In the present work, we develop a deep-learning approach for differentiating the eye-movement behavior of people with neurodegenerative diseases over healthy control subjects during reading well-defined sentences. We define an information compaction of the eye-tracking data of subjects without and with probable Alzheimer's disease when reading a set of well-defined, previously validated, sentences including high-, low-predictable sentences, and proverbs. Using this information we train a set of denoising sparse-autoencoders and build a deep neural network with these and a softmax classifier. Our results are very promising and show that these models may help to understand the dynamics of eye movement behavior and its relationship with underlying neuropsychological correlates.
@article{arxiv.1702.00837,
title = {Eye-Movement behavior identification for AD diagnosis},
author = {Juan Biondi and Gerardo Fernandez and Silvia Castro and Osvaldo Agamennoni},
journal= {arXiv preprint arXiv:1702.00837},
year = {2018}
}