AI Tool Linked to Lower Hospital Deaths in RWJBarnabas Study

RWJBarnabas Health and Rutgers University researchers found that an AI early warning system helped detect clinical decline in hospitalized patients earlier, according to a press release.

The study, published in NEJM AI, evaluated 23,132 high risk patients across 11 RWJBarnabas Health hospitals. Deaths among high risk patients fell from 23.1 percent to 18.6 percent after the system was implemented, an 18 percent reduction in the risk adjusted odds of in hospital death.

The tool, Epic Deterioration Index, continuously analyzes data from the electronic health record to identify patients at increased risk of serious clinical decline. Rapid response team activations among high risk patients increased from 25.3 percent of hospital stays to 37.5 percent after implementation.