Recurrent neural network and wavelet transform based distinction between Alzheimer and control EEG

The diagnosis of Alzheimer's disease (AD) at the present time remains dependent upon clinical symptomatology. Lifetime accuracy in the best clinics remains 86-89%, and mean diagnostic delay in the clinical course of the disease remains 3.6 years after symptomatic onset. Although EEG is an obvious quantitative parameter related to the illness, it's limitation is the absence of an identified set of features that discriminates AD EEG abnormalities from those due to confounding conditions. As a consequence, no computerized method exists up to date that can reliably detect those abnormalities. The objective of this study is to develop a robust computerized method for early detection of AD in EEG. The authors explore the ability of specifically designed and trained recurrent neural network (RNN), combined with wavelet preprocessing, to discriminate between EEGs of early onset AD patients and age-matched control subjects. The RNNs are chosen because they can implement extremely nonlinear decision boundaries and possess memory of the state which is crucial for the considered task. The results on eyes-closed resting EEG reveal particularly favorable network behavior when applied to wavelet filtered subbands as opposed to original signal data.