Protocol Design Challenges in the Detection of Awareness in Aware Subjects Using EEG Signals.

Autor:	Henriques J; Laboratoire de Mathématiques de Besançon, Besançon, France.; Cegos Deployment, Besançon, France., Gabriel D; INSERM CIC 1431, Centre d'Investigation Clinique, CHU de Besançon, France.; EA 481 Laboratoire de Neurosciences de Besançon, Besançon, France., Grigoryeva L; Laboratoire de Mathématiques de Besançon, Besançon, France., Haffen E; INSERM CIC 1431, Centre d'Investigation Clinique, CHU de Besançon, France.; EA 481 Laboratoire de Neurosciences de Besançon, Besançon, France.; Service de Psychiatrie de l'adulte, CHU de Besançon, France.; Fondation FondaMental, Créteil, France., Moulin T; INSERM CIC 1431, Centre d'Investigation Clinique, CHU de Besançon, France.; EA 481 Laboratoire de Neurosciences de Besançon, Besançon, France.; Département de Recherche en imagerie fonctionnelle, CHU de Besançon, France.; Service de neurologie, CHU de Besançon, France., Aubry R; INSERM CIC 1431, Centre d'Investigation Clinique, CHU de Besançon, France.; Espace Ethique Bourgogne/Franche-Comté, CHU de Besançon/Dijon, France.; Département douleur soins palliatifs, CHU de Besançon, France., Pazart L; INSERM CIC 1431, Centre d'Investigation Clinique, CHU de Besançon, France., Ortega JP; Laboratoire de Mathématiques de Besançon, Besançon, France juan-pablo.ortega@univ-fcomte.fr.; Centre National de la Recherche Scientifique (CNRS), Besançon, France.
Jazyk:	angličtina
Zdroj:	Clinical EEG and neuroscience [Clin EEG Neurosci] 2016 Oct; Vol. 47 (4), pp. 266-275. Date of Electronic Publication: 2014 Dec 08.
DOI:	10.1177/1550059414560397
Abstrakt:	Recent studies have evidenced serious difficulties in detecting covert awareness with electroencephalography-based techniques both in unresponsive patients and in healthy control subjects. This work reproduces the protocol design in two recent mental imagery studies with a larger group comprising 20 healthy volunteers. The main goal is assessing if modifications in the signal extraction techniques, training-testing/cross-validation routines, and hypotheses evoked in the statistical analysis, can provide solutions to the serious difficulties documented in the literature. The lack of robustness in the results advises for further search of alternative protocols more suitable for machine learning classification and of better performing signal treatment techniques. Specific recommendations are made using the findings in this work. (© EEG and Clinical Neuroscience Society (ECNS) 2014.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu