A Systematic Review of Wearable Sensor-Based Technologies for Fall Risk Assessment in Older Adults

Area of Science:

• Gerontology
• Biomedical Engineering
• Data Science

Background:

• Falls are a leading cause of injury and death in older adults (65+).
• Predicting fall risk enables timely interventions and prevention strategies.
• Wearable sensors and big data analysis offer promising tools for fall risk assessment.

Purpose of the Study:

• To systematically review wearable sensor-based technologies for fall risk assessment in community-dwelling older adults.
• To evaluate the accuracy and effectiveness of current approaches.
• To identify factors influencing fall risk prediction accuracy.

Main Methods:

• Systematic literature review of 614 identified research articles.
• Inclusion of 25 relevant studies for comprehensive comparison.
• Evaluation of approaches based on sensor characteristics, features, and data processing.

Main Results:

• Wearable sensor-based approaches provide accurate and effective fall risk assessment.
• Key factors influencing prediction accuracy include sensor location, type, utilized features, and data modeling techniques.
• Features derived from raw sensor signals are crucial for predictive model development.

Conclusions:

• Wearable sensors are a viable tool for assessing fall risk in older adults.
• Further research is required to identify clinically interpretable features.
• Development of a generalized framework integrating sensor technologies and data modeling is needed for improved fall risk assessment.