Accurate detection of sepsis at ED triage using machine learning with clinical natural language processing

Sepsis is a life-threatening condition with organ dysfunction and is a leading cause of death and critical illness worldwide. Accurate detection of sepsis during emergency department triage would allow early initiation of lab analysis, antibiotic administration, and other sepsis treatment protocols. The purpose of this study was to determine whether EHR data can be extracted and synthesized with the latest machine learning algorithms (KATE Sepsis) and clinical natural language processing to produce accurate sepsis models, and compare KATE Sepsis performance with existing sepsis screening protocols, such as SIRS and qSOFA. A machine learning model (KATE Sepsis) was developed using patient encounters with triage data from 16 participating hospitals. KATE Sepsis, SIRS, standard screening (SIRS with source of infection) and qSOFA were tested in three settings. Cohort-A was a retrospective analysis on medical records from a single Site 1. Cohort-B was a prospective analysis of Site 1. Cohort-C was a retrospective analysis on Site 1 with 15 additional sites. Across all cohorts, KATE Sepsis demonstrates an AUC of 0.94-0.963 with 73-74.87% TPR and 3.76-7.17% FPR. Standard screening demonstrates an AUC of 0.682-0.726 with 39.39-51.19% TPR and 2.9-6.02% FPR. The qSOFA protocol demonstrates an AUC of 0.544-0.56, with 10.52-13.18% TPR and 1.22-1.68% FPR. For severe sepsis, across all cohorts, KATE Sepsis demonstrates an AUC of 0.935-0.972 with 70-82.26% TPR and 4.64-8.62% FPR. For septic shock, across all cohorts, KATE Sepsis demonstrates an AUC of 0.96-0.981 with 85.71-89.66% TPR and 4.85-8.8% FPR. SIRS, standard screening, and qSOFA demonstrate low AUC and TPR for severe sepsis and septic shock detection. KATE Sepsis provided substantially better sepsis detection performance in triage than commonly used screening protocols.