Feature extraction from the EEG of comatose patients by global adaptive segmentation.
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00023752%3A_____%2F99%3A00000016" target="_blank" >RIV/00023752:_____/99:00000016 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Feature extraction from the EEG of comatose patients by global adaptive segmentation.
Original language description
The objective of this study was to prepare a set of robust EEG indicators for automatic assessment of coma scales. There exists a correlation between the EEG indicators and the clinical scores in the comatose patients. One of the possible approaches to pattern recognition is the application of learning classifier. During the learning phase of the classifier tuning, the teacher provides the set of etalons, extracted from the signal, and labels them visually according to the coma depth. Such epochs can serve as the prototypes of the appropriate class. Tests showed, that the indicators of the consciousness level, such as the burst-suppression pattern, could be correctly defined. It is expected that the use of global adaptive segmentation is suitable for automatic feature extraction in coma and deep narcosis.
Czech name
—
Czech description
—
Classification
Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
FH - Neurology, neuro-surgery, nuero-sciences
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/NG14" target="_blank" >NG14: Neurophysiological indicators with respect to the vigilance level in dementia.</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
1999
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Neuroimage
ISSN
1053-8119
e-ISSN
—
Volume of the periodical
10
Issue of the periodical within the volume
1
Country of publishing house
US - UNITED STATES
Number of pages
1
Pages from-to
—
UT code for WoS article
—
EID of the result in the Scopus database
—