Validation of an IMU-Based Gait Analysis Method for Assessment of Fall Risk Against Traditional Methods.

Area of Science:

• Gerontology
• Biomedical Engineering
• Clinical Biomechanics

Background:

• Falls are a significant health concern for older adults, leading to serious injuries and reduced quality of life.
• Accurate fall risk assessment is crucial for implementing preventative therapies.
• Traditional methods like Gait Speed (GS) and Time Up and Go (TUG) have limitations in identifying individuals prone to falls.

Purpose of the Study:

• To develop and validate a novel method for identifying fallers using wearable sensor technology and a Support Vector Machine (SVM) classifier.
• To compare the accuracy of the proposed SVM method with established fall risk assessment tools.

Main Methods:

• Gait parameters were collected over a 30-minute walk using an Inertial Measurement Unit (IMU) placed on the foot.
• A Support Vector Machine (SVM) classifier was trained using these gait parameters to distinguish between fallers and non-fallers.
• The method was validated on a cohort of 157 participants aged over 70 years.

Main Results:

• Significant differences in stride speed, clearance, angular velocity, acceleration, and step variability were observed between fallers and non-fallers (p<0.05).
• The proposed SVM method achieved a classification accuracy of 79.6%, outperforming the Gait Speed (GS) method (77.0%).
• The SVM approach eliminates the need for specific cut-off values, offering a more adaptable fall risk assessment.

Conclusions:

• The IMU-based SVM classifier is a potentially valuable tool for identifying fallers in older adults.
• This method enables continuous, long-term fall risk monitoring without requiring frequent clinical assessments.
• The findings support the integration of wearable sensor technology into routine geriatric fall prevention strategies.