Objective: Nowadays proper detection of cognitive impairment has become a challenge for
the scientific community. Alzheimer's Disease (AD), the most common cause of dementia, has a high
prevalence that is increasing at a fast pace towards epidemic level. In the not-so-distant future this fact
could have a dramatic social and economic impact. In this scenario, an early and accurate diagnosis of
AD could help to decrease its effects on patients, relatives and society. Over the last decades there have
been useful advances not only in classic assessment techniques, but also in novel non-invasive screening
Methods: Among these methods, automatic analysis of speech -one of the first damaged skills in AD
patients- is a natural and useful low cost tool for diagnosis.
Results: In this paper a non-linear multi-task approach based on automatic speech analysis is presented.
Three tasks with different language complexity levels are analyzed, and promising results that encourage
a deeper assessment are obtained. Automatic classification was carried out by using classic Multilayer
Perceptron (MLP) and Deep Learning by means of Convolutional Neural Networks (CNN) (biologically-
inspired variants of MLPs) over the tasks with classic linear features, perceptual features, Castiglioni
fractal dimension and Multiscale Permutation Entropy.
Conclusion: Finally, the most relevant features are selected by means of the non-parametric Mann-