Stacked generalization for early diagnosis of Alzheimer's disease

The diagnosis of Alzheimer's disease (AD) at an early stage is a major concern due to growing number of elderly population affected by the disease, as well as the lack of a standard diagnosis procedure available to community clinics. Recent studies have used wavelets and other signal processing methods to analyze EEG signals in an attempt to find a non-invasive biomarker for AD. These studies had varying degrees of success, in part due to small cohort size. In this study, multiresolution wavelet analysis is performed on event related potentials of the EEGs of a relatively larger cohort of 44 patients. Particular emphasis was on diagnosis at the earliest stage and feasibility of implementation in a community health clinic setting. Extracted features were then used to train an ensemble of classifiers based stacked generalization approach. We describe the approach, and present our promising preliminary results.