Tip Sheet: Johns Hopkins Researchers Present Findings at American College of Emergency Physicians Scientific Assembly

10/02/2018

10-1-2018 Kim P Emergency-Department- sign-iStock-694292326
Credit: iStock
What: The annual American College of Emergency Physicians (ACEP) Scientific Assembly will bring together more than 8,000 emergency medicine physicians, including those from Johns Hopkins Medicine. Johns Hopkins Medicine’s Department of Emergency Medicine faculty will present research findings on a variety of topics.

When: Oct. 1-4, 2018

Where: San Diego Convention Center

Study Summaries:


Prediction of Acute Kidney Injury in the Emergency Department Using EHR Data and Machine Learning Methods

When: Tuesday, Oct. 2, noon to 1:45 p.m. PDT

Jeremiah Hinson, M.D., Ph.D., assistant professor of emergency medicine at the Johns Hopkins University School of Medicine, will present findings related to acute kidney injury using machine learning methods, a form artificial intelligence. Hinson says this is the first time machine learning has been used to identify patients at elevated risk for acute kidney injury (AKI) from a group of emergency department patients. The team hopes this model will be used to reduce the incidence and severity of AKI in the near future.

Machine Learning-Based Electronic Triage: A Prospective Evaluation

When: Tuesday, Oct. 2, 5 p.m. PDT

Scott Levin, Ph.D., associate professor of emergency medicine in at the Johns Hopkins University School of Medicine, will highlight results of a prospective evaluation of an electronic health record decision support tool known as electronic triage (e-triage), which can improve care by enhancing decision-making and increasing clinical emergency department (ED) efficiency. Levin and his team previously created the tool to assist providers in making decisions on patient care in the ED triage stage of the process, such as the order in which patients will be seen. The study, conducted at a large urban academic ED, showed that e-triage led to a substantial change in distribution of patient acuity levels.
 


On the web: