The mechanisms of chronic post-stroke cognitive impairments are currently poor understood. However, the study of functional connectivity gives new opportunities to better elucidate the physiopathology. Here, using resting functional connectivity and a machine learning approach, we tried to predict the evolution of cognitive functions up to 36 months after stroke. The results showed that the prediction capacity depends on the studied cognitive domain, and that a particular focus should be done on frontal and temporal cortices.
This abstract and the presentation materials are available to members only; a login is required.