Artificial intelligence (AI) is revolutionizing healthcare by transforming how medical professionals diagnose, treat, and manage patient care. From analyzing medical images and patient data to identifying high-risk cases and predicting treatment outcomes, AI is enhancing healthcare services’ accuracy, efficiency, and effectiveness. By leveraging machine learning algorithms and natural language processing, AI is helping healthcare providers make more informed decisions, improve patient outcomes, and streamline clinical workflows. 

The University of Florida has recently developed a video processing technology that uses Artificial Intelligence. This technology will enable neurologists to track the progression of Parkinson’s disease in patients effectively, enhancing their care and quality of life in the process.  

What is Parkinson’s disease? 

Parkinson’s disease is a neurological disorder that affects mobility and may lead to stiffness, tremors, slowness of movement, and difficulties with balance and coordination. Typically, symptoms start mildly and get worse with time. Parkinson’s disease cannot be diagnosed with a particular lab test or imaging scan; nevertheless, a patient’s performance in several exercises and manoeuvres can assist medical professionals in determining the disorder’s severity. 

AI-Powered Video Analysis 

The finger-tapping test is a common way to screen for Parkinson’s disease. It involves rapidly tapping the thumb and index finger ten times. Diego Guarin, Ph.D., an assistant professor of applied physiology and kinesiology at the UF College of Health and Human Performance, developed the system. It uses machine learning to analyze video recordings of patients performing the test.  

“By studying these videos, we could detect even the smallest alterations in hand movements characteristic of Parkinson’s disease but might be difficult for clinicians to visually identify,” said Guarin, affiliated with the Norman Fixel Institute for Neurological Diseases at UF Health. “The beauty of this technology is that a patient can record themselves performing the test, and the software analyzes it and informs the clinician how the patient is moving so the clinician can make decisions.”  

Tracking the disease with ML 

The Movement Disorder Society-Unified Parkinson’s Disease Rating Scale is the most widely used rating system for tracking the progression of Parkinson’s disease. Guarin emphasized that although the rating is reliable, it is limited to a 5-point scale, making it challenging to follow slight changes in growth and are open to arbitrary interpretations.  

The research team, which included UF neurologists Joshua Wong, M.D., Nikolaus McFarland, M.D., Ph.D., and Adolfo Ramirez-Zamora, M.D., developed a more objective method to quantify motor symptoms in Parkinson’s patients using machine learning algorithms to analyze videos and capture subtle changes in the disease over time,  

AI made it easier! 

“We found that we can observe the same features that the clinicians are trying to see by using a camera and a computer,” Guarin said. “With help from AI, the same examination is made easier and less time-consuming for everyone involved.” Guarin said the automated system has also revealed previously unnoticed details about movement using precise data collected by the camera, like how quickly the patient opens or closes the finger during movement and how much the movement properties change during every tap. 

“We’ve seen that, with Parkinson’s disease, the opening movement is delayed, compared to the same movement in healthy individuals,” Guarin said. “This is new information that is almost impossible to measure without the video and computer, telling us the technology can help to better characterize how Parkinson’s disease affects movement and provide new markers to help evaluate the effectiveness of therapies.”  

Training the model using HiPerGator 

To perfect the system, which Guarin initially designed to analyze facial features for conditions other than Parkinson’s disease, the team tapped into UF’s HiPerGator — one of the world’s largest AI supercomputers — to train some of its models.  

“HiPerGator enabled us to develop a machine learning model that simplifies the video data into a movement score,” Guarin explained. “We used HiPerGator to train, test, and refine different models with large amounts of video data, and now those models can run on a smartphone.”  

A gamechanger for clinical trials 

Michael S. Okun, M.D., the director of the Norman Fixel Institute and medical advisor for the Parkinson’s Foundation, said the automated video-based assessments could be a “game changer” for clinical trials and care.  

“The finger-tapping test is one of the most critical elements used for diagnosis and measuring disease progression in Parkinson’s disease,” Okun said. “Today, it takes an expert to interpret the results, but what is transformative is how Diego and three Parkinson’s neurologists at the Fixel Institute were able to use AI to objectify disease progression.”  

Besides offering neurologists and other healthcare professionals this technology, Guarin is collaborating with UFIT to transform it into a mobile app enabling patients to track their disease at home over time. 

Source: University of Florida