A technique that uses video and machine learning to quantify motor symptoms in early-stage Parkinson’s disease could help reveal signs of the disease and other movement disorders earlier, potentially leading to better treatment outcomes.
In a study just published in Parkinsonism and related disordersA team of researchers from the University of Florida and the Fixel Institute for Neurological Diseases has shown that video assessment can help detect parkinsonism in a person early by comparing movement on the left and right sides of the body. According to the researchers, this method takes advantage of the fact that Parkinson’s disease often begins asymmetrically, meaning one side is more affected than the other in the early stages of the disease.
The researchers used machine learning to analyse videos of people performing simple hand and leg movements that neurologists often use. The team looked for subtle differences between healthy individuals and those with early Parkinson’s disease. Their method was 86% accurate in distinguishing between the two groups.
“The technique is noninvasive, uses standard video recordings and could potentially help detect signs of parkinsonism earlier, improving treatment outcomes and patient management,” said senior author Deigo Guarin, assistant professor of applied physiology and kinesiology at UF.