Cracking the Code: How to identify Movement issues in early stage Parkinson’s Disease?

A new technique utilizing videos and machine learning to assess motor symptoms in early-stage Parkinson’s disease could enable earlier detection of the condition and other movement disorders, potentially leading to improved treatment outcomes.

In a recently published study in Parkinsonism & Related Disorders, researchers from the University of Florida and the Fixel Institute for Neurological Diseases demonstrated that video analysis could identify early Parkinsonism by comparing the movements of an individual’s left and right sides.

The researchers explain that Parkinson’s disease often begins asymmetrically, with one side of the body being more affected in the early stages. By applying machine learning to video recordings of individuals performing simple hand and leg movements—similar to those assessed by neurologists—the team detected subtle differences between healthy individuals and those with early Parkinson’s disease, achieving 86% accuracy in distinguishing between the two groups.

“This technique is non-invasive, relies on standard video recordings, and could play a crucial role in the early detection of Parkinsonism, ultimately enhancing treatment outcomes and patient care,” said lead author Deigo Guarin, an assistant professor of applied physiology and kinesiology at the University of Florida.

For further details, refer to: Diego L. Guarín et al., “What the Trained Eye Cannot See: Quantitative Kinematics and Machine Learning Detect Movement Deficits in Early-Stage Parkinson’s Disease from Videos,” Parkinsonism & Related Disorders (2024). DOI: 10.1016/j.parkreldis.2024.107104

Provided by: University of Florida

Citation: “What the trained eye cannot see: Detecting movement deficits in early-stage Parkinson’s disease” (2024, August 15). Retrieved August 15, 2024.

This document is protected by copyright. No part may be reproduced without written permission, except for fair use in private study or research. The content is provided for informational purposes only.