Toward Automated Early Sepsis Alerting: Identifying Infection Patients from Nursing Notes

TL;DR

This paper presents a machine learning approach to automatically monitor nursing notes for signs of infection, aiming to enable earlier sepsis detection and improve patient outcomes.

Contribution

It introduces a novel method for generating annotated datasets from free text nursing notes and develops a machine learning model with high F1-scores for infection detection.

Findings

F1-score ranged from 79 to 96% across tasks.

The method effectively captures infection signs from unstructured clinical notes.

Automated monitoring can potentially improve early sepsis alerting.

Abstract

Severe sepsis and septic shock are conditions that affect millions of patients and have close to 50% mortality rate. Early identification of at-risk patients significantly improves outcomes. Electronic surveillance tools have been developed to monitor structured Electronic Medical Records and automatically recognize early signs of sepsis. However, many sepsis risk factors (e.g. symptoms and signs of infection) are often captured only in free text clinical notes. In this study, we developed a method for automatic monitoring of nursing notes for signs and symptoms of infection. We utilized a creative approach to automatically generate an annotated dataset. The dataset was used to create a Machine Learning model that achieved an F1-score ranging from 79 to 96%.