Impact of Patient-Specificity on Seizure Onset Detection Performance

Author

Shoeb, A. ; Bourgeois, B. ; Treves, S.T. ; Schachter, S.C. ; Guttag, J.

Author_Institution

Massachusetts Inst. of Technol., Cambridge

fYear

2007

fDate

22-26 Aug. 2007

Firstpage

4110

Lastpage

4114

Abstract

In this paper we quantify the degree to which patient- specificity affects the detection latency, sensitivity, and specificity of a seizure detector using 536 hours of continuously recorded scalp EEG from 16 epilepsy patients. We demonstrate that a detector that knows of an individual´s seizure and non- seizure EEG outperforms a detector limited to knowledge of an individual´s non-seizure EEG, and a detector limited to knowledge of population seizure and non-seizure EEG.

Keywords

diseases; electroencephalography; feature extraction; medical signal processing; support vector machines; epilepsy; feature extraction; patient-specificity; scalp EEG; seizure EEG; seizure onset detection performance; support-vector machine classifier; time 536 hour; unary patient-specific detector; Delay; Detectors; Electroencephalography; Epilepsy; Feature extraction; Hospitals; Nervous system; Pediatrics; Scalp; Testing; EEG; Epilepsy; Seizure Detection; Support-Vector Machines; Adolescent; Child; Child, Preschool; Electroencephalography; Female; Humans; Male; Models, Biological; Predictive Value of Tests; Seizures; Signal Processing, Computer-Assisted; Software;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE

Conference_Location

Lyon

ISSN

1557-170X

Print_ISBN

978-1-4244-0787-3

Type

conf

DOI

10.1109/IEMBS.2007.4353240

Filename

4353240