Early Detection of Alzheimer’s Disease by Blind Source Separation, Time Frequency Representation, and Bump Modeling of EEG Signals

Abstract

Abstract. 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 timefrequency 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.

Blind source separation to enhance spectral and non-linear features of magnetoencephalogram recordings. Application to Alzheimer's disease

“…Previous research by other authors had shown the utility of the BSS and component selection preprocessing when spectral and time-scale features were computed from EEGs of MCI patients who later proceeded to AD [12,22]. These EEG signals were characterised with the relative powers in six frequency bands [12].…”

“…Additionally, a later study used a "bump modelling" of the partially reconstructed EEG wavelet time-frequency transform and a neural network classifier to further improve the subject classification [22]. In contrast to these studies, our classification method allowed us to assess the improvement in each variable (MF, SpecEn, LZC or SampEn) separately.…”

“…Thus, features extracted from the BSS-processed signals x partial (t) may distinguish AD patients better than those extracted from the original MEGs -x(t) - [12,14,22].…”

“…Instead, we apply BSS as a preprocessing step to enhance the differences between AD patients and controls' brain activity [12,14,22]. Thus,…”

“…Considering these research studies, it can be hypothesised that the application of BBS, together with features extracted from electromagnetic brain activity recordings, may enhance features associated with diseases like AD. This is due to the fact that some BSS components of the EEG and MEG signals may be more sensitive to AD than others [12,14,22]. Hence, the most relevant components may be selected and the electromagnetic brain signals may be partially reconstructed using only these components to achieve a better discrimination between AD patients and healthy subjects [14].…”