EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

XGBoost (eXtreme Gradient Boosting) Can Predict Organisms Growing in Urine Culture from the Emergency Department

Johnathan M Sheele, Ronna L Campbell, Derick D Jones

Western Journal of Emergency Medicine · 08.04.2026 · 27 (3)

DOI: 10.5811/westjem.48715 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Western Journal of Emergency Medicine, online erschienen am 08.04.2026. Verfasst von Johnathan M Sheele und 2 weiteren Autor:innen. Beteiligte Einrichtung: Mayo Clinic, Department of Emergency Medicine, Jacksonville, Florida. Hauptthemen laut MEDLINE: Emergency Service, Hospital, Urinary Tract Infections. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Urinary tract infections are common in the emergency department (ED) but are frequently misdiagnosed and mismanaged. We sought to determine whether eXtreme Gradient Boosting (XGBoost), an open-source machine-learning library, could predict the organisms growing in urine cultures ordered from the ED.

Methods

We developed XGBoost algorithms to retrospectively examine 62,963 Mayo Clinic ED encounters between January 1, 2017–December 31, 2021, during which a urinalysis and urine culture were performed. The model used 1,303 patient variables. All patient ages were included. Data were from the electronic health record and available to the clinician during the patient encounter.

Results

For the most common bacteria growing in urine culture, XGBoost was able to predict the presence of a member of the Enterobacteriaceae family with an area under the receiver operating curve (AUC) of 0.90 and an accuracy of 0.79. The model predicted the presence of 10 different bacterial genera with an AUC of 0.70-0.88 and an accuracy of 0.87-0.99. Furthermore, XGBoost was able to predict whether the urine culture would report Gram-positive or Gram-negative bacteria with an AUC of 0.81 and 0.90, respectively, and an accuracy of 0.85 and 0.86, respectively. The model predicted whether yeast would be reported with an AUC of 0.84 and an accuracy of 1.00.

Discussion

XGBoost can predict the bacterial genus and Gram-staining results of the bacteria growing in urine cultures

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Emergency Service, HospitalUrinary Tract InfectionsHumansBoosting Machine Learning AlgorithmsRetrospective StudiesUrinalysis

Autor:innen und Institutionen

  • Mayo Clinic, Department of Emergency Medicine, Jacksonville, Florida.
  • Mayo Clinic, Department of Emergency Medicine, Rochester, Minnesota.

Zitieren

APA

Sheele, J. M., Campbell, R. L., & Jones, D. D. (2026). XGBoost (eXtreme Gradient Boosting) Can Predict Organisms Growing in Urine Culture from the Emergency Department. Western Journal of Emergency Medicine, 27(3). https://doi.org/10.5811/westjem.48715

Vancouver

Sheele JM, Campbell RL, Jones DD. XGBoost (eXtreme Gradient Boosting) Can Predict Organisms Growing in Urine Culture from the Emergency Department. Western Journal of Emergency Medicine. 2026;27(3). doi:10.5811/westjem.48715

BibTeX
@article{Sheele2026,
  author = {Sheele, Johnathan M and Campbell, Ronna L and Jones, Derick D},
  title = {XGBoost (eXtreme Gradient Boosting) Can Predict Organisms Growing in Urine Culture from the Emergency Department},
  journal = {Western Journal of Emergency Medicine},
  year = {2026},
  volume = {27},
  number = {3},
  doi = {10.5811/westjem.48715}
}
Kostenlos starten →