Hospitalized patients don’t always decline with warning. Vital signs shift, lab values drift — and by the time it’s obvious to the naked eye, the window to intervene has narrowed.
That’s the gap RWJBarnabas Health and Rutgers Robert Wood Johnson Medical School set out to close with an AI-enabled early warning system, called the Epic Deterioration Index.
The tool continuously scans information already sitting in a patient’s electronic health record and recalculates a risk score every 15 minutes. Once a patient crosses into the highest-risk category, the system automatically alerts a hospital’s rapid response team.
According to to new reresearch, it’s working.
A study, published in NEJM AI, a journal from the New England Journal of Medicine group, evaluated outcomes among 23,132 high-risk patients across 11 RWJBarnabas Health hospitals. After the system was implemented, deaths among those high-risk patients fell from 23.1% to 18.6% — an 18% reduction in the risk-adjusted odds of in-hospital death.
Rapid response team activations among high-risk patients rose from 25.3% of hospital stays to 37.5% once the system went live. Notably, transfers to intensive care units didn’t rise alongside that jump, even as mortality dropped.
***
AI isn’t always an overnight sensation. In fact, getting to this point at RWJBH took years of groundwork.
RWJBH and Rutgers first piloted the systemwide approach at Robert Wood Johnson University Hospital, the system’s academic medical center, refining how alerts were triggered and training clinicians before expanding to the health system’s other 10 hospitals.
Thomas Nahass, VP of Health Informatics and an intensive care physician at RWJBarnabas Health, and assistant professor of medicine at Rutgers Robert Wood Johnson Medical School, said the goal was to identify patients earlier.
“Before they reached a point where intervention becomes much more difficult,” he said. “The deterioration index gives us an earlier point in time. If we can get a critical care eye on the patient sooner, we can change the course of their outcome.”
Andy Anderson, chief medical and quality officer at RWJBarnabas Health and a co-author on the study, said the findings show what’s possible when technology and clinical teams work together.
“Every minute matters when a patient’s condition begins to worsen,” he said. “This study demonstrates how AI-enabled tools, when paired with experienced clinical teams, can help us identify patients at risk sooner and deliver the right care at the right time.”
***
Researchers believe the improvement came from several things working together — staff education, sharpened clinical awareness, EHR alerts and automated rapid response notifications — rather than any single piece of the system on its own.
Because the underlying tool is already built into Epic, one of the most widely used electronic health record systems in the country, the implications may reach well beyond New Jersey.
Researchers are now studying a next phase of the work, aimed at catching patients whose risk scores are climbing rapidly — hoping to buy back even more time before the next crisis begins.
Stephen O’Mahony, Senior VP and Chief Medical Information Officer at RWJBarnabas Health and the study’s senior author, said the results are the ultimate proof of concept.
“This is what an integrated academic health system is for,” he said. “We combined Rutgers’ methodological rigor with the operational reach of 11 RWJBarnabas hospitals. The mortality benefit was not produced by an algorithm but by the partnership around the algorithm.”
For information about RWJBarnabas Health, go to rwjbh.org.
For information about Robert Wood Johnson Medical School, go to rwjms.rutgers.edu
