"This effort truly highlights the importance of interdisciplinary collaboration. Thanks to the combined medical expertise, scientific expertise, and technological expertise, we were able to accomplish a goal that will change the lives of countless individuals," said study author Angelos Barmpoutis, Ph.D., a professor at the Digital Worlds Institute at the University of Florida, in a press release.
Parkinson’s disease can refer to a variety of conditions, including the most common type, idiopathic Parkinson’s, and rarer conditions like progressive supranuclear palsy. Current diagnostic techniques produce accurate diagnoses 55- 78% of the time in the first five years of assessment, meaning that between one in four and one in two patients are misdiagnosed. Novel ways to improve diagnosis are needed.
In the current study, researchers investigated whether MRI imaging alongside machine learning could help differentiate between different varieties of Parkinson’s disease. They used software known as Automated Imagining Differentiation for Parkinsonism (AIDP), which uses machine learning to analyze diffusion-weighted MRI brain scans, which assess how water molecules diffuse in the brain to indicate where neurodegeneration is occurring.
The researchers tested the software on 249 patients and a retrospective cohort of 396 patients. Ultimately, AIDP differentiated between typical Parkinson's disease and atypical parkinsonism with 96% accuracy. AIDP predictions were neuropathologically confirmed in 46 of 49 brains, or in 93.9% of those examined.
"This is an instance where the innovation between technology and artificial intelligence has been proven to enhance diagnostic precision, allowing us the opportunity to further improve treatment for patients with Parkinson's disease. We look forward to seeing how this innovation can further impact the Parkinson's community and advance our shared goal of better outcomes for all." said study author Michael Okun, M.D., director of the Norman Fixel Institute for Neurological Diseases at the University of Florida, in a press release.
Sources: Science Daily, JAMA Neurology
