Multiple sclerosis (MS) disease is characterized by regional demyelination that occurs as focal lesions. This leads to disruptions of connectivity patterns in sub-cortical regions that can result in motor, sensory, and/or cognitive dysfunction. Among symptoms, cognitive impairment is increasingly being recognized as a common and disabling symptom of MS that contributes to poor quality of life in affected patients. Up to 70% of MS patients experience cognitive dysfunction during the course of their disease. The areas which have commonly shown more deficits are information processing speed, complex attention, memory, and executive function. Scientific evidence supports cognitive screening and evaluation for people with MS. Despite this, cognitive function is not openly discussed, routinely evaluated or optimally treated. Consequently, it is one of the major unmet needs in MS care. The cognitive impairment assessments currently being used each have a drawback.

We are proposing software, based on machine learning, which analyzes the data gathered in a task-based functional magnetic resonance imaging (fMRI) at early stages of MS and in Relapsing-Remitting MS (RRMS) suffers. MS causes disruptions in the functional connectivity network of the brain which can be determined using brain network analyses. Our proposed solution examines the changes in brain functional connectivity topologies induced by a specific cognitive task performance requiring attention, working memory, and information processing speed. As a result, cognitive impairment can be detected and treated at the very early stages of MS.