Background Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) can spread rapidly in nursing homes and long-term care (LTC) facilities. Symptoms-based screening and manual contact tracing have limitations that render them ineffective for containing the viral spread in LTC facilities. Symptoms-based screening alone cannot identify asymptomatic people who are infected, and the viral spread is too fast in confined living quarters to be contained by slow manual contact tracing processes. Objective We describe the development of a digital contact tracing system that LTC facilities can use to rapidly identify and contain asymptomatic and symptomatic SARS-CoV-2 infected contacts. A compartmental model was also developed to simulate disease transmission dynamics and to assess system performance versus conventional methods. Methods We developed a compartmental model parameterized specifically to assess the coronavirus disease (COVID-19) transmission in LTC facilities. The model was used to quantify the impact of asymptomatic transmission and to assess the performance of several intervention groups to control outbreaks: no intervention, symptom mapping, polymerase chain reaction testing, and manual and digital contact tracing. Results Our digital contact tracing system allows users to rapidly identify and then isolate close contacts, store and track infection data in a respiratory line listing tool, and identify contaminated rooms. Our simulation results indicate that the speed and efficiency of digital contact tracing contributed to superior control performance, yielding up to 52% fewer cases than conventional methods. Conclusions Digital contact tracing systems show promise as an effective tool to control COVID-19 outbreaks in LTC facilities. As facilities prepare to relax restrictions and reopen to outside visitors, such tools will allow them to do so in a surgical, cost-effective manner that controls outbreaks while safely giving residents back the life they once had before this pandemic hit.

No abstract

Background Wearables and artificial intelligence (AI)–powered digital health platforms that utilize machine learning algorithms can autonomously measure a senior’s change in activity and behavior and may be useful tools for proactive interventions that target modifiable risk factors. Objective The goal of this study was to analyze how a wearable device and AI-powered digital health platform could provide improved health outcomes for older adults in assisted living communities. Methods Data from 490 residents from six assisted living communities were analyzed retrospectively over 24 months. The intervention group (+CP) consisted of 3 communities that utilized CarePredict (n=256), and the control group (–CP) consisted of 3 communities (n=234) that did not utilize CarePredict. The following outcomes were measured and compared to baseline: hospitalization rate, fall rate, length of stay (LOS), and staff response time. Results The residents of the +CP and –CP communities exhibit no statistical difference in age (P=.64), sex (P=.63), and staff service hours per resident (P=.94). The data show that the +CP communities exhibited a 39% lower hospitalization rate (P=.02), a 69% lower fall rate (P=.01), and a 67% greater length of stay (P=.03) than the –CP communities. The staff alert acknowledgment and reach resident times also improved in the +CP communities by 37% (P=.02) and 40% (P=.02), respectively. Conclusions The AI-powered digital health platform provides the community staff with actionable information regarding each resident’s activities and behavior, which can be used to identify older adults that are at an increased risk for a health decline. Staff can use this data to intervene much earlier, protecting seniors from conditions that left untreated could result in hospitalization. In summary, the use of wearables and AI-powered digital health platform can contribute to improved health outcomes for seniors in assisted living communities. The accuracy of the system will be further validated in a larger trial.

BACKGROUND Severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2) can spread rapidly in nursing homes and long term care (LTC) facilities. Symptoms-based screening and manual contact tracing have limitations that render them ineffective for containing viral spread in LTC facilities: (i) symptoms-based screening alone cannot identify asymptomatic infected persons; (ii) viral spread is too fast in confined living quarters to be contained by slow manual contact tracing processes. OBJECTIVE We describe the development and implementation of a digital contact tracing system that LTC facilities can use to rapidly identify, isolate and then test asymptomatic and symptomatic infected contacts. Computer simulation models were also developed to assess the performance of the system versus conventional containment methods. METHODS We developed a stochastic transmission model parameterized specifically for COVID-19 in LTC facilities. Using various scenarios we used the model to quantify the effectiveness of several intervention groups to control outbreaks: no intervention, symptom mapping, PCR testing, manual contact tracing, and digital contact tracing. RESULTS Our digital contact tracing system allows users to rapidly identify and then isolate close contacts, to store and track infection data in a respiratory line listing tool, and identify contaminated rooms. Our simulation results suggest that digital contact tracing allow for rapid and effective identification and containment of potentially infected contacts. CONCLUSIONS Digital contact tracing systems show promise as effective tool to control COVID-19 outbreaks. As facilities prepare to relax restrictions and re-open to outside visitors, such tools will allow them to do so in a surgical, cost-effective manner that both controls outbreaks while also safely giving residents back the life they once had before this pandemic hit. CLINICALTRIAL Not applicable

BACKGROUND Wearables and AI-powered digital health platforms that utilize machine learning algorithms can autonomously measure a senior’s change in activity and behavior and may be useful tools for proactive interventions that target modifiable risk factors. OBJECTIVE The objective of this study was to analyze how an AI-powered digital health platform, wearable device, and location system could provide improved health outcomes for residents living in assisted living communities. METHODS A total of 490 older adults at six AL communities were observed over a 24-month period. Numerous facility and resident level outcomes were measured for the intervention and control group, including staff response time, hospitalization rate, fall rate, and length of stay (LOS). The intervention group consisted of 3 communities that utilized CarePredict (n=256) and the control group that consisted of 3 communities (n=234) that did not utilize CarePredict. RESULTS Results: The data shows that CarePredict installed communities (+CP) exhibited a 40% lower hospitalization rate, 64% lower fall rate, and 67% greater length of stay than control communities (-CP). The +CP communities exhibit a 40% improvement in staff take alert time and 37% faster reach resident time. CONCLUSIONS The AI-powered digital health platform provides the community staff with actionable information regarding each resident’s activities and behavior. Staff can use this information to identify seniors at increased probability for a health decline, intervene much earlier, and take pre-emptive action to protect the senior against falls, UTIs, and other conditions that left untreated could result in hospitalization. In summary, the use of this system in AL communities can contribute to faster staff response times, reduced hospitalizations and falls, and increased length of stay. CLINICALTRIAL Informed consent was obtained from all of the communities and participants included in the study.