Sepsis is lethal, prevalent, and costly for healthcare organizations. In this session, attendees will learn how Emory Healthcare, the largest health system in Georgia, developed a real-time application that predicts onset-time of sepsis based on live ICU data and provides clinicians with actionable visual alerts.
The Emery solution includes a scalable, cloud-based system that continuously streams bedside data and uses the prediction engine to generate hourly scores. Interoperability is achieved by using FHIR resources and APIs. This system monitors roughly 100 patients a day at Emory Tele-ICU center and reliably predicts onset of sepsis with an AUC of 0.9.
• Deploying cloud-based applications into clinical workflow.
• Adopting FHIR as a data model for clinical decision support.
• Training and operating machine learning models on healthcare data.