Developing machine learning models of disease progression and survival outcomes in ALS patients: evaluating the utility of structural brain MRI as an ALS biomarker
Project Overview
Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disorder with no known cure, leading to progressive loss of motor function and ultimately the death of the patient. While it is known that patients with ALS experience changes in certain brain regions, the relationships between these brain-related changes, patient symptoms, and survival outcomes are still unknown. Magnetic resonance imaging (MRI) is a non-invasive neuroimaging technique that can be used to detect and quantify the brain changes in ALS patients. Combining machine learning and deep learning methods with MRI-based brain measures, we propose to develop accurate disease biomarkers and models that can be used to track the progress of the disease in the patients, and predict their future clinical symptoms and survival outcomes. By combining advanced MRI analysis techniques and innovative machine learning and deep learning approaches, we can uncover complex data patterns that would otherwise remain undetectable, providing further insights into the mechanisms involved in disease progression, survival, and clinical disability. The proposed study will lead to development of MRI-based biomarkers that can be used to non-invasively monitor disease progression as well as prognostic models that can be used for disease management and clinical trial enrichment.
Principal Investigator
Mahsa Dadar , Centre de recherche de l’hôpital Douglas/Douglas Hospital Research Centre
Team Members
Sanjay Kalra, University of Alberta
Partners and Donors
ALS Society of Canada