Enhanced Detection and Segmentation of Sit Phases in Patients with Parkinson’s Disease Using a Single SmartWatch and Random Forest Algorithms
This study demonstrates that a random forest algorithm can accurately detect and segment <i>Sit</i> phases in people with PD using data from a single ankle-worn SmartWatch. The algorithm's performance was comparable to manual segmentation, while substantially reducing the time and effort required. These findings represent a meaningful step forward in enabling efficient, long-term, and home-based monitoring of mobility and symptom progression in people with PD.
Authors
- Christian Duval (ORCID: https://orcid.org/0000-0001-5906-1041)
- Karina Lebel (ORCID: https://orcid.org/0000-0002-5409-7130)
- Jean‐François Daneault (ORCID: https://orcid.org/0000-0002-8530-1827)
- Camille Martin
- Patrick Boissy (ORCID: https://orcid.org/0000-0001-6582-4519)
- Étienne Goubault (ORCID: https://orcid.org/0000-0002-3825-4001)
Institutions
- Rutgers, The State University of New Jersey (US)
- Université de Sherbrooke (CA)
- Institut de recherche Robert-Sauvé en santé et en sécurité du travail (CA)
- Université du Québec à Montréal (CA)
- Centre Intégré Universitaire de Santé et de Services Sociaux du Saguenay–Lac-Saint-Jean (CA)
- Institut Universitaire de Gériatrie de Montréal (CA)
- Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal (CA)
Publication Details
- Journal
- Sensors
- Published
- 2025-10-03
- DOI
- https://doi.org/10.3390/s25196104
- Primary Topic
- Parkinson's Disease Mechanisms and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Canada Research Chairs
- Canadian Institutes of Health Research