A new AI-based tool, VisionMD, developed by the University of Florida, is transforming how clinicians assess and treat Parkinson’s disease and other movement disorders by providing precise and objective video analyses.
A breakthrough in medical technology is emerging from the University of Florida, where a researcher has designed an innovative open-source computer program aimed at revolutionizing the assessment of Parkinson’s disease and other movement disorders. This new tool, named VisionMD, utilizes artificial intelligence to scrutinize video recordings of patients, thereby enabling more accurate and objective monitoring of their motor functions.
Diego Guarin, an assistant professor of applied physiology and kinesiology at UF’s College of Health and Human Performance and a member of UF Health’s Fixel Institute for Neurological Diseases, is the mastermind behind VisionMD.
He developed the software to mitigate the risks associated with the traditional, often subjective clinical assessments.
“Over the years, we have shown through our research that video analysis of patients performing finger-tapping and other movements provides valuable information about how the disease is progressing and responding to medications or deep brain stimulation,” Guarin said in a news release. “However, clinicians don’t have the time and personnel to analyze their videos. To address this, we developed software that can deliver useful results with just a few clicks.”
Working in concert with neurologists and clinicians from the Fixel Institute, Guarin has fine-tuned VisionMD to extract precise motion metrics from standard videos.
These recordings can be captured on smartphones, laptops or even through Zoom, offering unparalleled convenience and ensuring data privacy by operating entirely on local computers.
“It’s not cloud-based, so there is no risk of data leaving the network. You can even unplug from the internet, and it still runs,” Guarin added.
The global medical community has already taken note. Researchers across Germany, Spain and Italy are employing VisionMD to analyze thousands of patient videos.
Florian Lange, a neurologist at University Hospital Würzburg, is one such early adopter who highlighted the software’s ability to provide consistent, objective measurements.
“A big challenge with many aspects of medicine today is how difficult it is to get objective data, especially with movement disorders like Parkinson’s disease or tremor,” Lange said in the news release. “If the three of us watched the same video of a patient, we might rate the severity at three different levels. But the software gives us precise, unbiased data.”
In Würzburg, Lange and his colleague Martin Reich, a neuroimaging professor at the University of Würzburg, have adapted VisionMD to optimize treatments for patients with tremor, particularly those with deep brain stimulation (DBS) implants.
The tool’s ability to accurately compare different DBS configurations in identifying the best symptom relief settings is a notable advancement.
“There are millions of possible programming options, but this tool helps us narrow it down quickly and accurately,” added Reich.
As open-source software, VisionMD is freely available, allowing researchers and clinicians to improve and tailor it to their specific needs. The team behind the tool is also working on incorporating additional motor assessment tasks to further its clinical utility.
Early users praise VisionMD’s accessibility and straightforward operation, suggesting it could significantly impact movement disorder care and research.
“It takes only a few seconds to process each video,” Guarin added. “We are confident most clinicians will be able to use it, regardless of their technical expertise.”
The research has been published in the journal Nature.
Source: University of Florida