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

Emilia Apostolova, Tom Velez


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%.
Anthology ID:
W17-2332
Volume:
BioNLP 2017
Month:
August
Year:
2017
Address:
Vancouver, Canada,
Editors:
Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, Junichi Tsujii
Venue:
BioNLP
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
257–262
Language:
URL:
https://aclanthology.org/W17-2332
DOI:
10.18653/v1/W17-2332
Bibkey:
Cite (ACL):
Emilia Apostolova and Tom Velez. 2017. Toward Automated Early Sepsis Alerting: Identifying Infection Patients from Nursing Notes. In BioNLP 2017, pages 257–262, Vancouver, Canada,. Association for Computational Linguistics.
Cite (Informal):
Toward Automated Early Sepsis Alerting: Identifying Infection Patients from Nursing Notes (Apostolova & Velez, BioNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-2332.pdf
Code
 ema-/antibiotic-dictionary
Data
MIMIC-III