RESEARCH ARTICLE


EEG Patterns in Mild Cognitive Impairment (MCI) Patients



Mary Baker1, Kwaku Akrofi*, 1, Randolph Schiffer2, Michael W. O’ Boyle3
1 Department of Electrical and Computer Engineering, Texas Tech University, USA
2 Department of Neuropsychiatry, Texas Tech University Health Sciences Center, USA
3 Department of Human Development and Family Studies, Texas Tech University, USA


Article Metrics

CrossRef Citations:
65
Total Statistics:

Full-Text HTML Views: 1154
Abstract HTML Views: 1197
PDF Downloads: 583
Total Views/Downloads: 2934
Unique Statistics:

Full-Text HTML Views: 597
Abstract HTML Views: 747
PDF Downloads: 416
Total Views/Downloads: 1760



Creative Commons License
© Baker et al; Licensee Bentham Open

open-access license: This is an open access article licensed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited.

* Address correspondence to this author at the Department of Electrical and Computer Engineering, Texas Tech University, USA; E-mail: kwaku.akrofi@ttu.edu


Abstract

An emerging clinical priority for the treatment of Alzheimer’s disease (AD) is the implementation of therapies at the earliest stages of disease onset. All AD patients pass through an intermediary stage of the disorder known as Mild Cognitive Impairment (MCI), but not all patients with MCI develop AD. By applying computer based signal processing and pattern recognition techniques to the electroencephalogram (EEG), we were able to classify AD patients versus controls with an accuracy rate of greater than 80%. We were also able to categorize MCI patients into two subgroups: those with EEG Beta power profiles resembling AD patients and those more like controls. We then used this brain-based classification to make predictions regarding those MCI patients most likely to progress to AD versus those who would not. Our classification algorithm correctly predicted the clinical status of 4 out of 6 MCI patients returning for 2 year clinical follow-up. While preliminary in nature, our results suggest that automated pattern recognition techniques applied to the EEG may be a useful clinical tool not only for classification of AD patients versus controls, but also for identifying those MCI patients most likely to progress to AD.