A Mixed Reality Approach to Verify the Feasibility of Monitoring Parkinson's Disease Gait Impairments - 17/06/26
, Helena R. Gonçalves a , Ana Margarida Rodrigues c, d, Cristina P. Santos a, b, ⁎⁎ Abstract |
Background |
The application of virtual dimensions as mixed reality (MR) integrated into smart glasses brings a new concept for Parkinson's disease (PD) gait monitoring, which immerses patients in interactive, personalized virtual environments closer to everyday life. This study introduces a novel MR approach to monitor gait impairments in PD.
Methods |
Two virtual environments, customized to patients' daily motor challenges, were developed for the MR smart glasses HoloLens. A new cross-sectional study was conducted with ten PD patients to validate the proposed solution.
Results |
It was verified that the proposed MR-based solution could immerse patients in daily environments and evoke gait-associated impairments ( ρ -value≤0.018), being observed significant gait alterations in patients' gait cadence, step time, stance/swing phase, and freezing of gait episodes. Also, patients showed great enthusiasm for using the implemented MR-based technologies.
Conclusions |
Overall, this research introduced the MR-based approach as a complementary tool for motor monitoring of PD-related gait disabilities.
Le texte complet de cet article est disponible en PDF.Graphical abstract |
Highlights |
• | Mixed reality introduces a solution for feasible Parkinson's disease gait monitoring. |
• | Proposed virtual scenarios aimed to mimic and induce daily gait challenges. |
• | Customized scenarios with home virtual objects were included, such as a doorway. |
• | The new solution was combined with a motion analysis system to measure patients' gait. |
• | Patients showed gait disturbances when immersed in the employed virtual scenarios. |
Keywords : Gait disorders, Gait analysis, Mixed reality, Motion tracking, Parkinson's disease
Plan
Vol 47 - N° 4
Article 100949- août 2026 Retour au numéro
Article précédent
- Stratified Domain Generalized Motor Imagery Electroencephalogram Classification via Deep Mixture Distribution Representation Learning
- Tian-jian Luo, Xiaochen Zhang
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?