Channel selection for automatic seizure detection

Highlights ► The current study is an evaluation of different methods for channel selection preceding automatic seizure detection. ► When choosing channels for an automatic seizure detection algorithm, best choice is the three channels with the highest variance during training seizures. ► Using the h...

Full description

Saved in:
Bibliographic Details
Published in:Clinical neurophysiology 2012-01, Vol.123 (1), p.84-92
Main Authors: Duun-Henriksen, Jonas, Kjaer, Troels Wesenberg, Madsen, Rasmus Elsborg, Remvig, Line Sofie, Thomsen, Carsten Eckhart, Sorensen, Helge Bjarup Dissing
Format: Article
Language:English
Subjects:
Algorithms
Automatic seizure detection
Biological and medical sciences
Channel selection
Diagnosis, Computer-Assisted - methods
EEG
Electrodiagnosis. Electric activity recording
Electroencephalography - instrumentation
Electroencephalography - methods
Epilepsy
Epilepsy - diagnosis
Headache. Facial pains. Syncopes. Epilepsia. Intracranial hypertension. Brain oedema. Cerebral palsy
Humans
Investigative techniques, diagnostic techniques (general aspects)
Medical sciences
Nervous system
Nervous system (semeiology, syndromes)
Neurology
Sensitivity and Specificity
Support Vector Machine
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights ► The current study is an evaluation of different methods for channel selection preceding automatic seizure detection. ► When choosing channels for an automatic seizure detection algorithm, best choice is the three channels with the highest variance during training seizures. ► Using the highest variance selection method, the seizure detection performance is similar to when a neurophysiologist chooses the channels he finds best suited.
ISSN:1388-2457
1872-8952
DOI:10.1016/j.clinph.2011.06.001