A multifactorial fall risk assessment system for older people utilizing a low-cost, markerless Microsoft Kinect

Area of Science:

• Gerontology
• Biomedical Engineering
• Rehabilitation Science

Background:

• Falls are a significant health issue for older adults, leading to injuries and reduced quality of life.
• Accurate assessment of multifactorial fall risk is crucial for effective prevention strategies.

Purpose of the Study:

• To develop and validate a low-cost, markerless fall risk assessment system for older adults using Microsoft Kinect.
• To identify key fall risk factors and provide personalized intervention targets.

Main Methods:

• A Kinect-based test battery was designed to assess major fall risk factors.
• 102 older participants were recruited, and their fall risks were assessed over a 6-month period.
• A random forest classification model was developed to predict fall risk.

Main Results:

• The high fall risk group demonstrated significantly poorer performance on the Kinect-based tests.
• The developed classification model achieved an average accuracy of 84.7% in identifying fall risk.
• Individual performance data was visualized against a normative database for targeted interventions.

Conclusions:

• The Kinect-based system effectively screens older adults at high risk of falls with high accuracy.
• The system can identify specific fall risk factors, enabling tailored interventions.
• This technology offers a low-cost, accessible solution for fall prevention in older populations.