Related Experiment Video
Updated: Mar 17, 2026
08:05
Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
11.2K
Using Embedded Sensors in Independent Living to Predict Gait Changes and Falls
Lorraine J Phillips1, Chelsea B DeRoche1, Marilyn Rantz1
11 University of Missouri, Columbia, MO, USA.
Western Journal of Nursing Research
|July 30, 2016
Summary
Predicting falls in older adults is possible by analyzing changes in gait speed and stride length using sensor data. Early detection of gait changes can help identify individuals at higher risk of falling.
Area of Science:
- Gerontology
- Biomedical Engineering
- Data Science
Background:
- Falls are a significant risk for older adults in independent living.
- Predicting falls requires continuous monitoring of physiological parameters.
- Gait parameters are sensitive indicators of mobility changes.
Purpose of the Study:
- To investigate the use of Big Data from sensor systems to predict falls.
- To analyze pre-fall changes in gait parameters for fall risk assessment.
- To establish the association between gait changes and future fall events.
Main Methods:
- Utilized 66 terabytes of data collected over 10 years from in-home sensors.
- Analyzed Kinect-recorded gait parameters (speed, stride length) for residents who fell and those who did not.
- Examined associations between 69 fall events and continuous gait data from 2,070 participants over 3-48 months.
Main Results:
- A cumulative change in gait speed over time significantly predicts fall probability (p < .0001).
- A cumulative speed change of 2.54 cm/s increased fall odds by 4.22 times within 3 weeks.
- In-home gait parameters measured by sensors are associated with future falls.
Conclusions:
- Continuous monitoring of in-home gait parameters can predict future falls.
- Sensor-based gait analysis offers a non-invasive method for fall risk assessment.
- This Big Data approach enables proactive interventions to prevent falls in independent living settings.
