Using AI to better understand—and fight—Alzheimer’s disease
Machine learning is helping researchers unlock the secrets to ‘cognitive resilience’.
The brain pathology of Alzheimer’s disease doesn’t always lead to dementia, and researchers at the University of Michigan Engineering and Medical School believe this “cognitive resilience” phenomenon could lead to new treatments.
The team is taking a radically different approach. Instead of focusing on preventing or slowing the disease by studying a small number of genes or treatments at a time, they model the brain as a vast, interconnected network. And they analyze how millions of genetic interactions across a lifetime might shape cognitive resilience.
Anne Draelos, assistant professor of biomedical engineering, has applied advanced machine learning and generative AI—techniques often used in video production and autonomous driving—to tackle this complexity.
“What those applications have in common with neuroscience is that their data has a high degree of dimensionality; there’s the need to integrate many different kinds of data into a single mathematical model,” Draelos said.
The researchers simulate how genes interact in the brain and how potential treatments might reinforce resilience. Early studies in mice have demonstrated that the approach is promising.
“Eventually, we want to be able to take a blood sample, sequence the patient’s genome to identify their specific risk profile and then determine which drugs could promote resiliency networks,” said Catherine Kaczorowski, the Elinor Levine Professor of Dementia Research at the U-M Medical School and a lead researcher on the project. “We’ll be working with pharmaceutical companies and other collaborators to identify drugs that are already FDA-approved and could improve outcomes for dementia patients.”
AI contributed to this human-edited summary of the article AI powers a new front in the fight against Alzheimer’s by Gabe Cherry.