AI and Parkinson's
NSF-supported researchers at the University of Rochester have developed an artificial intelligence system that can diagnose the severity of Parkinson's disease using a motor performance test from the comfort of home.
Credit: U.S. National Science Foundation
Artificial Intelligence allows for transformational advances in the science and engineering fields. AI is also being used now to help people suffering from Parkinson's disease to remotely assess the severity of their symptoms. We explore the future of AI tools for disease management in the U.S. National Science Foundation's "Discovery Files."
Parkinson's disease is the fastest growing neurological disability that causes problems with movement and other health issues. It affects over 8 million people according to the World Health Organization. The disease is progressive, and the symptoms get more severe.
As the disease progresses, Doctors have patients perform simple motor tasks to rate the severity using the Movement Disorder Society Unified Parkinson's Disease Rating Scale.
NSF-Supported researchers at the University of Rochester have developed a new AI tool that uses the rating scale guidelines to assess the severity of tremors.
Accessing via webcam, individuals with Parkinson's Disease perform a standardized finger-tapping exercise. The AI Model tracks the key points of the hand and measures interpretable and explainable metrics such as speed, hesitations, and rhythm.
While expert neurologists performed slightly better, the AI model outperformed primary care physicians with Unified Parkinson's Disease Rating Scale certification.
This new model has huge implications for patients that have difficulty travelling to appointments or accessing neurologists, allowing for improved access and health equity.
To hear more science and engineering news, including the researchers making it, subscribe to "NSF's Discovery Files" podcast.
Images and other media in the National Science Foundation Multimedia Gallery are available for use in print and electronic material by NSF employees, members of the media, university staff, teachers and the general public. All media in the gallery are intended for personal, educational and nonprofit/non-commercial use only.
Images credited to the National Science Foundation, a federal agency, are in the public domain. The images were created by employees of the United States Government as part of their official duties or prepared by contractors as "works for hire" for NSF. You may freely use NSF-credited images and, at your discretion, credit NSF with a "Courtesy: National Science Foundation" notation.
Additional information about general usage can be found in Conditions.