Remote Patient Monitoring May Predict 30-Day Readmission Risk

A remote patient monitoring tool that assesses patient ambulation and mobility could be useful for predicting risk for 30-day hospital readmissions, according to new data published in JAMA Network Open.

Overall, a remote patient monitoring tool helped predict 30-day hospital readmissions, discharge location (patient home versus a rehabilitation center), and length of stay at over 80 percent accuracy, researchers from Johns Hopkins University School of Medicine found.

Understanding patient mobility has long been integral to predicting patient risk. Having a patient get up and walk around reduces the risk of functional decline and increases the odds that a patient will get better quicker.

But understanding patient mobility is no simple task, with previous measures of patient mobility falling short.

Mobility questionnaires, for example, may be good at understanding how a patient perceives her own mobility at a given moment, but they are often too subjective and difficult to quantify. Timed walk tests can also provide a good look into how fast a patient can walk and for how long, but these tests are labor intensive and aren’t always practical to deploy on all patients.

Wearable accelerometers have begun to show some promise, the researchers said. However, current strategies rely too heavily on step count, while there may be other metrics for patient mobility that are more effective for assessing patient risk.

This latest study found that remote patient monitoring tools may be better equipped to fully understand the course of patient mobility and recovery.

“Although daily step counts enable continuous monitoring, additional parameters, such as ambulation speed and the change in distance and speed during recovery, could refine assessment of patient mobility and improve prediction models,” the researchers explained.

The team analyzed the approach on 100 cardiac surgery patients in a progressive care unit (PCU) at Johns Hopkins Hospital. Using the real-time location system already deployed to track hospital workers, the team introduced patients to the Activity and Mobility Program. All movement or ambulation was voluntary in the program, although clinicians did recommend patients get up and walk around at least three times each day.

The program yielded about 28 percent compliance on the first day, with that compliance waning in subsequent days. The researchers posited that this was because patients who walked around more were able to be discharged sooner. Generally speaking, outcomes were better for patients who walked around at least once each day.

The system was deemed largely successful, the researchers reported, with them managing to identify 19 parameters that could successfully inform a risk assessment. Those parameters related to patient walking distance, gait speed, frequency of walking, and changes in certain measures after the patient continued to take multiple walks each day.

Understanding these factors led to accurate prediction of certain clinical quality measures. Researchers could predict 30-day hospital readmissions with nearly 87 percent sensitivity and about 88 percent specificity. Numbers were similar predicting discharge location and length of stay in the PCU, as measured by full days in the PCU.

“The findings of this study suggest that a real-time location system, already installed in the hospital for tracking the locations of staff and equipment, can be used to monitor voluntary out-of-room ambulations in a cardiac surgery PCU,” the researchers said.

These findings are important, as healthcare organizations weigh the differences between wearable and remote patient monitoring systems. In this case, the remote patient monitoring tool yielded better or more actionable data.

“Remote tracking and wearable accelerometers both provide measures of mobility but have some key differences: remote tracking can distinguish out-of-room ambulation events and can provide information on patient speed, although the resolution (approximately 6 m [20 ft] in this study) is larger than a single step,” the researchers said. “Furthermore, remote tracking is easy to implement and is scalable.”

There are benefits beyond assessing patient risk, the team noted. Understanding a patient’s movement patterns will help providers with goal-setting and shared decision-making during care encounters.

“Because data can be collected and analyzed in real-time, a patient’s ambulation history could be updated and displayed in the electronic medical record or on a patient’s smartphone in real time,” the team concluded. “The ability to track and monitor ambulation history could enable goal setting and identification of at-risk patients based on real-time prediction models.”