July 9, 2026
JAMDA Highlight
By Barbara Resnick, PhD, CRNP
The purpose of the study, “Real-World Evaluation of a Remote Patient Monitoring Service for Early Detection of Clinical Deterioration in Skilled Nursing Facilities,”1 was to evaluate a remote patient monitoring (RPM) service that relies on contactless cardiorespiratory monitoring in skilled nursing facilities (SNFs) for early detection of patient deterioration.
This is important and relevant for residents based on even just what occurs following hospitalizations. Specifically, approximately 4% of residents admitted to SNFs following hospitalizations die during their initial stay, and hospital readmissions are common, affecting 23-30% of residents.
Programs to evaluate residents for acute changes in condition, such as INTERACT, rely on direct observation of residents by caregivers within the community. Conversely, an early warning system based on objective, continuously collected vital sign data may complement these observation-based assessments by identifying physiological changes that precede overt clinical signs, thereby alerting staff to early deterioration that may not be readily apparent during routine intermittent assessments.
RPM is one way to facilitate this. It utilizes a contactless radar-based device to continuously monitor respiratory rate and heart rate from the bedside. To test the value of this system, a retrospective observational study using real-world clinical service data was done via services delivered by Cicadia Health in California between January 2024 and March 2025. The RPM data included contactless monitoring of respiratory rate and heart rate using a radar-based bedside monitor that captured the data continuously from residents at rest. Nurses then monitored these data daily or twice a day.
Residents were automatically shortlisted for review if their daily average respiratory rate increased by ≥ 2 breaths/min relative to a 3-day rolling baseline. In addition, the system flagged residents whose average respiratory rate over the preceding four hours exceeded their one-day rolling baseline by ≥ 4 breaths/min, to enable recognition of more acute changes. The team assessed whether the deviation likely represented a true physiological change and potential early deterioration, incorporating electronic health record information, including routine vital signs, as supplemental context.
To evaluate the value of this system, a study was conducted in 184 SNFs in the United States over a 14-month period. Residents were monitored using a contactless cardiorespiratory bedside monitor. Of the 7,242 hospital transfers that were unplanned and potentially preventable, 23.5% were directly preceded by an RPM alert (sensitivity), with an average lead time of 63 hours. The overall positive predictive value for remote patient monitoring across all facilities was 35.4%.
RPM alerted on average for 23.9 unique patients per 100 beds per month. An estimated 2.6 hospital transfers were potentially prevented per 100 beds per month across all facilities, while 3.5 transfers were potentially prevented per 100 beds per month in high-adoption facilities. High adoption was considered as sites that had high rates of Escalation Reports (rates > 90%), which were high recognition of a change in condition. This was believed to reflect stronger adoption and adherence to the RPM clinical protocol.
Conclusions and Implications
RPM using continuous, contactless cardiorespiratory monitoring enabled early identification of certain patient deterioration events such as respiratory infections or cardiovascular changes with clinically meaningful sensitivity and lead time, and manageable alert burden, complementing standard care. These findings may guide future design and prospective validation of RPM programs using continuous monitoring technology.
Dr. Resnick is the co-editor-in-chief of JAMDA.
1 Lauteslager T, Oganesyan M, Liu YG, et al. Real-world evaluation of a remote patient monitoring service for early detection of clinical deterioration in skilled nursing facilities. J Am Med Dir Assoc. 2026; 27(5): https://www.sciencedirect.com/science/article/pii/S1525861026000319