Analytics in Action News

Artificial Intelligence Tool Seeks to Enhance Parkinson’s Diagnosis

A new artificial intelligence tool aims to differentiate the precise diagnosis for early Parkinson’s from two related Parkinson’s-like syndromes.

Artificial intelligence tool seeks to enhance Parkinson's diagnosis

Source: Getty Images

By Jessica Kent

- Researchers from the University of Florida will use a $5 million grant from NIH to test a new artificial intelligence tool aimed at improving the diagnosis of Parkinson’s and related conditions.

The AI tool will distinguish the precise diagnosis for early Parkinson’s disease or two related but distinct Parkinson’s-like syndromes. The three distinct neurodegenerative disorders – Parkinson’s disease, multiple system atrophy Parkinsonian variant (MSAp), and progressive supranuclear palsy (PSP) – can share overlapping motor and non-motor features, like changes in gait.

However, these three conditions also have critical differences in pathology and prognosis. Accurately diagnosing patients with these conditions is key to determining the best possible treatments for patients, as well as developing improved therapies for the future.

Previous research has shown that accuracy in diagnosis of Parkinson’s can be as low as 58 percent, and more than half of misdiagnosed patients actually have one of the two variants.

Testing of the new AI tool will include MRI images from 315 patients at 21 sites across North America. To differentiate between the forms of Parkinsonism, researchers have developed a novel, noninvasive biomarker technique using diffusion-weighted MRI. This technique measures how water molecules diffuse in the brain and helps identify where neurodegeneration is occurring.

With the new NIH grant, the team will create a new web-based software tool that they will test within the Parkinson’s study group, a large North American network of clinician-researchers evaluating Phase 2 and Phase 3 clinical trials in Parkinsonism. Patient recruitment is scheduled to begin at 19 US sites and two in Canada by summer and continue for two years.

“What is new is the use of artificial intelligence for predicting the type of Parkinsonism,” said Angelos Barmpoutis, PhD, an associate professor and coordinator of research and technology at UF’s Digital Worlds Institute.

“In order to train a computer to identify Parkinsonism, we need to teach it using a lot of data. One solution for that is crowd sourcing — going around to different institutes that have patients and asking them to contribute to this big project. We try to collect as many data points by creating what I believe is one of the largest databases for this particular type of diagnosis.”

Physicians at the 21 study sites will upload MRI images from a baseline visit with each participating patient, and the algorithm will compute a diagnosis and determine if it matches the diagnosis received in clinic.

Additionally, a UF neurologist and University of Chicago neurologist who specialize in movement disorders will assess video of each patient and their clinical history to evaluate the diagnosis. Each participant will then be reevaluated clinically 18 months later to confirm their diagnosis.

“This isn’t going to replace the physician’s decision making; it’s just meant to be another tool in their toolkit,” said David Vaillancourt, PhD, professor and chair of the UF College of Health & Human Performance's department of applied physiology and kinesiology. “The goal is that clinical trials will be better because they will focus on specific variants. Patients will be able to know their diagnosis earlier.”

The team’s ultimate goal is to gain approval from the FDA for use of the tool as a clinically approved diagnostic marker to adequately distinguish between forms of Parkinsonism.

“One of the critical needs in the Parkinson’s field is to be able to accurately diagnose patients in the early stages, including differentiating between types of Parkinsonisms,” said Michael Okun, MD, chair of UF’s department of neurology and executive director of the Norman Fixel Institute for Neurological Diseases at UF Health.

“This project is a huge step forward as, if successful, we will have developed a reliable marker for different forms of Parkinsonism. We will be able to use this marker to test new therapies stuck in the development pipeline.”

Researchers expect that the project will help accelerate the development of improved treatments for all three conditions.

“This will hopefully translate into better therapies available sooner for those with Parkinson’s disease and Parkinsonisms,” Okun concluded.