The National Institutes of Health (NIH) has awarded a $5 million grant to researchers investigating whether an artificial intelligence tool might improve the accuracy of diagnosing Parkinson’s disease at its early stages.
Early diagnosis is challenging due to the overlap of Parkinson’s motor and non-motor symptoms and those of two related neurodegenerative disorders, multiple system atrophy parkinsonian variant (MSAp) and progressive supranuclear palsy (PSP).
“What is new is the use of artificial intelligence for predicting the type of Parkinsonism,” Angelos Barmpoutis PhD, an associate professor and coordinator of research and technology with the Digital Worlds Institute at the University of Florida (UF), said in a press release.
“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,” he added.
About 58% of Parkinson’s cases are reported to be accurately diagnosed at early stages, affecting disease management and patient prognosis for those who are not.
“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 and professor of the 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,” he added.
The researchers previously developed a non-invasive MRI imaging technique, called diffusion-weighted MRI, that quantifies whether free water molecules accumulate in certain brain areas, namely the substantia nigra — an area involved in motor control and affected in Parkinson’s — that could provide a way to track brain damage like neurodegeneration.
Their technique was validated in a large international study in patients, showing that diffusion-weighted MRI could help distinguish between people with Parkinson’s and those with MSAp and PSP.
Now, the team will create a web-based software tool to evaluate MRI scans in patients through the Parkinson Study Group, a North American network of clinician-researchers working with Phase 2 and 3 trials in parkinsonism. Patient recruitment is schedule to start this summer across 19 clinical sites in the U.S. and two in Canada.
Testing of the artificial intelligence (AI) tool will take place at these sites, and include MRI images from 315 patients. Physicians at the study sites will upload these MRI scans, all taken at a first (baseline) visit for each participant. The computer-based algorithm will then analyze the scans and establish a diagnosis, which will be compared with the clinical diagnosis given each person. Two neurologists specialized in movement disorders will also assess a patient’s clinical history and video recordings to evaluate each diagnosis.
Patients will be re-evaluated 18 months later to confirm their diagnosis.
Researchers hope to develop a tool that will aid doctors in establishing an accurate and early diagnosis of Parkinson’s and of atypical parkinsonism, MSAp and PSP.
“This isn’t going to replace the physician’s decision making; it’s just meant to be another tool in their toolkit,” Vaillancourt said. “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.”
If study results are promising, the researchers will ask the U.S. Food and Drug Administration to approve the tool for use in clinically diagnosing these diseases.
“This will hopefully translate into better therapies available sooner for those with Parkinson’s disease and Parkinsonisms,” Okun said.
We are sorry that this post was not useful for you!
Let us improve this post!
Tell us how we can improve this post?