Shishkin Sl

EEG filtering based on blind source separation (BSS) for early detection of Alzheimer's disease

OBJECTIVEnDevelopment of an EEG preprocessing technique for improvement of detection of Alzheimers disease (AD). The technique is based on filtering of EEG data using blind source separation (BSS) and projection of components which are possibly sensitive to cortical neuronal impairment found in early stages of AD.nnnMETHODSnArtifact-free 20s intervals of raw resting EEG recordings from 22 patients with Mild Cognitive Impairment (MCI) who later proceeded to AD and 38 age-matched normal controls were decomposed into spatio-temporally decorrelated components using BSS algorithm AMUSE. Filtered EEG was obtained by back projection of components with the highest linear predictability. Relative power of filtered data in delta, theta, alpha 1, alpha 2, beta 1, and beta 2 bands were processed with Linear Discriminant Analysis (LDA).nnnRESULTSnPreprocessing improved the percentage of correctly classified patients and controls computed with jack-knifing cross-validation from 59 to 73% and from 76 to 84%, correspondingly.nnnCONCLUSIONSnThe proposed approach can significantly improve the sensitivity and specificity of EEG based diagnosis.nnnSIGNIFICANCEnFiltering based on BSS can improve the performance of the existing EEG approaches to early diagnosis of Alzheimers disease. It may also have potential for improvement of EEG classification in other clinical areas or fundamental research. The developed method is quite general and flexible, allowing for various extensions and improvements.

Trimmed estimators for robust averaging of event-related potentials

Averaging (in statistical terms, estimation of the location of data) is one of the most commonly used procedures in neuroscience and the basic procedure for obtaining event-related potentials (ERP). Only the arithmetic mean is routinely used in the current practice of ERP research, though its sensitivity to outliers is well-known. Weighted averaging is sometimes used as a more robust procedure, however, it can be not sufficiently appropriate when the signal is nonstationary within a trial. Trimmed estimators provide an alternative way to average data. In this paper, a number of such location estimators (trimmed mean, Winsorized mean and recently introduced trimmed L-mean) are reviewed, as well as arithmetic mean and median. A new robust location estimator tanh, which allows the data-dependent optimization, is proposed for averaging of small number of trials. The possibilities to improve signal-to-noise ratio (SNR) of averaged waveforms using trimmed location estimators are demonstrated for epochs randomly drawn from a set of real auditory evoked potential data.

Early detection of alzheimer’s disease by blind source separation, time frequency representation, and bump modeling of EEG signals

The early detection Alzheimer’s disease (AD) is an important challenge. In this paper, we propose a novel method for early detection of AD using electroencephalographic (EEG) recordings: first a blind source separation algorithm is applied to extract the most significant spatio-temporal components; these components are subsequently wavelet transformed; the resulting time-frequency representation is approximated by sparse “bump modeling”; finally, reliable and discriminant features are selected by orthogonal forward regression and the random probe method. These features are fed to a simple neural network classifier. The method was applied to EEG recorded in patients with Mild Cognitive Impairment (MCI) who later developed AD, and in age-matched controls. This method leads to a substantially improved performance (93% correctly classified, with improved sensitivity and specificity) over classification results previously published on the same set of data. The method is expected to be applicable to a wide variety of EEG classification problems.