An innovative video-processing method that employs artificial intelligence (AI) has emerged from the University of Florida. This exciting tool is poised to significantly improve the monitoring and management of Parkinson's Disease, offering numerous benefits for both patients and healthcare providers alike.
The creator of the system, Diego Guarin, Ph.D., assistant professor of applied physiology and kinesiology in the UF College of Health and Human Performance, has applied machine learning to analyze videos of patients performing a standard test for Parkinson's disease, known as the finger-tapping test. This test involves the rapid tapping of the thumb and index finger ten times.
"By utilizing the capabilities of artificial intelligence within this context, we are able to detect even the smallest of changes in a patient's hand movements, something that can pose quite a challenge for clinicians," Guarin explains. He further points out that the patients can self-record while performing the test, and the resulting video is then examined by the software, providing thorough insights to the healthcare provider.
Parkinson's Disease is a neurological disorder that greatly affects motor functions and coordination. The symptoms often start off subtly and gradually progress over time. Current methods of diagnosis involve a series of physical tests performed by the patient under the supervision of a medical professional.
Guarin's research team, comprised of UF neurologists Joshua Wong, M.D.; Nicolaus McFarland, M.D., Ph.D.; and Adolfo Ramirez, M.D., have developed a more objective manner of quantifying the motor symptoms in Parkinson's patients. Through the innovative use of machine learning algorithms, they successfully measure any changes, however subtle, in the progression of the disease.
The revolutionary automated system has also revealed previously undetectable details about a patient's movement. For instance, the ability to document the speed at which the patient opens or closes the finger during movements.
"Employing technology in this way is showing promising results in our understanding of how Parkinson's Disease affects movement and in providing potential markers for evaluating therapy effectiveness," Guarin enthuses.
By harnessing the power of HiPerGator, one of the world's largest AI supercomputers, the team has been able to further refine their models and develop a machine learning model that simplifies the video data into a movement score. Guarin sheds light on how HiPerGator's capabilities have allowed the team to train, test, and fine-tune their models.
The automated video-based assessments have been praised as a "game changer" for clinical trials and care by Michael S. Okun, M.D., the director of the Norman Fixel Institute and medical advisor for the Parkinson's Foundation. Guarin and his team are now in the process of developing it into an app for mobile devices which allows patients to self-monitor their disease progression at home.
Disclaimer: The above article was written with the assistance of AI. The original sources can be found on ScienceDaily.
