Multiway array decomposition analysis of EEGs in Alzheimer's disease

Methods for the extraction of features from physiological datasets are growing needs as clinical investigations of Alzheimer's disease (AD) in large and heterogeneous population increase. General tools allowing diagnostic regardless of recording sites, such as different hospitals, are essential and if combined to inexpensive non-invasive methods could critically improve mass screening of subjects with AD. In this study, we applied two state of the art multiway array decomposition (MAD) methods to extract unique features from electroencephalograms (EEGs) of AD patients obtained from multiple sites. In comparison to MAD, spectral–spatial average filter (SSFs) of control and AD subjects were used as well as a common blind source separation method, algorithm for multiple unknown signal extraction (AMUSE), and singular value decomposition (SVD) coupled to tensor unfolding. We trained a feed-forward multilayer perceptron (MLP) to validate and optimize AD classification from two independent databases. Using a third EEG dataset, we demonstrated that features extracted from MAD outperformed features obtained from SSFs AMUSE in terms of root mean squared error (RMSE) and reaching up to 100% of accuracy in test condition. We propose that MAD maybe a useful tool to extract features for AD diagnosis offering great generalization across multi-site databases and opening doors to the discovery of new characterization of the disease.

► Multi-array decomposition (MAD) method to extract unique, general features for multi-site diagnosis of Alzheimer's disease.
► Two state-of-the-art MAD were used: PARAFAC and non-negative tensor decomposition.
► MAD outperformed spectral mean, spatial–spectral mean, AMUSE and SVD/unfolding in training (97.6%), validation (97.6%), regularization (90%) and test (100%) using three independent databases.
► MAD can extract and reduce the number of linearly generalizable features with clinical meaning.