Learning tools to predict treatment responses for schizophrenia from neuroimaging data

Schizophrenia is a chronic mental disorder associated with a significant health, social and financial burden, not only for patients but also for their families, and society. However, the current treatment methods have been only partially successful, mainly due to the inter-individual differences between patients, which means that a treatment that is successful for one patient, might not work for another. Here, we will explore ways to determine whether a treatment will be successful based on measurable features, including many derived from various modalities of magnetic resonance imaging of patientâs brain. The proposed project aims to develop systems that can learn models that will enable psychiatrists to administer “patient-specific treatment”, by using earlier clinical experience to determine which treatment is best suited for each individual patient, based on measurements from brain scans. Such an objective evidence-based approach can potentially improve patient outcome as these
clinical decisions would be less influenced by the subjective diagnostic tools that are currently used in
psychiatric practice.

Faculty Supervisor:

Russell Greiner

Student:

Sunil Kalmady

Partner:

IBM Canada

Discipline:

Computer science

Sector:

Medical devices

University:

Program: