Multistage classification identifies altered cortical phase- and amplitude-coupling in Multiple Sclerosis
Distinguishing groups of subjects or experimental conditions in a high-dimensional feature space is a common goal in modern neuroimaging studies. Successful classification depends on the selection of relevant features as not every neuronal signal component or parameter is informative about the resea...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811922008734 |
| _version_ | 1811178620493758464 |
|---|---|
| author | Marcus Siems Johannes Tünnerhoff Ulf Ziemann Markus Siegel |
| author_facet | Marcus Siems Johannes Tünnerhoff Ulf Ziemann Markus Siegel |
| author_sort | Marcus Siems |
| collection | DOAJ |
| description | Distinguishing groups of subjects or experimental conditions in a high-dimensional feature space is a common goal in modern neuroimaging studies. Successful classification depends on the selection of relevant features as not every neuronal signal component or parameter is informative about the research question at hand. Here, we developed a novel unsupervised multistage analysis approach that combines dimensionality reduction, bootstrap aggregating and multivariate classification to select relevant neuronal features. We tested the approach by identifying changes of brain-wide electrophysiological coupling in Multiple Sclerosis. Multiple Sclerosis is a demyelinating disease of the central nervous system that can result in cognitive decline and physical disability. However, related changes in large-scale brain interactions remain poorly understood and corresponding non-invasive biomarkers are sparse. We thus compared brain-wide phase- and amplitude-coupling of frequency specific neuronal activity in relapsing-remitting Multiple Sclerosis patients (n = 17) and healthy controls (n = 17) using magnetoencephalography. Changes in this dataset included both, increased and decreased phase- and amplitude-coupling in wide-spread, bilateral neuronal networks across a broad range of frequencies. These changes allowed to successfully classify patients and controls with an accuracy of 84%. Furthermore, classification confidence predicted behavioral scores of disease severity. In sum, our results unravel systematic changes of large-scale phase- and amplitude coupling in Multiple Sclerosis. Furthermore, our results establish a new analysis approach to efficiently contrast high-dimensional neuroimaging data between experimental groups or conditions. |
| first_indexed | 2024-04-11T06:21:40Z |
| format | Article |
| id | doaj.art-3f1e13e6caef4848912c2d442440c002 |
| institution | Directory Open Access Journal |
| issn | 1095-9572 |
| language | English |
| last_indexed | 2024-04-11T06:21:40Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj.art-3f1e13e6caef4848912c2d442440c0022022-12-22T04:40:32ZengElsevierNeuroImage1095-95722022-12-01264119752Multistage classification identifies altered cortical phase- and amplitude-coupling in Multiple SclerosisMarcus Siems0Johannes Tünnerhoff1Ulf Ziemann2Markus Siegel3Department of Neural Dynamics and Magnetoencephalography, Hertie Institute for Clinical Brain Research, University of Tübingen, Germany; Centre for Integrative Neuroscience, University of Tübingen, Germany; MEG Center, University of Tübingen, Germany; Department of Neurophysiology and Pathophysiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany; Correspondence author at: Department of Neural Dynamics and Magnetoencephalography, Hertie Institute for Clinical Brain Research, University of Tübingen, Germany.Department of Neurology & Stroke, Hertie Institute for Clinical Brain Research, University of Tübingen, GermanyDepartment of Neurology & Stroke, Hertie Institute for Clinical Brain Research, University of Tübingen, GermanyDepartment of Neural Dynamics and Magnetoencephalography, Hertie Institute for Clinical Brain Research, University of Tübingen, Germany; Centre for Integrative Neuroscience, University of Tübingen, Germany; MEG Center, University of Tübingen, Germany; Correspondence author at: Department of Neural Dynamics and Magnetoencephalography, Hertie Institute for Clinical Brain Research, University of Tübingen, Germany.Distinguishing groups of subjects or experimental conditions in a high-dimensional feature space is a common goal in modern neuroimaging studies. Successful classification depends on the selection of relevant features as not every neuronal signal component or parameter is informative about the research question at hand. Here, we developed a novel unsupervised multistage analysis approach that combines dimensionality reduction, bootstrap aggregating and multivariate classification to select relevant neuronal features. We tested the approach by identifying changes of brain-wide electrophysiological coupling in Multiple Sclerosis. Multiple Sclerosis is a demyelinating disease of the central nervous system that can result in cognitive decline and physical disability. However, related changes in large-scale brain interactions remain poorly understood and corresponding non-invasive biomarkers are sparse. We thus compared brain-wide phase- and amplitude-coupling of frequency specific neuronal activity in relapsing-remitting Multiple Sclerosis patients (n = 17) and healthy controls (n = 17) using magnetoencephalography. Changes in this dataset included both, increased and decreased phase- and amplitude-coupling in wide-spread, bilateral neuronal networks across a broad range of frequencies. These changes allowed to successfully classify patients and controls with an accuracy of 84%. Furthermore, classification confidence predicted behavioral scores of disease severity. In sum, our results unravel systematic changes of large-scale phase- and amplitude coupling in Multiple Sclerosis. Furthermore, our results establish a new analysis approach to efficiently contrast high-dimensional neuroimaging data between experimental groups or conditions.http://www.sciencedirect.com/science/article/pii/S1053811922008734Multivariate classificationFunctional connectivityNeuronal oscillationsAmplitude-couplingPhase-couplingMEG |
| spellingShingle | Marcus Siems Johannes Tünnerhoff Ulf Ziemann Markus Siegel Multistage classification identifies altered cortical phase- and amplitude-coupling in Multiple Sclerosis NeuroImage Multivariate classification Functional connectivity Neuronal oscillations Amplitude-coupling Phase-coupling MEG |
| title | Multistage classification identifies altered cortical phase- and amplitude-coupling in Multiple Sclerosis |
| title_full | Multistage classification identifies altered cortical phase- and amplitude-coupling in Multiple Sclerosis |
| title_fullStr | Multistage classification identifies altered cortical phase- and amplitude-coupling in Multiple Sclerosis |
| title_full_unstemmed | Multistage classification identifies altered cortical phase- and amplitude-coupling in Multiple Sclerosis |
| title_short | Multistage classification identifies altered cortical phase- and amplitude-coupling in Multiple Sclerosis |
| title_sort | multistage classification identifies altered cortical phase and amplitude coupling in multiple sclerosis |
| topic | Multivariate classification Functional connectivity Neuronal oscillations Amplitude-coupling Phase-coupling MEG |
| url | http://www.sciencedirect.com/science/article/pii/S1053811922008734 |
| work_keys_str_mv | AT marcussiems multistageclassificationidentifiesalteredcorticalphaseandamplitudecouplinginmultiplesclerosis AT johannestunnerhoff multistageclassificationidentifiesalteredcorticalphaseandamplitudecouplinginmultiplesclerosis AT ulfziemann multistageclassificationidentifiesalteredcorticalphaseandamplitudecouplinginmultiplesclerosis AT markussiegel multistageclassificationidentifiesalteredcorticalphaseandamplitudecouplinginmultiplesclerosis |