Tool Developed to Assist with Triage in the Emergency Department

Published in Insight - Insight Nov./Dec. 2022

Johns Hopkins researchers thought they had developed an effective artificial intelligence (AI) tool that could help emergency department (ED) nurses decide the best approach for incoming patients. When they saw it in action in Johns Hopkins EDs, they felt validated.

Nurses typically evaluate new patients in an ED and assign a number from one (the sickest) to five (the least sick) that determines the path of care. But the evaluation is subjective, with two nurses evaluating the same patient sometimes disagreeing, says Scott Levin, an associate professor of emergency medicine who helped develop the tool.

The technology is integrated into a patient’s digital health record. A nurse asks a patient for information about their condition and takes vital signs. The data, combined with the patient’s health care history, is run through the AI algorithm to predict the patient’s risk of several acute outcomes and to recommend a triage level of care, along with an explanation for the decision — all in a matter of seconds. The nurse then assigns the triage level.

“What we’ve done is help the nurses confidently identify a larger group of those low risk patients,” says Levin, who is also a director of Johns Hopkins’ Center for Data Science in Emergency Medicine. “When you do that, those people go on more efficient patient care pathways and get out of the ED sooner, creating improved patient flow.”

The technology is currently used as part of the triage process in EDs at The Johns Hopkins Hospital, Johns Hopkins Bayview Medical Center and Howard County General Hospital. Starting this month, it will be used at Sibley Memorial Hospital. The system is also employed in hospitals in Florida and Connecticut, and will soon launch at several hospitals in Missouri.

TriageGO (the tool) and the company formed around it, Stocastic, were recently acquired by Beckman Coulter, a business that provides clinical diagnostics.

“It’s a dream scenario,” says Levin. “Our whole team will continue working for Beckman Coulter on TriageGO, but also on other decision-support products Beckman Coulter is developing for the emergency department.”

Levin founded Stocastic in 2017 with Eric Hamrock, who was then a health care administrator at Howard County General Hospital before leaving to work for Stocastic full time. Jeremiah Hinson, an associate professor of emergency medicine at Johns Hopkins and a director of the Center for Data Science in Emergency Medicine, is Stocastic’s chief medical officer.

Read the original article: “Digital Health Startup That Assists Emergency Department Decision Making Acquired.”

New Tool Transforms Data Collection for Clinical Research

Software translates data from electronic health records into a common open format, enabling researchers to quickly run queries across institutions without risking patient privacy.

An illustration represents sharing clinical data, thanks to Observational Medical Outcomes Partnership (OMOP).

Study Shows Johns Hopkins AI System Catches Sepsis Sooner

The new system identifies patients at risk for the illness, which develops quickly and is notoriously difficult to detect.

An illustration represents the analysis of germs.