Fall Detection and Prevention for Memory Care Through Real-time Artificial Intelligence Applied to Video
- Conditions
- Alzheimer's Disease and Related DementiaFall Injury
- Interventions
- Behavioral: SafelyYou Fall Prevention System
- Registration Number
- NCT03685240
- Lead Sponsor
- SafelyYou
- Brief Summary
The purpose of the research is to study a new safety monitoring system developed by SafelyYou to help care for a loved one with dementia. The goal is to provide better support for unwitnessed falls.
The SafelyYou system is based on AI-enabled cameras which detect fall related events and upload video only when these events are detected. The addition of a Human in the Loop (HIL) will alert the facility staff when an event is detected by the system.
- Detailed Description
This process enables staff to know about falls without requiring residents wear a device and to see how falls occur for residents that cannot advocate for themselves while still protecting resident privacy by only uploading video when safety critical events are detected. Seeing how the resident went to the ground (1) prevents the need for emergency room visits when residents intentionally moved to the ground without risk and (2) allows the care team to determine what caused an event like a fall and what changes can be made to reduce risk.
PRELIMINARY EVIDENCE. The proposed study follows a series of pilots. In pilot 1, we showed the technical feasibility of detecting falls from video with 200 falls acted out by healthy subjects. In pilot 2, in a 40-resident facility, we demonstrated the acceptance of privacy-safety tradeoffs and showed a reduction of total facility falls by 80% by providing the system for 10 repeat fallers. In pilot 3, we addressed repeatability of fall reduction in a cohort of 87 residents with ADRD in 11 facilities of three partner networks. In pilot 4 (NIH SBIR Phase I), we demonstrated that falls can be detected reliably in real-time within the partner facilities. We detected 93% of the falls; reduced the time on the ground by 42%; showed that when video was available, the likelihood of EMS visit was reduced by 50%; and reduced total facility falls by 38%.
Recruitment & Eligibility
- Status
- UNKNOWN
- Sex
- All
- Target Recruitment
- 460
Not provided
Not provided
Study & Design
- Study Type
- INTERVENTIONAL
- Study Design
- PARALLEL
- Arm && Interventions
Group Intervention Description Intervention SafelyYou Fall Prevention System AI-enabled camera fall detection with Human-in-the-Loop (HIP) review
- Primary Outcome Measures
Name Time Method Fall rate due to sit to stand transition detection Data will be collected during year 1 and assessed at the end of year 1. Care staff will be alerted as soon as the transition is detected (intervention of the front line staff). This may produce an immediate reduction in falls due to this type of transition.
Enrollment rate Data on enrollment will be recorded during recruitment in year 1 and assessed at the end of year 1 Detection of falls will be performed with blurred video, hence with increased privacy. Expected outcome will be the change in enrollment rate compared to previous feasibility studies (i.e. impacted rate of positive responses to recruitment efforts within facilities).
Fall rate due to gait change detection Data will be collected through year 1 and assessed at the end of year 1. As the system learns to may produce an immediate impact on the fall rate by intervention of the front-line staff when the change is detected.
- Secondary Outcome Measures
Name Time Method
Trial Locations
- Locations (1)
SafelyYou
🇺🇸San Francisco, California, United States