Wearable technology and ECG processing for fall risk assessment, prevention and detection.

Area of Science:

• Gerontology
• Biomedical Engineering
• Cardiology

Background:

• Falls are a major cause of injury and mortality in older adults.
• Cardiovascular disorders, including autonomic dysfunction and postural hypotension, increase fall risk.
• Heart Rate Variability (HRV) derived from electrocardiograph (ECG) can assess autonomic dysfunction linked to falls.

Purpose of the Study:

• To evaluate the utility of wearable ECG monitoring for fall risk assessment.
• To develop methods for preventing falls related to orthostatic hypotension.
• To create a system for detecting falls in real-time.

Main Methods:

• Utilized statistical and data-mining techniques to build classification and regression models.
• Employed cross-validation for model validation.
• Analyzed HRV features from ECG data for fall prediction and detection.

Main Results:

• A classifier identified future fallers among hypertensive patients with 72% accuracy.
• A regression model predicted falls due to orthostatic hypotension with 80% accuracy.
• A classifier detected simulated falls using ECG with 77.3% accuracy.

Conclusions:

• ECG monitoring demonstrates satisfactory performance for fall risk assessment, prevention, and detection.
• This technology is a viable alternative to existing fall prevention systems.
• ECG is widely recommended for other conditions and is well-accepted by seniors.