Table of Contents Author Guidelines Submit a Manuscript
Journal of Healthcare Engineering
Volume 6 (2015), Issue 1, Pages 55-70
Research Article

Discrimination of Mild Cognitive Impairment and Alzheimer's Disease Using Transfer Entropy Measures of Scalp EEG

Joseph McBride,1 Xiaopeng Zhao,1 Nancy Munro,2 Gregory Jicha,3,4 Charles Smith,3,4 and Yang Jiang3,5

1Department of Mechanical, Aerospace, and Biomedical Engineering, University of Tennessee, Knoxville, TN, USA
2Oak Ridge Nation Laboratory, Oak Ridge, TN, USA
3Sanders-Brown Center on Aging, University of Kentucky College of Medicine, Lexington, KY, USA
4Department of Neurology, University of Kentucky College of Medicine, Lexington, KY, USA
5Department of Behavioral Science, University of Kentucky College of Medicine, Lexington, KY, USA

Received 1 April 2014; Accepted 1 December 2014

Copyright © 2015 Hindawi Publishing Corporation. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Mild cognitive impairment (MCI) is a neurological condition related to early stages of dementia including Alzheimer's disease (AD). This study investigates the potential of measures of transfer entropy in scalp EEG for effectively discriminating between normal aging, MCI, and AD participants. Resting EEG records from 48 age-matched participants (mean age 75.7 years)—15 normal controls, 16 MCI, and 17 early AD—are examined. The mean temporal delays corresponding to peaks in inter-regional transfer entropy are computed and used as features to discriminate between the three groups of participants. Three-way classification schemes based on binary support vector machine models demonstrate overall discrimination accuracies of 91.7— 93.8%, depending on the protocol condition. These results demonstrate the potential for EEG transfer entropy measures as biomarkers in identifying early MCI and AD. Moreover, the analyses based on short data segments (two minutes) render the method practical for a primary care setting.