Recent works showed that meaningful dominant components can be extracted from the EEG of patients in coma through an algorithm based on the joint use of Principal Component Analysis (PCA) and Independent Component Analysis (ICA). A procedure for automatic critical epoch detection would support the doctor in the long time monitoring of the patients, thus we investigated the automatic quantification of the criticality of the epochs. In this paper we propose a procedure based on the extraction of dominant components and features for the quantification of the critical state of each epoch, in particular we use entropy and kurtosis. This feature analysis allowed us to detect some epochs that are likely to be critical and that are worth being carefully inspected electrographically by the expert.

Analysis of the automatic detection of critical epochs from coma-EEG by dominant components and features extraction

F. La Foresta;;F. Morabito
2006

Abstract

Recent works showed that meaningful dominant components can be extracted from the EEG of patients in coma through an algorithm based on the joint use of Principal Component Analysis (PCA) and Independent Component Analysis (ICA). A procedure for automatic critical epoch detection would support the doctor in the long time monitoring of the patients, thus we investigated the automatic quantification of the criticality of the epochs. In this paper we propose a procedure based on the extraction of dominant components and features for the quantification of the critical state of each epoch, in particular we use entropy and kurtosis. This feature analysis allowed us to detect some epochs that are likely to be critical and that are worth being carefully inspected electrographically by the expert.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/20.500.12318/11256
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact