Falling, Fall Injury, Fall Patients, Lower Limb Amputation Knee, Parkinson Disease, Stroke
Conditions
Brief summary
The purpose of this study is to evaluate the feasibility and efficacy of a smart airbag system that detects and mitigates fall-related impact in individuals with high fall risk.
Detailed description
The purpose of this study is to evaluate the feasibility and efficacy of a smart airbag system that detects and mitigates fall-related impact in individuals with high fall risk. The specific aims of this study are: 1. To evaluate and optimize pre-fall detection algorithms and the usability of the smart airbag system for fall mitigation in individuals with high fall risk. 2. To evaluate the efficacy of the smart airbag system in mitigating real-world falls and its effect on community mobility in individuals with high fall risk. The investigators hypothesize that a soft, smart airbag system that uses advanced machine learning algorithms can accurately detect and mitigate falls, deploying appropriately to reduce hip fractures due to falls. The investigators also expect that wearing this device will decrease fear of falling and thus increase community mobility and social interaction.
Interventions
DEVICEAirbag Belt Fall Protection System
Both versions of Airbags features different number of IMU sensors. Participant's will be randomly assigned one of the two versions. The algorithms developed in this project will help the researcher to identify the optimal performance (sensitivity and specificity values for detecting falls). Based on this information the research team will be able to choose a version for home/community deployment portion of the study. Based on the performance of the airbags in detecting true positives (falls) and true negatives (non-falls) accurately one of the airbags will be used in community deployment phase of the study.
Sponsors
Shirley Ryan AbilityLab
Study design
Allocation
NA
Intervention model
SINGLE_GROUP
Primary purpose
DEVICE_FEASIBILITY
Masking
NONE
Intervention model description
This device feasibility enrollment number of 200 is a larger sample in order to create a machine learning algorithm
Eligibility
Sex/Gender
ALL
Age
18 Years to 85 Years
Healthy volunteers
Yes
Inclusion criteria
INCLUSION AND
Exclusion criteria
All potential subjects will be evaluated by research staff in order to match them to the inclusion and
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Pre-fall classification performance | 1 year | Derivation(s) from a confusion matrix |
Countries
United States
Outcome results
None listed