In the US, Alzheimer?s disease (AD) is the single most expensive disease, the only disease in the top six for which the number of deaths is increasing. The greatest cost contributors are frequent hospitalizations, where falls are the largest culprit, and frequent need for assistance with the activities of daily living. Fall safety systems show the potential to reduce costs and increase quality of care by reducing the likelihood of emergency events (e.g., detecting falls before a fracture occurs and reducing the number of repeat falls). Unfortunately, current safety devices require wearable or sensor technology not suitable for individuals with dementia and incapable of showing caregivers how falls occur. Our goal is to extend the impacts of SafelyYou Guardian, an online fall detection system with off-the- shelf wall-mounted cameras to automatically detect falls for patients with AD and related dementias (ADRD), enabled by a human-in-the-loop (HIL). The HIL, who can monitor several facilities at a time, confirms the fall detection alerts provided by our artificial intelligence algorithms, and places a call to the facilities, so an intervention can happen within minutes of the fall detection (as opposed to hours after, when the next scheduled visit to the room of the patient happens). Subsequently, an Occupational Therapist (OT) reviews the fall videos to make recommendations on how to re-organize the patient space (intervention), to prevent future falls. We leverage our HIL paradigm, in which our deep learning (a subfield of artificial intelligence) approaches identify and pre-filter falls well enough to leave the last check to a human, who will call the facilities in case of detected safety critical events (falls). The present Fast Track NIH SBIR project leverages the already recruited 100 patients in our partner 11 memory care facilities, recruited through our previous IRB-approved pilots, which we leverage: Pilot 1: We demonstrated the feasibility of the system by collecting proof-of-concept data containing 200 acted falls of healthy subjects and showed accurate fall detection. Pilot 2: We demonstrated acceptance of privacy/safety tradeoffs by patients, family and staff, through the collection of 3 months of video data at WindChime of Marin, a memory care facility from the Integral Senior Living network, in which we identified 4 total hours of fall data. This led to clinical benefits including an 80% fall reduction through the intervention of an Occupational Therapist (OT) to re-organize patient space. Pilot 3: We demonstrated scalability and acceptance by deploying the system in 11 facilities, totaling 100 patients monitored by our system (offline, no HIL intervention). Pilot 4 (ongoing): We demonstrated the ability to perform online (real-time) fall detection, with real-time intervention of the HIL through our partner company Magellan-Solutions, which provides the 24/7 monitoring service for the facilities, and confirmed the decrease of the number of falls, with the 100 patients. In this project, we will develop a comprehensive fall detection and prevention system for memory care called SafelyYou Comprehensive Care. We operate in memory care facilities (which for the purpose of our work includes skilled nursing and assisted living). In Phase I, we seek to establish the technical feasibility and preliminary clinical benefit of sit-to-stand detection, passive gait monitoring, and real- time fall detection on blurred video. We hypothesize that sit-to-stand detection will remove the need for bed alarms; passive gait monitoring will allow identification of high-risk individuals, allowing interventions to be proactively applied; and applying all techniques on blurred video will increase opt-in rate for those with privacy concerns (today 25% opt-in leading to existing facility-wide outcomes). In Phase II, we seek to examine clinical outcomes using a waitlist randomized control study design with sample size of 280 participants. We hypothesize that when compared to standard-of-care (waitlist control group), SafelyYou Comprehensive Care will reduce fall rates, reduce number of severe falls that require ER care and hospitalizations, and be more cost effective.
The goal of this Fast-Track SBIR project is to extend the impact of SafelyYou Guardian, a real- time fall detection system using off-the-shelf wall-mounted cameras to develop a comprehensive fall detection and prevention system for memory care called SafelyYou Comprehensive Care. SafelyYou Guardian is an online fall detection system with off-the-shelf wall-mounted cameras to automatically detect falls for patients with AD and related dementias (ADRD), enabled by a Human-in-the-Loop (HIL). In Phase I, this Fast Track SBIR project will perform a first trial to establish the technical feasibility and preliminary clinical benefit of sit-to- stand detection, passive gait monitoring, and real-time fall detection on blurred video. We want to demonstrate that sit-to-stand detection can remove the need for bed alarms; that passive gait monitoring will enable identification of high-risk individuals, allowing interventions to be proactively applied; and that applying all techniques on blurred video will increase opt-in rate for those with privacy concerns (today 25% opt-in leading to existing facility-wide outcomes). In Phase II, through a 280-patient trial, we will examine clinical outcomes of the system using a waitlist randomized control study. We want to demonstrate that when compared to standard- of-care (waitlist control group), SafelyYou Comprehensive Care will reduce fall rates, reduce number of severe falls that require ER care and hospitalizations, and be more cost effective. The project leverages a 100-patient population in our 11 partner facilities (assisted living and skill nursing), recruited through our previous IRB-approved pilots. Past results demonstrated an 80% decrease in the fall rate in a single facility over the course of a three months period.
