Detection of falls using accelerometers and mobile phone technology

Area of Science:

• Biomedical Engineering
• Gerontology
• Wearable Technology

Background:

• Falls are a significant risk for older adults, leading to injury and reduced independence.
• Existing fall detection systems often have limitations in terms of accuracy, cost, or user-friendliness.
• Mobile phone technology offers a ubiquitous and potentially cost-effective platform for fall detection.

Purpose of the Study:

• To evaluate the sensitivity and specificity of mobile phone technology for detecting simulated falls.
• To compare the performance of mobile phone-based fall detection with a dedicated external accelerometer.

Main Methods:

• An experimental study involving 18 healthy adults simulating various falls and daily activities.
• Motion signals were captured using a mobile phone and a waist-worn accelerometer.
• Data analysis included Bland-Altman analysis to assess agreement between devices.

Main Results:

• The mobile phone achieved a sensitivity of 0.77 and a specificity of 0.81.
• The waist-worn accelerometer demonstrated higher performance with 0.96 sensitivity and 0.82 specificity.
• Bland-Altman analysis indicated good agreement between the mobile phone and the external accelerometer.

Conclusions:

• Mobile phone technology presents a feasible and attractive solution for fall detection in older adults, particularly those living alone.
• Optimizing fall detection may involve using a waist-worn accelerometer that wirelessly transmits data to a mobile phone.
• This approach could enhance safety and independence for elderly individuals at risk of falls.