Eye movement behavior identification for Alzheimer's disease diagnosis

• Main Author: Juan Biondi, Gerardo Fernandez, Silvia Castro, Osvaldo Agamennoni
• Format: Article
• Language: English
• Published: IMR (Innovative Medical Research) Press Limited 2018-11-01
• Series: Journal of Integrative Neuroscience
• Subjects: |eye-tracking|deep-learning|alzheimer’s disease|neurodegenerative diseases|eye movement behavior|neuropsychological processes
• Online Access: https://jin.imrpress.com/fileup/1757-448X/PDF/1546069972927-1824017746.pdf

We develop a deep-learning approach to differentiate between the eye movement behavior of people with neurodegenerative diseases during reading compared to healthy control subjects. The subjects with and without Alzheimer’s disease read well-defined and previously validated sentences including high- and low-predictable sentences, and proverbs. From these eye-tracking data trial-wise information is derived consisting of descriptors that capture the reading behavior of the subjects. With this information a set of denoising sparse-autoencoders are trained and a deep neural network is built using the trained autoencoders and a softmax classifier that identifies subjects with Alzheimer’s disease with 89.78% accuracy. The results are very encouraging and show that such models promise to be helpful for understanding the dynamics of eye movement behavior and its relation with underlying neuropsychological processes.