Probabilistic neural networks for diagnosis of Alzheimer's disease using conventional and wavelet coherence

Recently, the authors presented an EEG (electroencephalogram) coherence study of the Alzheimer's disease (AD) and found statistically significant differences between AD and control groups. In this paper a probabilistic neural network (PNN) model is presented for classification of AD and healthy controls using features extracted in coherence and wavelet coherence studies on cortical connectivity in AD. The model is verified using EEGs obtained from 20 AD probable patients and 7 healthy/control subjects based on a standard 10-20 electrode configuration on the scalp. It is shown that extracting features from EEG sub-bands using coherence, as a measure of cortical connectivity, can discriminate AD patients from healthy controls effectively when a mixed band classification model is applied. For the data set used a classification accuracy of 100% is achieved using the conventional coherence and a spread parameter of the Gaussian function in a particular range found in this research.

Research highlights► A probabilistic neural network for classification of AD and healthy controls. ► Features are extracted in coherence and wavelet coherence studies of AD. ► The model is verified using EEGs obtained from 20 probable AD and 7 healthy subjects. ► Extracting features using coherence discriminates AD patients from controls. ► A high classification accuracy is achieved using the conventional coherence.