Imperial College London
Alternate

Dr Syed Anas Imtiaz

Faculty of Engineering, Department of Electrical and Electronic Engineering

Research Fellow
 
 
 
//

Contact

 

+44 (0)20 7594 6297anas.imtiaz Website

 
 
//

Location

 

907Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Kok:2021:10.1109/EMBC46164.2021.9630782,
author = {Kok, XH and Imtiaz, SA and Rodriguez, Villegas E},
doi = {10.1109/EMBC46164.2021.9630782},
pages = {273--276},
publisher = {IEEE},
title = {Towards automatic identification of epileptic recordings in long-term EEG monitoring},
url = {http://dx.doi.org/10.1109/EMBC46164.2021.9630782},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Electroencephalogram  (EEG)  is  a  crucial  tool  inthe  diagnosis  and  management  of  epilepsy.  The  process  ofanalyzing  EEG  is  time  consuming  leading  to  the  developmentof  seizure  detection  algorithms  to  aid  its  analysis.  This  ap-proach  is  limited  since  it  requires  seizures  to  occur  duringmonitoring periods and can often lead to misdiagnosis in caseswhere  seizure  occurrence  is  rare.  For  such  cases,  it  has  beenshown  that  the  interictal  periods  in  EEG  signals,  which  is  thepredominant  state  in  long-term  monitoring,  can  be  useful  forthe  diagnosis  of  epilepsy.  This  paper  presents  an  algorithm,using  the  information  in  interictal  periods,  to  discriminatebetween  long-term  EEG  recordings  of  epilepsy  patients  andhealthy  subjects.  It  extracts  several  time  and  frequency-timedomain  features  from  the  signals  and  classifies  them  usingan  ensemble  classifier,  achieving  100%  sensitivity  and  98.7%specificity in classifying 267 recordings from 105 subjects. Theresults  demonstrate  the  feasibility  of  this  approach  to  reliablyidentify   EEG   recordings   of   epilepsy   subjects   automaticallywhich can be highly useful to facilitate screening and diagnosisof  epilepsy,  especially  in  those  parts  of  the  world  where  thereis  a  lack  of  trained  personnel  for  interpreting  EEG  signals.
AU  - Kok,XH
AU  - Imtiaz,SA
AU  - Rodriguez,Villegas E
DO  - 10.1109/EMBC46164.2021.9630782
EP  - 276
PB  - IEEE
PY  - 2021///
SP  - 273
TI  - Towards automatic identification of epileptic recordings in long-term EEG monitoring
UR  - http://dx.doi.org/10.1109/EMBC46164.2021.9630782
UR  - https://ieeexplore.ieee.org/document/9630782
UR  - http://hdl.handle.net/10044/1/90864
ER  -
Download