Characterization of EEGs in Alzheimer's Disease using Information Theoretic Methods

Abstract

The number of people that now go on to develop Alzheimer's disease (AD) and other types of dementia is rapidly rising. For maximum benefits from new treatments, the disease should be diagnosed as early as possible, but this is difficult with current clinical criteria. Potentially, the EEG can serve as an objective, first line of decision support tool to improve diagnosis. It is non-invasive, widely available, low-cost and could be carried out rapidly in the high-risk age group that will develop AD. Changes in the EEG due to the dementing process could be quantified as an index or marker. In this paper, we investigate two information theoretic methods (Tsallis entropy and universal compression algorithm) as a way to generate potentially robust markers from the EEG. The hypothesis is that the information theoretic makers for AD are significantly different to those of normal subjects. An attraction of the information theoretic approach is that, unlike most existing methods, there may be a natural link between the underlying ideas of information theoretic methods, the physiology of AD and its impact on brain functions. Data compression has not been investigated as a means of generating EEG markers before and is attractive because it does not require a priori knowledge of the source model. In this paper, we focus on the LZW algorithm because of its sound theoretical foundation. We used the LZW algorithm and Tsallis model to compute the markers (compression ratios and normalized entropies, respectively) from two EEG datasets.

Diagnosis of Alzheimers Disease from EEG Signals: Where Are We Standing?

“…As pointed out earlier, several studies have investigated whether the complexity of EEG signals is perturbed by MCI or AD [77,82,87,88,89,90,91,92,93,94,95]. The following measures have been applied in this context: approximate entropy [87,88,89,90], sample entropy [87,94], Tsallis entropy [82], multiscale entropy [87,95], auto-mutual information [77,87,88], Lempel-Ziv complexity [87], universal compression [82], fractal dimension [91], correlation dimension [92,93], and largest Lyapunov exponent [93].…”

“…The parameter q is a measure of the non-extensitivity of the system of interest: the Tsallis entropy of two independent systems is in general not equal to the sum of the Tsallis entropies of those systems; only when q = 1 the Tsallis entropy of two independent systems is equal to the sum of the Tsallis entropies of those systems, as expected for an extensive system. In [82] the Tsallis entropy of EEG signals is determined by quantizing the amplitude of the EEG; Tsallis entropy is computed from the histogram of amplitude values (with q = 0.5, for the sake of definiteness). Approximate entropy [73] reflects the likelihood that patterns in a given signal will not be followed by additional "similar" patterns.…”

Complexity Measures for Quantifying Changes in Electroencephalogram in Alzheimer’s Disease

“…Information theoretic methods (i.e., TsEn and LZC) have emerged as a potentially useful complexity-based approach to derive robust EEG biomarkers of AD [47,[58][59][60][61][62]. They are attractive because of the potential natural link between information theory-based biomarkers and changes in the brain caused by AD [58]. Conceptually, information processing activities in the brain are thought to be reflected in the information content of the EEG.…”

“…In this study, we investigated an important class of complexity measures, information theoretic methods, which offers a potentially powerful approach for quantifying changes in the EEG due to AD [58]. Information theoretic methods (i.e., TsEn and LZC) have emerged as a potentially useful complexity-based approach to derive robust EEG biomarkers of AD [47,[58][59][60][61][62]. They are attractive because of the potential natural link between information theory-based biomarkers and changes in the brain caused by AD [58].…”

Complexity extraction of electroencephalograms in Alzheimer's disease with weighted-permutation entropy

“…Recently, different kinds of entropic algorithms have been applied to the analysis of EEG signals of healthy subjects during resting states or cognitive tasks, epilepsy and Parkinson's disease. 9,10 Furthermore, several entropic studies [11][12][13][14][15][16][17] have all shown that the EEG of AD patients seems to be less complex than that of age-matched control subjects.…”