Carleton University

Purpose

Early identification of cognitive decline allows for earlier intervention with appropriate care so that entry to long term care can be delayed. This project explores two non-invasive assessments (eye-tracking and speech patterns) that have potential for cognitive assessment. Specifically, the project will design a system to capture voice and eye-gaze data during tasks, with the goal of detecting speech and oculomotor abnormalities associated with cognitive decline. It will combine the two modalities and leverage multimodal analysis techniques to generate more sensitive predictions. The project will analyze combinations of tasks to achieve the assessment. The project will collect longitudinal data, to allow intra-subject analysis in addition to cross-sectional analysis to validate the performance of the system. The project will lead to a more cost-effective approach for assessment that could be done at home or remotely and that is an alternative to more expensive or invasive diagnostic testing currently being done.