Multivariate approaches for Alzheimer´s disease diagnosis using Bayesian classifiers

Alzheimer´s Disease (AD) is the most common cause of dementia that usually affects the elderly. The early accurate diagnosis of the AD still remains a diagnostic challenge especially during the early stage of the disease that offers better opportunities to treat its symptoms. In this work we present a complete computer-aided diagnosis (CAD) system for the early diagnosis of the AD based on multivariate approaches. Features are extracted from the neurological images by means of multivariate techniques such as principal component analysis (PCA) and linear discriminant analysis (LDA), and a Bayesian framework is used on these features for automatic classification. The resulting CAD system yields better accuracy values than other recently developed techniques.