ParCuR—A Novel AI-Enabled Gait Cueing Wearable for Patients with Parkinson’s Disease
OPEN ACCESS
Author / Producer
Date
2025-11-02
Publication Type
Journal Article
ETH Bibliography
yes
OPEN ACCESS
Data
Rights / License
Abstract
Freezing of gait (FoG) is a common motor symptom in advanced Parkinson’s disease, leading to falls, disability, and reduced quality of life. Although cueing systems using visual or auditory stimuli can help patients resume walking, existing solutions are often expensive, uncomfortable, and conspicuous. ParCuR (Parkinson Cueing and Rehabilitation) is a compact, ankle-worn wearable integrating an inertial sensor, haptic stimulator, and AI-based software. It was developed to detect FoG episodes in real time and provides automatic sensory cues to assist patients with Parkinson’s Disease (PwP). A classifier was trained for FoG detection using the DAPHNet dataset, comparing patient-specific and patient-independent models. While a small-scale trial with PwP assessed usability and reliability. ParCuR is watch-sized (35 × 41 mm), discreet, and comfortable for daily use. The online detection algorithm triggers stimulation within 0.7 s of episode onset and achieves 94.9% sensitivity and 91.3% specificity using only 14 frequency-based features. Preliminary trials confirmed device feasibility and guided design refinements. This low-cost, wearable solution supports personalized, real-time FoG detection and responsive cueing, improving patient mobility while minimizing discomfort and continuous stimulation habituation.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
Volume
25 (22)
Pages / Article No.
7077
Publisher
MDPI
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
assistive cueing; freezing of gait; machine learning; Parkinson’s disease; somatosensory stimulation; wearable electronics