The National Institutes of Health (NIH) have funded a five-year effort to use state-of-the-art artificial intelligence methods to study Alzheimer’s Disease. The project titled – “Ultrascale Machine Learning to Empower Discovery in Alzheimer’s Disease Biobanks” also known as AI4AD – is being led by a team at USC’s Mark and Mary Stevens Neuroimaging and Informatics Institute. It will involve 40 co-investigators at 11 research centres.
Alzheimer’s is a devastating progressive neurodegenerative disorder which affects nearly 50 million people worldwide. Estimates indicate that this disease is likely to increase to more than 100 million by 2050 due to an ageing population. Early diagnosis can help stop disease progression and improve quality of life. However, there is still no definitive treatment for Alzheimer’s disease.
Applying artificial intelligence methods
Researchers will apply AI methods to giant databases of genetic, imaging and cognitive data collected from Alzheimer’s patients. In turn, they hope to strengthen precision diagnostics, prognostication and treatment development.
Paul Thompson, PhD, associate director of the INI and project leader for the new grant, stated:
“Our team of experts in computer science, genetics, neuroscience and imaging sciences will create algorithms that analyse data at a previously impossible scale.
Collectively, this will enable the discovery of new features in the genome that influence the biological processes involved in Alzheimer’s disease.”
The first objective of the project is to identify genetic and biological markers that predict an Alzheimer’s diagnosis (and to distinguish between subtypes). The team will apply sophisticated AI and machine learning methods to a variety of data types. This includes brain images and whole genome sequences. These findings will then be related back to the clinical progression of Alzheimer’s. Moreover, the team are also creating a dedicated ‘Drug Repurposing Core’ . The aim of this is to identify ways to repurpose existing drugs to target newly identified genome segments, molecules or neurobiological processes of Alzheimer’s. They hope this will yield significant translational impact on disease and drug development. Overall, the goals of AI4AD is to leverage the promise of machine learning to contribute to precision diagnostics, prognostication and targeted treatments.
Image credit: By wildpixel – canva.com