A Comparative Study of Functional Connectivity Measures for Brain Network Analysis in the Context of AD Detection with EEG

Abstract

This work addresses brain network analysis considering different clinical severity stages of cognitive dysfunction, based on resting-state electroencephalography (EEG). We use a cohort acquired in real-life clinical conditions, which contains EEG data of subjective cognitive impairment (SCI) patients, mild cognitive impairment (MCI) patients, and Alzheimer's disease (AD) patients. We propose to exploit an epoch-based entropy measure to quantify the connectivity links in the networks. This entropy measure relies on a refined statistical modeling of EEG signals with Hidden Markov Models, which allow a better estimation of the spatiotemporal characteristics of EEG signals. We also propose to conduct a comparative study by considering three other measures largely used in the literature: phase lag index, coherence, and mutual information. We calculated such measures at different frequency bands and computed different local graph parameters considering different proportional threshold values for a binary network analysis. After applying a feature selection procedure to determine the most relevant features for classification performance with a linear Support Vector Machine algorithm, our study demonstrates the effectiveness of the statistical entropy measure for analyzing the brain network in patients with different stages of cognitive dysfunction.

Keywords: AD detection; EEG signals; brain network; coherence; epoch-based entropy; graph theory; mild cognitive impairment; mutual information; phase lag index; subjective cognitive impairment.

Figure 1

Position of the 30 electrodes used for EEG recording (marked in color).

Figure 2

HMM modeling of an EEG signal with N states.

Figure 3

Illustration of multichannel (D = 2, N = 6) EEG signal modeling with HMM.

Figure 4

The global ranking of the four connectivity measures in terms of accuracy considering all the graph parameters and class comparisons together.

Figure 5

The average SVM posterior probability that one person is classified into the positive class for the four connectivity measure and the five graph parameters, when comparing: (a) SCI vs. AD, (b) SCI vs. MCI and (c) AD vs. MCI.