Multiple characteristics analysis of Alzheimer's electroencephalogram by power spectral density and Lempel-Ziv complexity

Abstract

To investigate the electroencephalograph (EEG) background activity in patients with Alzheimer's disease (AD), power spectrum density (PSD) and Lempel-Ziv (LZ) complexity analysis are proposed to extract multiple effective features of EEG signals from AD patients and further applied to distinguish AD patients from the normal controls. Spectral analysis based on autoregressive Burg method is first used to quantify the power distribution of EEG series in the frequency domain. Compared with the control group, the relative PSD of AD group is significantly higher in the theta frequency band while lower in the alpha frequency bands. In order to explore the nonlinear information, Lempel-Ziv complexity (LZC) and multi-scale LZC is further applied to all electrodes for the four frequency bands. Analysis results demonstrate that the group difference is significant in the alpha frequency band by LZC and multi-scale LZC analysis. However, the group difference of multi-scale LZC is much more remarkable, manifesting as more channels undergo notable changes, particularly in electrodes O1 and O2 in the occipital area. Moreover, the multi-scale LZC value provided a better classification between the two groups with an accuracy of 85.7 %. In addition, we combine both features of the relative PSD and multi-scale LZC to discriminate AD patients from the normal controls by applying a support vector machine model in the alpha frequency band. It is indicated that the two groups can be clearly classified by the combined feature. Importantly, the accuracy of the classification is higher than that of any one feature, reaching 91.4 %. The obtained results show that analysis of PSD and multi-scale LZC can be taken as a potential comprehensive measure to distinguish AD patients from the normal controls, which may benefit our understanding of the disease.

Keywords: Alzheimer’s disease; Electroencephalogram; Lempel–Ziv complexity; Multi-scale Lempel–Ziv complexity; Power spectrum density.

Fig. 1

The distribution of electrode loci in the modified 10–20 electrode configuration for 16-channel EEGs marked in a brain is represented in a, and the real EEG recordings of 16-channels in b

Fig. 2

Multi-scale LZC block diagram

Fig. 3

The relative PSD values averaged over the 16 electrodes in the four frequency bands for AD group and control group. Standard errors are represented with error bars. P values returned by one way ANOVA are also displayed

Fig. 4

Topographic maps of PSD values for AD group (left), the control group (middle), and the normalized differences between two groups (right) in a delta, b theta, c alpha and d beta sub-band, respectively

Fig. 5

The average traditional LZC values (a) and the average multi-scale LZC values (b) averaged over the 16 electrodes in the four frequency bands for AD group and control group. Standard errors are represented with error bars. Asterisk represents significant difference between two groups with P < 0.01 by ANOVA analysis

Fig. 6

The average traditional LZC values (a) and the average multi-scale LZC values (b) of the EEGs in AD group and control group for all channels

Fig. 7

Scatter plots of average a LZC and b multi-scale LZC values of the EEGs on O1 and O2 channel for AD group and the control group in the alpha frequency band

Fig. 8

ROC curves which assesses the classification performance between AD patients and the normal controls in the alpha band with LZC and multi-scale LZC. In addition, the green dotted line is known as the “no-discrimination line” and corresponds to a classifier which returns random guesses. (Color figure online)

Fig. 9

ROC curves for discriminating AD patients and normal controls with PSD, multi-scale LZC and their combined feature