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.

Brain network analysis for the discrimination of dementia disorders using electrophysiology signals: A systematic review

“…• Node betweenness centrality (NBC): The betweenness of a node is the number of shortest paths passing through a node in a graph. It is a pointer to the influence a node has on the information flow in a graph/network (Jalili, 2016;Abazid et al, 2021). • Node strength (NS): Node strength measures the node's contribution to the entire network by taking the sum of the weights of the link and joining it to the adjacent nodes (Hata et al, 2016;Duan et al, 2020).…”

Wireless electroencephalogram monitoring system for deciphering neurological disorders using brain connectivity patterns

“…Classification based on complex network topology to differentiate different types of dementia like MCI (Babiloni et al, 2004), AD (Afshari & Jalili, 2017), dementia with Lewy bodies (DLB) (van Dellen et al, 2015) and vascular dementia (VD) (Babiloni et al, 2004; Vecchio et al, 2021) are potential areas of research but not widely investigated. Support Vector Machine (SVM) algorithm with features of statistical entropy has been efficiently used for classification of subjective cognitive impairment (SCI) patients, MCI patients, and AD (Abazid et al, 2021). Further, a recent study demonstrated a fully automatic procedure based on machine learning to discriminate MCI and AD subjects (Ding et al, 2022).…”

“…So far limited studies were published in classification of neurological disorder using EEG signals in ensemble CNN or with other deep learning approaches. Among them classification algorithm using features derived from functional connectivity data has found success in deciphering the neurological disorder (Abazid et al, 2021; Alotaibi & Maharatna, 2021; Ding et al, 2022; Kinney‐Lang et al, 2019; van Diessen et al, 2013; Wadhera & Kakkar, 2020; Wang et al, 2022). Another major limitation for the realization of wireless EEG monitoring system would be the lack of technology infrastructure that can enable smooth transmission of data and services.…”

Weighted Brain Network Analysis on Different Stages of Clinical Cognitive Decline

“…We show that this new framework allows conducting a refined brain network analysis, which highly contributes to a better understanding of the evolution of AD from SCI to dementia through the MCI stage. In a more recent study [ 76 ], we combined EpEn to graph theory but considered binary network analysis to discriminate automatically between SCI, MCI and AD patients (a classification problem). By contrast, the present work investigates the brain network topology over the three stages in order to retrieve global patterns that characterize the evolution towards dementia.…”