Component analysis of somatosensory evoked potentials for identifying spinal cord injury location

Abstract This study aims to determine whether the time-frequency components (TFCs) of somatosensory evoked potentials (SEPs) can be used to identify the specific location of a compressive spinal cord injury using a classification technique. Waveforms of SEPs after compressive injuries at various loc...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yazhou Wang, Guangsheng Li, Keith D. K. Luk, Yong Hu
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2017
Materias:
R
Q
Acceso en línea:https://doaj.org/article/9463bc3df4d5486ab4e9ef0da6a8f6a2
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9463bc3df4d5486ab4e9ef0da6a8f6a2
record_format dspace
spelling oai:doaj.org-article:9463bc3df4d5486ab4e9ef0da6a8f6a22021-12-02T16:07:03ZComponent analysis of somatosensory evoked potentials for identifying spinal cord injury location10.1038/s41598-017-02555-w2045-2322https://doaj.org/article/9463bc3df4d5486ab4e9ef0da6a8f6a22017-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-02555-whttps://doaj.org/toc/2045-2322Abstract This study aims to determine whether the time-frequency components (TFCs) of somatosensory evoked potentials (SEPs) can be used to identify the specific location of a compressive spinal cord injury using a classification technique. Waveforms of SEPs after compressive injuries at various locations (C4, C5 and C6) in rat spinal cords were decomposed into a series of TFCs using a high-resolution time-frequency analysis method. A classification method based on support vector machine (SVM) was applied to the distributions of these TFCs among different pathological locations. The difference among injury locations manifests itself in different categories of SEP TFCs. High-energy TFCs of normal-state SEPs have significantly higher power and frequency than those of injury-state SEPs. The location of C5 is characterized by a unique distribution pattern of middle-energy TFCs. The difference between C4 and C6 is evidenced by the distribution pattern of low-energy TFCs. The proposed classification method based on SEP TFCs offers a discrimination accuracy of 80.2%. In this study, meaningful information contained in various SEP components was investigated and used to propose a new application of SEPs for identification of the location of pathological changes in the cervical spinal cord.Yazhou WangGuangsheng LiKeith D. K. LukYong HuNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-12 (2017)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Yazhou Wang
Guangsheng Li
Keith D. K. Luk
Yong Hu
Component analysis of somatosensory evoked potentials for identifying spinal cord injury location
description Abstract This study aims to determine whether the time-frequency components (TFCs) of somatosensory evoked potentials (SEPs) can be used to identify the specific location of a compressive spinal cord injury using a classification technique. Waveforms of SEPs after compressive injuries at various locations (C4, C5 and C6) in rat spinal cords were decomposed into a series of TFCs using a high-resolution time-frequency analysis method. A classification method based on support vector machine (SVM) was applied to the distributions of these TFCs among different pathological locations. The difference among injury locations manifests itself in different categories of SEP TFCs. High-energy TFCs of normal-state SEPs have significantly higher power and frequency than those of injury-state SEPs. The location of C5 is characterized by a unique distribution pattern of middle-energy TFCs. The difference between C4 and C6 is evidenced by the distribution pattern of low-energy TFCs. The proposed classification method based on SEP TFCs offers a discrimination accuracy of 80.2%. In this study, meaningful information contained in various SEP components was investigated and used to propose a new application of SEPs for identification of the location of pathological changes in the cervical spinal cord.
format article
author Yazhou Wang
Guangsheng Li
Keith D. K. Luk
Yong Hu
author_facet Yazhou Wang
Guangsheng Li
Keith D. K. Luk
Yong Hu
author_sort Yazhou Wang
title Component analysis of somatosensory evoked potentials for identifying spinal cord injury location
title_short Component analysis of somatosensory evoked potentials for identifying spinal cord injury location
title_full Component analysis of somatosensory evoked potentials for identifying spinal cord injury location
title_fullStr Component analysis of somatosensory evoked potentials for identifying spinal cord injury location
title_full_unstemmed Component analysis of somatosensory evoked potentials for identifying spinal cord injury location
title_sort component analysis of somatosensory evoked potentials for identifying spinal cord injury location
publisher Nature Portfolio
publishDate 2017
url https://doaj.org/article/9463bc3df4d5486ab4e9ef0da6a8f6a2
work_keys_str_mv AT yazhouwang componentanalysisofsomatosensoryevokedpotentialsforidentifyingspinalcordinjurylocation
AT guangshengli componentanalysisofsomatosensoryevokedpotentialsforidentifyingspinalcordinjurylocation
AT keithdkluk componentanalysisofsomatosensoryevokedpotentialsforidentifyingspinalcordinjurylocation
AT yonghu componentanalysisofsomatosensoryevokedpotentialsforidentifyingspinalcordinjurylocation
_version_ 1718384791023255552