Researchers affiliated with Yale New Haven (Conn.) Health have developed an Epic application that predicts the risk of patients with gastrointestinal bleeding.
The first-of-its-kind machine learning model combs EHR data including symptoms, labs and medical history to create a clinical risk score for patients with GI bleeding. The researchers said creating the tool in Epic, the most widely-used EHR, offers the opportunity for other health systems to customize the data fields to their own patient populations.
"Caring for patients in a hospital is complex and fast-paced. Physicians shouldn't need to spend time punching in numbers that already exist within the EHR," said Dennis Shung, MD, PhD, assistant professor of medicine and director of digital health for digestive diseases at Yale, in a Sept. 9 statement.
The application performed better than current clinical risk scores and identified very low-risk patients for discharge from the emergency department, according to the July study in Gastroenterology.