Eye movement behavior identification for Alzheimer's disease diagnosis
| Autor: | Gerardo Fernandez, Osvaldo Agamennoni, Juan Andrés Biondi, Silvia Mabel Castro |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
business.industry
General Neuroscience Medicine Eye movement Identification (biology) eye-tracking|deep-learning|alzheimer’s disease|neurodegenerative diseases|eye movement behavior|neuropsychological processes General Medicine Disease business Neuroscience lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry lcsh:RC321-571 |
| Zdroj: | Journal of Integrative Neuroscience, Vol 17, Iss 4, Pp 349-354 (2018) |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|