields no significant differences in performance between single-channel features and functional connectivity features regarding the question of age group separation. |
| topic |
EEG - Electroencephalogram t-SNE (t-distributed stochastic neighbor embedding) ordinal pattern statistics nonlinear dimensionality reduction biomarkers functional connectivity |
| url |
https://www.frontiersin.org/articles/10.3389/fphys.2020.614565/full |
| work_keys_str_mv |
AT ingakottlarz extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT ingakottlarz extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT sebastianberg extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT dianatoscanotejeida extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT irissteinmann extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT mathiasbahr extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT stefanluther extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT stefanluther extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT stefanluther extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT melaniewilke extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT melaniewilke extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT ulrichparlitz extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT ulrichparlitz extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT ulrichparlitz extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT alexanderschlemmer extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities AT alexanderschlemmer extractingrobustbiomarkersfrommultichanneleegtimeseriesusingnonlineardimensionalityreductionappliedtoordinalpatternstatisticsandspectralquantities |
| _version_ |
1724315796624113664 |