For patients diagnosed with Parkinson’s disease, one of the greatest uncertainties is what comes next. Some people experience relatively mild symptoms for years. Others face a much steeper course marked by worsening movement problems, cognitive decline, or both. New research from the University of Miami suggests artificial intelligence may help identify patients at increased risk for rapid decline years before those changes become apparent.
Just as importantly, researchers discovered that some of the most valuable predictive information came not from advanced brain imaging but from clinical measurements neurologists already collect during routine patient visits.
“One of the most difficult things about Parkinson’s disease is not knowing how it will go,” said Ihtsham ul Haq, M.D., professor of neurology at the University of Miami Miller School of Medicine, the Cornfeld-Hurowitz Endowed Chair in Movement Disorders and associate director of the Evelyn F. McKnight Brain Institute. Dr. Haq is senior author of the study. “We wanted to use AI’s ability to analyze many kinds of information at once to see if it could predict who would have a more rapid motor or cognitive decline.”
Bringing AI and Neurology Together
The interdisciplinary project brought together UM neurologists, radiologists, computer scientists and artificial intelligence experts. Among them was Yelena Yesha, Ph.D., a professor in the Department of Computer Science in the UM College of Arts and Sciences, Knight Foundation Endowed Chair of Data Science and AI and a Miller School faculty member with a secondary appointment in radiology.
A few years ago, Dr. Haq and co-author Tatjana Rundek, M.D., Ph.D., a professor of neurology and Evelyn F. McKnight Chair for Learning and Memory in Aging at the Miller School, approached Dr. Yesha to explore whether artificial intelligence could help address difficult questions in neurodegenerative disease, including predicting which patients might face a more aggressive Parkinson’s disease trajectory.
Click here to continue reading this Miller School of Medicine NEWS article “Can AI Models Identify Parkinson’s Patients at Risk for Faster Decline?” by Kyra Gurney.
