Using technology to improve observation rates and drive appropriate admissions

Doylestown Health is using a platform developed by XSOLIS to help nurses stay on top of rapidly changing patient conditions and ensure each patient is properly triaged and cared for.

For all their advantages, EHRs are not as good at detecting changes in patient status that separate those who are observed and those who end up being admitted. Nursing staff are often left to comb and click through data in an endless game of capture.

But at Doylestown Health, AI and algorithmic technology are providing this in a more efficient way.

A suburban Philadelphia healthcare network centered around a 270-bed freestanding hospital is using predictive analytics technology from XSOLIS to improve medical utilization management. In the first six months of use, officials say they have improved observation rates by 20% and observation to patient conversion rates by 37%. And three years later, the initial return on investment of 4.6x has now improved to 7.3x.

Mary Beth Mitchell, MSN, RN, CPHQ, CCM, SSBB, senior executive director of care transformation strategies at Doylestown Health, oversaw this transformation, as well as palliative care and clinical documentation improvement, while leading the case management department. the hospital.

Mary Beth Mitchell, MSN, RN, CPHQ, CCM, SSBB, senior executive director of care transformation strategies at Doylestown Health. Photo courtesy of Doylestown Health.

Mitchell says hospitals would like to be able to admit all patients who present, but payers insist on observation status as a less expensive alternative based on how sick the patient is. This usually takes no more than 48 hours.

“We’re contractually required to review and make sure we have the patient in the right status so that when we bill the insurer, we bill correctly,” she says.

Utilization review (UR) nurses should review every patient who comes in and is placed in a bed, whether they’re in observation status or inpatient status, to make sure they’re in the right status, Mitchell says. These nurses create patient summaries that are sent to the payer, who can then agree or disagree with the status assigned to the patient by the hospital.

Before adopting the XSOLIS technology platform, those nurses, each day, would start at one end of the 270-patient list, either at the payer or on the floor, and move to the other end, one chart at a time. , to look for changes in patient status that rise to the threshold of changing status from observation to hospital or vice versa, Mitchell says.

“I can look at a chart in the morning and the patient seems fit for observation,” she says. “But during the day, many things happen to patients. But [UR nurses] We won’t look at that chart again until the next day because that’s a manual process.”

Some hospitals start with certain diagnoses, but they’re still guessing what they’re going to find on those particular charts, Mitchell says.

The technology platform ‚Äúsets a rigor for us, and through their AI platform [we] are able to use that severity to predict that the patient should be hospitalized or observed,” she says.

The technology continuously combs each chart, looking for events entered by clinicians and notifying UR nurses when those events rise to the level of suggesting a change in status, Mitchell says.

“It’s almost like an assistant, constantly reviewing your lists,” she says.

Since UR nurses typically work a Monday-Friday schedule, the technology is especially useful for capturing changes in patient status late on Fridays, while also alerting those nurses to changes over the weekend when they arrive Monday morning. she says.

Unlike data presentation in EHRs, where less important data is often a distracting presence for UR nurses, the technology emphasizes key measures.

“When I’m going through an EHR, I have to click in and out of each tab,” Mitchell says. “I have to look at every medication the patient is taking. I really don’t want to analyze things that don’t make sense. [The technology] it boils down. For drug lists, we only see what are considered visible drugs.”

The XSOLIS platform presents summaries of recommended status changes to UR nurses, who can pull them down and send them to payers via electronic fax or other means, Mitchell says.

The technology also accounts for traditional Medicare standards for admissions and the fact that most private payers use one of two criteria – Milliman or Interqual.

One drawback is that this process can reduce the UR nurse’s role to being a box checker, Mitchell says. But using the right technology can restore their ability to practice at the top of their license by allowing them to consider multiple diagnoses for a patient.

“Staff nurses like it because they’re using their clinical skills,” she says. “It’s more satisfying to do their job.”

Mitchell says healthcare organizations should thoroughly examine and test the technology platform before deploying it. Different vendors and products offer different paths and goals, making it vital to ensure that a platform can fit seamlessly into a health system’s workflow and meet the needs of administrators and staff.

“We asked for data”, she says. “We asked to talk to other hospitals. Were they actually seeing it make a difference? How are they using it? At the time we made the decision, we felt pretty comfortable that this would help us make it happen that we needed to achieve.”

“It’s really important at this time that hospitals learn to use technology to their advantage,” Mitchell adds. “Anytime you make something by hand, someone is going to miss something. We use technology to help us.”

Scott Mace is a contributing writer for HealthLeaders.

Leave a Comment

Your email address will not be published.