Detecting neurophysiological alterations during Mild Cognitive Impairment and 
Dementia using wavelet-based energy computation and a Mahalanobis Distance 
classifier

Frantzidis, Christos; Semertzidou, Anastasia; Ladas, Aristea; Karagianni, Maria; Lithari, Chrysa; Kyrillidou, Athina; Grigoriadou, Eirini; Klados, Manousos; Vivas, Ana; Kounti, Fotini; Tsolaki, Magda; Pappas, Costas; Bamidis, Panagiotis

doi:10.1016/j.neulet.2011.05.225

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Conference Paper

Detecting neurophysiological alterations during Mild Cognitive Impairment and Dementia using wavelet-based energy computation and a Mahalanobis Distance classifier

MPS-Authors

There are no MPG-Authors in the publication available

External Resource

No external resources are shared

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Frantzidis, C., Semertzidou, A., Ladas, A., Karagianni, M., Lithari, C., Kyrillidou, A., et al. (2011). Detecting neurophysiological alterations during Mild Cognitive Impairment and Dementia using wavelet-based energy computation and a Mahalanobis Distance classifier. Neuroscience Letters, 500(Suppl.), e53-e53. doi:10.1016/j.neulet.2011.05.225.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0025-02EB-6

Abstract

Recently, a transitional stage, called Mild Cognitive Impairment (MCI) has been identified. Early MCI detection is of crucial importance for preventing dementia onset. The aim of this study is to provide a classification framework able to discriminate subtle alterations due to neurodegenerative processes. Primary attention was given at the MCI stage. Therefore two MCI groups were formed according the patient's performance in the Montreal Cognitive Assessment (MoCA) test; a group of 39 patient with a low cognitive decline (MCI-1; MoCA ≥ 25), and a group of 31 patients with moderate cognitive decline group (MCI-2; MoCA < 25). In addition, we tested 17 healthy control participants, and 14 mild demented patients. Participants underwent a full neuropsychologic examination. Application of the Independent Component Analysis (ICA) and visual inspection of EEG data during resting state condition with eyes closed was initially adopted for noise rejection. Then, the energy for each frequency band was computed through discrete wavelet transform (DWT). These spectral components for 57 electrodes served as an input to a classification system employing Mahalanobis Distance. Classification results (84.16% overall accuracy) demonstrated the system's robustness and reliability. Discrimination reached 82.35% for healthy controls, 92.31% for MCI-1, 74.19% for MCI-2 and 85.71% for mild demented patients. The classification system is proposed in order to supplement the neuropsychologic examination and to correlate subtle cognitive deficits revealed by MoCA with modified neurophysiological patterns, providing thus a better understanding to the progression of neurodegenerative mechanisms.