Related Experiment Video
Updated: Jan 18, 2026
05:26
Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights
Published on: October 25, 2024
1.7K
Prediction for prospective falls via gait evaluation using mobile devices for stroke survivors: A markerless motion
Winnie Wt Lam1,2, Wei Tech Ang3, Kenneth Nk Fong1,2
1Department of Rehabilitation Sciences, The Hong Kong Polytechnic University, Hong Kong SAR.
Clinical Rehabilitation
|January 16, 2026
Summary
Gait analysis using mobile devices can predict falls in stroke survivors. Specific gait patterns like low cadence and altered stance/swing times indicate higher fall risk.
Area of Science:
- Rehabilitation Medicine
- Biomechanical Engineering
- Neurology
Background:
- Stroke survivors frequently have lower extremity impairments, increasing fall risk.
- Predicting falls is crucial for rehabilitation and improving quality of life.
Purpose of the Study:
- To investigate prospective fall risk prediction in chronic stroke survivors.
- To analyze gait kinematic markers using markerless motion capture on mobile devices.
Main Methods:
- A prospective cohort study involving 46 chronic stroke survivors and 50 healthy controls.
- Gait parameters were captured using three iPad Pros along a 3-meter walkway.
- Fall history was collected over an 18-month follow-up period.
Main Results:
- 13% of stroke participants experienced falls within 18 months.
- Stroke survivors exhibited slower walking speed, shorter step width, and longer stance time.
- Low cadence, low swing phase, and high stance phase were significant fall predictors.
Conclusions:
- Markerless motion capture on mobile devices effectively predicts prospective fall risk in stroke survivors.
- Gait parameters like cadence and stance/swing times are vital for fall prediction.
- Further research with larger cohorts is recommended to refine prediction models.
