What is it about?
Parkinson’s disease often changes the way people walk, but these changes can be subtle. In this study, we explored whether everyday movement data collected by a simple wrist-worn activity monitor could help identify these changes, using machine learning models.
Featured Image
Photo by Solen Feyissa on Unsplash
Why is it important?
Passive monitoring of walking in people with Parkinson’s disease could make it possible to track how these walking patterns change over time as the condition progresses. By collecting movement data during everyday life, rather than only during clinic visits, researchers and clinicians may gain a clearer picture of how symptoms develop. In addition, identifying very early changes in walking could allow people at risk to be monitored sooner, supporting earlier research, closer follow-up, and the development of treatments that aim to slow disease progression.
Perspectives
This research represents an early step towards detecting Parkinson’s-like movement patterns using wrist-worn activity monitors in everyday life. To fully realise this potential, we need more large-scale datasets similar to the Parkinson’s Progression Markers Initiative (PPMI)–Verily study. Collecting data from a wide and diverse range of people across the world will be essential to improve these methods, ensuring generalisability, that will support future research into earlier detection and better monitoring of Parkinson’s disease.
Aidan Acquah
University of Oxford
Read the Original
This page is a summary of: Characterising Parkinson's Disease-like Walking Using Wrist-worn Accelerometers, October 2025, ACM (Association for Computing Machinery),
DOI: 10.1145/3714394.3754359.
You can read the full text:
Contributors
The following have contributed to this page
