A comparative study of synchrony measures for the early diagnosis of Alzheimer's disease based on EEG

Abstract

It is well known that EEG signals of Alzheimer's disease (AD) patients are generally less synchronous than in age-matched control subjects. However, this effect is not always easily detectable. This is especially the case for patients in the pre-symptomatic phase, commonly referred to as Mild Cognitive Impairment (MCI), during which neuronal degeneration is occurring prior to the clinical symptoms appearance. In this paper, various synchrony measures are studied in the context of AD diagnosis, including the correlation coefficient, mean-square and phase coherence, Granger causality, phase synchrony indices, information-theoretic divergence measures, state space based measures, and the recently proposed stochastic event synchrony measures. Experiments with EEG data show that many of those measures are strongly correlated (or anti-correlated) with the correlation coefficient, and hence, provide little complementary information about EEG synchrony. Measures that are only weakly correlated with the correlation coefficient include the phase synchrony indices, Granger causality measures, and stochastic-event synchrony measures. In addition, those three families of synchrony measures are mutually uncorrelated, and therefore, they each seem to capture a specific kind of interdependence. For the data set at hand, only two synchrony measures are able to convincingly distinguish AD patients from age-matched control patients, i.e., Granger causality (in particular, full-frequency directed transfer function) and stochastic event synchrony. Those two measures are used as features to distinguish MCI patients from age-matched control subjects, yielding a leave-one-out classification rate of 83%. The classification performance may be further improved by adding complementary features from EEG; this approach may eventually lead to a reliable EEG-based diagnostic tool for MCI and AD.

On the Early Diagnosis of Alzheimer’s Disease from EEG Signals: A Mini-Review

“…The reported results are therefore often prone to overfitting, and they may be overoptimistic. To obtain more reliable classification results, one may for example apply crossvalidation, as has indeed been done in a handful studies (e.g., [10,8,51]). Third, in most existing studies, a single measure to detect EEG abnormalities is applied to a single EEG data set.…”

“…However, few studies systematically investigate large collections of EEG features (e.g., [10,51]); it would be of great interest to apply dimensionality reduction methods to hundreds or even thousands of EEG features, to determine the most discriminative EEG features in a disciplined and statistically rigorous fashion. Moreover, it still needs to be verified whether the effects listed in Sections 2.1 to 2.3 are independent.…”

“…Numerous studies have reported decreased EEG synchrony in MCI and AD patients under resting conditions ("spontaneous EEG")(see, e.g., [19,33,[45][46][47][48][49][50][51][52][53][54][55][56][57][58]). More precisely, the statistical dependence between spontaneous EEG signals recorded from different channels seems to be generally lower in MCI and AD patients than in age-matched control subjects.…”

“…More precisely, the statistical dependence between spontaneous EEG signals recorded from different channels seems to be generally lower in MCI and AD patients than in age-matched control subjects. A large variety of measures have been applied to quantify this loss in statistical dependence, e.g., Pearson correlation coefficient [51], coherence [51,52,54], Granger causality [33,45,51], information-theoretic [58,51] and state space based synchrony measures [19,46,51,55,56], phase synchrony indices [19,51,53,54,57], and stochastic event synchrony [47][48][49][50][51]. In a recent study, the spatial distribution of EEG phase synchrony in AD patients has been investigated [60].…”

Introduction to Focus Issue: Rhythms and Dynamic Transitions in Neurological Disease: Modeling, Computation, and Experiment

“…22,37 In Alzheimer's disease, brain rhythms shift to power at lower frequencies, and the coherence of fast rhythms decreases. 23,38,39 In Parkinson's disease, pathologically exaggerated beta oscillations characterize the abnormal rhythms. 25,[40][41][42][43][44] Transitions between dynamic regimes have been observed during sleep, and abnormal transitions have been associated with sleep disorders.…”