Here, we present and validate a method that lets us predict the severity of cognitive impairments after stroke, and the likely course of recovery over time. Our approach employs (a) a database that records the behavioural scores from a large population of patients who have, collectively, incurred a comprehensive range of focal brain lesions, (b) an automated procedure to convert structural brain scans from those patients into three-dimensional images of their lesions, and (c) a system to learn the relationship between patients' lesions, demographics and behavioural capacities at different times post-stroke. Validation against data collected from 270 stroke patients suggests that our first set of variables yielded predictions that match or exceed the predictive power reported in any comparable work in the available literature. Predictions are likely to improve when other determinants of recovery are included in the system. Many behavioural outcomes after stroke could be predicted using the proposed approach.
Keywords: Aphasia; Gaussian processes; Machine learning; Recovery; Speech production; Stroke.