Developing Machine-Learning Models to Predict Bacteremia in Febrile Adults Presenting to the Emergency Department: A Retrospective Cohort Study from a Large Center
Western Journal of Emergency Medicine · 2025
DOI: 10.5811/westjem.35866 ↗Kurz gefasst
Kohortenstudie in der Zeitschrift Western Journal of Emergency Medicine, 2025. Verfasst von Chia-Ming Fu und 10 weiteren Autor:innen. Beteiligte Einrichtung: National Taiwan University Hospital, Department of Emergency Medicine, Taipei City, Taiwan. Hauptthemen laut MEDLINE: Emergency Service, Hospital, Bacteremia, Machine Learning, Fever. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Bacteremia, a common disease but difficult to diagnose early, may result in significant morbidity and mortality without prompt treatment. We aimed to develop machine-learning (ML) algorithms to predict patients with bacteremia from febrile patients presenting to the emergency department (ED) using data that is readily available at the triage.
Methods
We included all adult patients (≥18 years of age) who presented to the emergency department (ED) of National Taiwan University Hospital (NTUH), a tertiary teaching hospital in Taiwan, with the chief complaint of fever or measured body temperature more than 38°C, and who received at least one blood culture during the ED encounter. We extracted data from the Integrated Medical Database of NTUH from 2009–2018.The dataset included patient demographics, triage details, symptoms, and medical history. The positive blood culture result of at least one potential pathogen was defined as bacteremia and used as the binary classification label. We split the dataset into training/validation and testing sets (60-to-40 ratio) and trained five supervised ML models using K-fold cross-validation. The model performance was evaluated using the area under the receiver operating characteristic curve (AUC) in the testing set.
Results
We included 80,201 cases in this study. Of them, 48120 cases were assigned to the training/validation set and 32,081 to the testing set. Bacteremia was identified in 5,831 (12.1%) and 3,824 (11.9%) cases of the training/validation set and test set, respectively. All ML models performed well, with CatBoost achieving the highest AUC (.844, 95% confidence interval [CI] .837-.850), followed by extreme gradient boosting (.843, 95% CI .836-.849), gradient boosting (.842, 95% CI .836-.849), light gradient boosting machine (.841, 95% CI .834-.847), and random forest (.828, 95% CI .821-.834).
Conclusion
Our machine-learning model has shown excellent discriminatory performance to predict bacteremia based only on clinical features at ED triage. It has the potential to improve care quality and save more lives if successfully implemented in the ED.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- National Taiwan University Hospital, Department of Emergency Medicine, Taipei City, Taiwan.
- Min-Sheng General Hospital, Department of Emergency Medicine, Taoyuan City, Taiwan.
- National Taiwan University, Department of Electrical Engineering, Taipei City, Taiwan.
- National Taiwan University, College of Medicine, Department of Emergency Medicine, Taipei City, Taiwan.
- En Chu Kong Hospital, Department of Nephrology, New Taipei City, Taiwan.
- Fu Jen Catholic University, School of Medicine, New Taipei City, Taiwan.
Zitieren
APA
Fu, C. M., Ngo, I., Lau, P. S., Ivanchuk, Y., Chou, F. Y., Wang, C. H., Lin, C. Y., Tsai, C. L., Chen, S. Y., Lu, T. C., & Wei, H. Y. (2025). Developing Machine-Learning Models to Predict Bacteremia in Febrile Adults Presenting to the Emergency Department: A Retrospective Cohort Study from a Large Center. Western Journal of Emergency Medicine. https://doi.org/10.5811/westjem.35866
Vancouver
Fu CM, Ngo I, Lau PS, Ivanchuk Y, Chou FY, Wang CH, et al. Developing Machine-Learning Models to Predict Bacteremia in Febrile Adults Presenting to the Emergency Department: A Retrospective Cohort Study from a Large Center. Western Journal of Emergency Medicine. 2025. doi:10.5811/westjem.35866
BibTeX
@article{Fu2025,
author = {Fu, Chia-Ming and Ngo, Ike and Lau, Pak Sheung and Ivanchuk, Yaroslav and Chou, Fan-Ya and Wang, Chih-Hung and Lin, Chien-Yu and Tsai, Chu-Lin and Chen, Shey-Ying and Lu, Tsung-Chien and Wei, Hung-Yu},
title = {Developing Machine-Learning Models to Predict Bacteremia in Febrile Adults Presenting to the Emergency Department: A Retrospective Cohort Study from a Large Center},
journal = {Western Journal of Emergency Medicine},
year = {2025},
doi = {10.5811/westjem.35866}
}
EUVIMED