Automatic Assessment of a Rollator-User's Condition During Rehabilitation Using the i-Walker Platform

Area of Science:

• Rehabilitation Medicine
• Robotics
• Biomedical Engineering

Background:

• Traditional patient condition assessments in rehabilitation rely on time-consuming clinical scales requiring patient or clinician input.
• Existing efforts to streamline assessments often focus on reduced feature sets for specific populations, still necessitating therapist intervention and patient fatigue.
• Continuous monitoring of patient progress during rehabilitation is crucial but challenging with conventional methods.

Purpose of the Study:

• To develop an automated system for assessing patient mobility using a robotic rollator.
• To predict the Tinetti mobility scale in real-time by extracting spatiotemporal gait parameters from sensor data.
• To provide a non-intrusive, continuous, and objective method for monitoring patient progress during rehabilitation.

Main Methods:

• Utilized onboard sensors of a robotic rollator to extract spatiotemporal gait parameters.
• Derived gait parameters from user forces on rollator handles and the rollator's odometry.
• Developed a predictive model to estimate the Tinetti mobility scale from the extracted gait parameters.
• Validated the approach with 19 volunteers with diverse physical and neurological disabilities across two clinical sites.

Main Results:

• The proposed system accurately predicted Tinetti mobility scores on the fly, demonstrating a small root mean squared prediction error.
• The automated assessment was achieved without requiring therapist intervention.
• The system successfully extracted relevant gait parameters from rollator sensor data.

Conclusions:

• This novel approach enables automatic, on-demand assessment of the Tinetti mobility scale using robotic rollator sensors.
• The method offers a valuable tool for continuous patient progress evaluation in everyday walking conditions.
• It has the potential to significantly improve the efficiency and objectivity of rehabilitation monitoring.