Context related artefact detection in prolonged EEG recordings

The need for reliable detection of artefacts in raw and processed EEG is wi dely acknowledged. Although different EEG analysis systems have been descri bed, only few general applicable artefact recognition techniques have emerg ed. This paper tackles the problem of artefact detection in seven 24 h EEG recordings in the intensive care unit. ICU recordings have received less at tention than, e.g, epilepsy monitoring, although recordings in this environ ment present an interesting application area. The EEG data used here was re corded during the difficult circumstances of an explorative ICU study. The data set includes a diverse set of EEG patterns, as well as EEG artefacts. The study investigates objective artefact detection methods based on statis tical differences between signal parameters, using time-varying autoregress ive modelling (AR) and Slope detection. In addition to matching the perform ance of artefact detection against two human observers, the study focuses o n the optimal settings for context incorporation by testing the algorithms for different time windows and epoch lengths. Results indicate that a relat ively short period (20-40 s) provides sufficient context information for th e methods used. The combined AR and Slope detection parameters yielded good performance, detecting approximately 90% of the artefacts as indicated by the consensus score of the human observers. (C) 1999 Elsevier Science Irela nd Ltd. All rights reserved.