Recognizing mild cognitive impairment based on network connectivity analysis of resting EEG with zero reference.
Physiol Meas
; 35(7): 1279-98, 2014 Jul.
Article
en En
| MEDLINE
| ID: mdl-24853724
The diagnosis of mild cognitive impairment (MCI) is very helpful for early therapeutic interventions of Alzheimer's disease (AD). MCI has been proven to be correlated with disorders in multiple brain areas. In this paper, we used information from resting brain networks at different EEG frequency bands to reliably recognize MCI. Because EEG network analysis is influenced by the reference that is used, we also evaluate the effect of the reference choices on the resting scalp EEG network-based MCI differentiation. The conducted study reveals two aspects: (1) the network-based MCI differentiation is superior to the previously reported classification that uses coherence in the EEG; and (2) the used EEG reference influences the differentiation performance, and the zero approximation technique (reference electrode standardization technique, REST) can construct a more accurate scalp EEG network, which results in a higher differentiation accuracy for MCI. This study indicates that the resting scalp EEG-based network analysis could be valuable for MCI recognition in the future.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Procesamiento de Señales Asistido por Computador
/
Encéfalo
/
Electroencefalografía
/
Disfunción Cognitiva
Tipo de estudio:
Prognostic_studies
Límite:
Aged
/
Female
/
Humans
/
Male
Idioma:
En
Revista:
Physiol Meas
Asunto de la revista:
BIOFISICA
/
ENGENHARIA BIOMEDICA
/
FISIOLOGIA
Año:
2014
Tipo del documento:
Article
Pais de publicación:
Reino Unido