The study was designed to assess facility-level and resident-level outcomes for communities that utilized CarePredict’s AI-powered digital health platform, wearable device, and real-time location system. Retrospective analysis of anonymized resident data was collected from six assisted living communities in three states over 24 months. A study flow chart is provided in Figure 1. Data were analyzed for 472 residents in year 1 and 490 residents in year 2. The participants agreed to the collection of data presented in this publication by signing the terms and conditions for use, and data were anonymized for statistical analysis. Due to the nonexperimental, retrospective, de-identified, and anonymized study design, no ethical approval was needed.

All de-identified data analyzed in this study were collected and reported by facility staff using each community’s online electronic healthcare software platform. The same software was used in all communities. CarePredict employees were provided access to the extracted anonymized data for scientific evaluation. No identifiable resident information has been or will be shared.

The CarePredict system consists of a wrist-worn wearable device, context beacons for room location, and a cloud-based AI-powered platform (Figure 2A-B). The wearable is worn on a user’s dominant arm, measures changes in their wrist kinematics, and autonomously quantifies gestures and activities of daily living such as eating, bathing, walking, bathroom visits, and sleep duration (Figure 2A-B). The wearable uses wireless communication to transfer data to the cloud over an encrypted connection and supports two-way audio that allows the resident to communicate to staff using mobile apps on iOS and Android devices. The wearable supports radio-frequency identification (RFID) protocols to allow integration with electronic door access systems enabling the resident to use their wearable for safe, secure, and convenient access to their apartment. The wearable measures 50 × 33 × 17.7 mm, weighs 40 g, and includes a six-axis accelerometer, a microprocessor, RFID, Bluetooth 4, Wi-Fi 802.11 b/g/n, and 1 Gb of onboard storage capable of storing 6 days of data. The wearable has a swappable battery, so the device does not need to be removed for charging. The battery is a 380mAH Li-ion 10.6g Polymer battery with 50 to 110 hours of battery life. The wearable has an operational temperature range of –20°C to +55°C, water-resistant to IP67, and the following certifications: FCC, CE, TELEC, RoHS, REACH, WEEE, Bluetooth.

The real-time location or context beacons enhance the accuracy of the wearable’s gesture recognition engine by bringing in room type data and permitting accurate room-level location tracking in an indoor setting [47]. Each beacon measures 52.1 × 52.1 × 28.0 mm, weighs 78 g, and uses Lithium CR123A batteries. The beacons utilize a proprietary line-of-sight technology to allow for real-time location monitoring on multi-floor levels with room-level accuracy and no bleed-throughs [46-48]. The CarePredict product is used in assisted living communities to provide five key functions (Figure 2C).

Facility staff at each community collected and reported the following data daily: occupancy, headcount, number of vacant units, unit move-ins and move-outs, staff service counts, duration, and type (such as dressing, bathing, grooming, transferring, and toileting), length of stay, fall incidents, emergency department and/or hospital admissions/discharges. Resident incident reports were utilized to document hospitalizations and fall incidents. The headcount, hospitalization, and fall incident numbers were used to compute both a hospitalization and fall rate. The hospitalization rate was defined as the number of hospitalization incidents per headcount in the facility, and the fall rate as the number of falls recorded per headcount per year. The average “baseline” rates for each community were measured from the first quarter of the study; the average “end of study” measurement was collected in the 8^th quarter of the study. The average rate of change between these periods was computed between these two periods. Staff response times were automatically measured in this study using the CarePredict system. Residents trigger an alert and call for staff assistance by depressing the button on their wearable, and a staff member acknowledges the alert using the CarePredict software. We analyzed both the duration of time the staff required to acknowledge an alert and then to reach the resident. The residents’ length of stay in each community was also measured. Length of stay is defined as the number of months a resident resides in a given community. The average, geometric, and median length of stay were analyzed, and detailed descriptions are provided in the supplementary materials section (Multimedia Appendix 2).

Descriptive statistics, including means, standard deviations, and distributions, were provided for all study variables and compared across groups (+CP vs. –CP communities). Study variables were compared to baseline measurements for each group. A two-sample, two-tailed, t-test was applied for metric variables to test for significant differences between groups. A P value <.05 was considered statistically significant.

Informed consent was obtained from the communities and participants included in the study.

The resident demographic data (age, sex) and facility staff service time were assessed. The average resident ages were 87.3 years (SD 1.2 years) for the +CP communities and 88.1 years (SD 1.6 years) for the –CP communities (Table 1). The percent of female residents was 66.2% (SD 3.8) in the +CP and 69.2% (SD 8.2) in the –CP communities. The +CP and -CP communities exhibited no statistical difference in resident age (P=.64) and gender (P=.63). The average staff service time (hours per headcount per month) for each +CP and -CP community is shown in Table 2. The average staff service hours per resident per month were statistically similar for the +CP and –CP communities (P=.94).

In this pilot study, we assessed whether the use of a wearable device and AI-powered digital health platform could provide improved health outcomes for older adults in an assisted living community. We found that the communities with CarePredict (+CP) exhibited a 40% lower hospitalization rate, 69% lower fall rate, and 67% greater length of residence stay compared to control communities (–CP). Overall, the use of CarePredict technology in assisted living communities appears to contribute to improved outcomes and shows promise as an effective tool to provide a higher quality of care.

