DocumentCode :
3321071
Title :
Forewarning of epileptic events from scalp EEG
Author :
Hively, Lee M. ; McDonald, J. Todd ; Munro, N. ; Cornelius, Emily
Author_Institution :
Comput. Sci. & Eng. Div., Oak Ridge Nat. Lab., Oak Ridge, TN, USA
fYear :
2013
fDate :
21-23 May 2013
Firstpage :
1
Lastpage :
4
Abstract :
This paper addresses epileptic event forewarning. One novel contribution is the use of graph theoretic measures to detect condition change from time-delay-embedding states. Another novel contribution is better forewarning of the epileptic events from two channels of scalp EEG, with a total true rate of 58/60 (sensitivity = 39/40, specificity = 19/20). Challenges include statistical validation in terms of true positives and true negatives; actionable forewarning in terms of time before the event; detection of the event to reset the forewarning algorithm; and implementation in a practical device.
Keywords :
electroencephalography; graph theory; medical disorders; medical signal processing; statistical analysis; epileptic event forewarning; graph theoretic measures; scalp EEG; statistical validation; time-delay-embedding states; true negatives; true positives; Electroencephalography; Epilepsy; Laboratories; Reliability; Scalp; Training; epilepsy; forewarning; scalp EEG;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Sciences and Engineering Conference (BSEC), 2013
Conference_Location :
Oak Ridge, TN
Print_ISBN :
978-1-4799-2118-8
Type :
conf
DOI :
10.1109/BSEC.2013.6618498
Filename :
6618498
Link To Document :
بازگشت