McGill University Led Study Develops Breakthrough AI to Predict Progression of Neurodegenerative Disease

McGill University Led Study Develops Breakthrough AI to Predict Progression of Neurodegenerative Disease

Brain researchers from Montreal Neurological Institute, the Hospital of McGill University, and the Ludmer Centre for Neuroinformatics and Mental Health recently concluded a study revealing that artificial intelligence (AI) algorithms reveal the potential to predict neurodegenerative diseases progression among humans. This AI breakthrough can be harnessed to assist physicians to adopt more effective treatment strategies for those affected by such health conditions.

The Study

Published in the journal Brain, the researchers, according to their press release from McGill University, utilized an algorithm to analyze the blood and post-mortem brain samples of 1969 patients with Alzheimer’s and Huntington’s disease. Apparently, this algorithm has the ability to learn and hence detect how the patients’ genes individually expressed themselves over the decades. The Canadian researchers establishes an important milestone—that achieving the ability to generate a long-term view of molecular changes underlying neurodegeneration is important as neurodegenerative disease develops and unfolds over the years.

Why does this represent a Breakthrough?

Because the Canadian-based researchers have opened the door to use dynamic, AI to study neurodegeneration as opposed to the use of static or “snapshot” data which inherently limited how much any one team can understand about the typically slow progression of this general disease category. Because the computing power of the cloud, algorithmic sophistication and rapidly advancing knowledge of data science, the researchers have contributed to the ability to uncover the chronological information contained in large-scale data by covering decades of disease progression, improving scientists ability to understand how changes in gene expression over that time are related to changes in a specific patient’s condition.

Moreover, the blood test detected 85% to 90% of the top predictive molecular pathways that the test of post-mortem brain data did, evidencing a compelling resemblance between molecular changes in both the brain and peripheral body.

Clarifying some of the future prospective precision-based benefits of this AI tool, study first author Yasser Iturria-Medina noted, “This test could one day be used by doctors to evaluate patients and prescribe therapies tailored to their needs.” He continued, “It could also be used in clinical trials to categorize patients and better determine how experimental drugs impact their predicted disease progression.”

Study Data

This study was made possible with data accessible via the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Rush Alzheimer’s Disease Center, Rush University Medical Center in Chicago. ADNI brings together researchers with study data as they investigate to define the progression of Alzheimer’s disease (AD). ADNI researchers collect, validate and utilize data, including MRI and PET images, genetics, cognitive tests, CSF and blood biomarkers as predictors of the disease. Study resources and data from the North American ADNI study are available for research input through their website

The Rush Alzheimer’s Disease Center, Rush University Medical in Chicago is one of 29 Alzheimer’s centers in the United States designated and funded by the National Institute on Aging. It also offers patient care services at the Rush Memory Clinic, including neurological and psychological evaluations and consultation with Alzheimer’s specialists.

Funding

In an example of a dynamic, collaborative, public/private funding model, the study was funded by McGill University’s Healthy Brain for Healthy Lives Initiative, the Ludmer Centre and the Brain Canada Foundation and Health Canada support to the McConnell Brain Imaging Centre at the NEURO.

Lead Research/Investigator

Yasser Iturria-Medina, Assistant Professor, Department of Neurology and Neurosurgery, Faculty of Medicine, McGill University; Leads NeuroPM lab at the Montreal Neurological Institute & Hospital (the NEURO) and Principal investigator at Ludmer Centre for Neuroinformatics & Mental Health

Other authors include Ahmed F. Kahn, Quadri Adewale and Amir H. Shirazi.

Call to Action: The study lead was noted that the investigators will next be testing the developed AI models in other diseases such as Parkinson’s disease and amyotrophic lateral sclerosis. TrialSite News monitors this ongoing—sign up for the daily newsletter for updates. Perhaps there could be opportunities to commercialize this AI breakthrough?