There are several possible explanations for these findings. First, since both the residents and staff wear the CarePredict device, it functions as both an effective communication platform and resident alert system allowing for the coordination of prompt care. The system also provides robust staff performance metrics, which can be used to encourage continually improving staff response times to residents who need aid. The alert system prevents minor situations from escalating to emergent situations requiring hospitalization. Residents desire prompt, attentive care in assisted living communities, and the CarePredict system helped contribute to the facility staff acknowledging alerts 40% faster and reach residents in response to those alerts in 37% less time [54,55]. The CarePredict system appears to provide community staff with an increased awareness of residents’ needs and allows them to provide more prompt care, and thus may directly contribute to the improved outcomes observed.

Second, the system provides the community staff with detailed information regarding each resident’s activities and behavior. Changes in an adult’s activity and behavior are well-characterized to precede health declines; therefore, staff can use this information to quickly identify older adults that are at an increased probability for a health decline and intervene much earlier [49,50]. For example, such information can be used to identify and flag older adults that show the earliest sign of a urinary tract infection (UTI). In particular, the CarePredict system identifies a new or marked increase in urination urgency or frequency, both well-established indicators for a symptomatic UTI [49-51]. These older adults can then be assessed, and if diagnosed with a UTI, can be provided antibiotics to treat the UTI before it may result in hospitalization [51]. This increased visibility provided by the system may also have contributed to the observed lower hospitalization rates and increased LOS.

Fall rates also appear to be positively impacted by the use of the CarePredict solution. The data shows that +CP communities exhibited a 69% lower fall rate than the –CP communities. Fall rates are known to increase steadily with age [20], and the rates vary considerably for older people in different settings. Lower fall rates (0.3-1.6 per person per year) are typically reported in independent living communities with relatively healthy adults (age ≥65 years), whereas higher fall rates (0.6-4.05 per person per year, mean 1.7) are observed in assisted living, memory care, and long-term care institutions [24,56,57]. In a recent systematic review on falls, the mean rate of falls was found to vary between 1.07 falls per person per year for a low-risk population, and up to 3.5 falls per person per year for a high-risk population [23]. The CarePredict solution appears to contribute to an observed fall rate (0.97) that is lower than average incident fall rates reported in the literature [23,27].

By identifying older adults whose activity and behavior pattern indicates decreasing mobility, staff can take pre-emptive action to mitigate senior fall risk, UTIs, or other incidents that may have required hospitalization. Reducing hospital admissions also helps to maintain census, reduce resident turnover, and increase resident LOS in the community. The data shows that +CP communities exhibited a nearly 40% lower average hospitalization rate than the –CP communities (33.8% versus 73.6%). Several senior living outcomes studies by Zimmerman et al and Hedrick et al reported average annual hospitalization rates of 51% and 40%, respectively [29,58]. The +CP communities exhibited hospitalization rates that were 18% and 7% lower than the averages reported by Zimmerman and Hedrick et al, respectively [29,58].

There are several limitations to this pilot study. First, the study was conducted at six assisted living communities with less than 500 total residents. This study needs to be replicated and results confirmed using a larger sample size of individuals. Second, the –CP communities did not use an alert response technology system in this study, and thus staff response times could not be collected and analyzed for the –CP communities. As a result, the impact that the CarePredict technology had on staff response times was only measured and analyzed for the +CP communities. We, therefore, could not compare the staff response times between the +CP and –CP communities, and rather only measured the response times for the +CP communities at baseline and end of the study. Third, staff in the +CP communities used the CarePredict technology system for multiple purposes: to acknowledge and respond to resident alerts, to communicate to residents and other staff members, and to autonomously collect resident activity and behavior data. Since Carepredict served multiple functions, it is difficult to attribute which of these system capabilities and data sets directly contributed to the improved outcomes.

To better understand the mechanisms by which these improvements were provided, in future studies, we plan to include a control group of communities that only utilize the CarePredict system for alerting and communication purposes. The added value provided by the predictive analytics feature will then be easier to assess and quantify directly. These results will also allow us to assess the impact that the proactive, actionable data generated by the CarePredict system will have on identifying and preventing high-risk residents from being hospitalized. Finally, although the six communities assessed in this study had comparable resident demographics (age, gender) and staff service hours per resident, other factors like residents’ hospital and fall history, and quality of care indicators may also have contributed to the differences observed in the measured outcomes.

The leading cause of residents moving out of assisted living communities is unplanned hospitalization [18]. Hospitalizations are a strong predictor of nursing home admission and are associated with health and disability declines, lower quality of life, and greater health care costs [29,58]. The findings of this study highlight that the CarePredict AI-powered digital health platform, wearable device, and location system shows promise to support caregiving staff in identifying older adults that have an increased probability for a health decline, and thereby give staff time to provide a proactive intervention and thus reduce the number of hospitalizations. AI-powered platforms and wearable devices show promise as assistive tools for senior living organizations to deliver improved outcomes. In future studies, we plan to explore the variables and specific mechanisms by which this technology can directly contribute to each performance metric and outcome.