Automatic EEG spike detection: What should the computer look for?

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Epileptiform spikes marked by eight electroencephalogram (EEG) readers are compared with a computer-based spike detector for 12 EEG files. The observed variability between readers shows that 18% of all marked spikes were marked by all readers and 38% were marked by only one reader. For all possible pairs of EEG readers the average number of spikes marked by one reader that were also marked by another was 52%. These findings suggest that a priori decisions should be made regarding criteria for spikes, e.g., definite spikes marked by many human readers versus possible spikes marked only by a few readers. Automatic spike detectors may approach practical useful screening sensitivities and selectivities based upon the required accuracy.

Original languageEnglish (US)
Title of host publicationProceedings of the Annual Conference on Engineering in Medicine and Biology
PublisherPubl by IEEE
Pages1195-1196
Number of pages2
Editionpt 3
ISBN (Print)0780302168
StatePublished - Dec 1 1991
Externally publishedYes
EventProceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Orlando, FL, USA
Duration: Oct 31 1991Nov 3 1991

Publication series

NameProceedings of the Annual Conference on Engineering in Medicine and Biology
Numberpt 3
Volume13
ISSN (Print)0589-1019

Other

OtherProceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
CityOrlando, FL, USA
Period10/31/9111/3/91

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint Dive into the research topics of 'Automatic EEG spike detection: What should the computer look for?'. Together they form a unique fingerprint.

Cite this