A FHIR-Enabled Streaming Sepsis Prediction System for ICUs

Sepsis is a common disease with very costly, potentially deadly implications. Early prediction of Sepsis and initiation of antibiotic is widely considered as an important determinant of patient survival. Cross-institutional validation and implementation of algorithms for early prediction of Sepsis at a minimum require common data formats, streaming analytic platforms for timely risk assessment, and interoperable and standardized interfaces. In this work we present an open-source cloud-based analytic pipeline, which receives de-identified patient data from an interoperable server and produces real-time Sepsis risk scores for Intensive Care Unit (ICU) patients.