What question did this study set out to answer?

The study aims to create and validate a predictive score for bacteremia to enhance detection in emergency department patients.

April 17, 2026Open Access

Development and validation of a bacteremia prediction score for adult emergency department patients using hybrid machine learning and regression

Key Points

The study aims to create and validate a predictive score for bacteremia to enhance detection in emergency department patients.
Conducted a retrospective cohort study with data from a tertiary academic hospital.
Developed the score using the AutoScore method combining machine learning and logistic regression.
Utilized vital signs and laboratory data from 24,856 patients to inform the model.
Performed external validation at two additional hospitals to assess model performance.
The bacteremia incidence was found to be 11.39% across the cohorts.
The developed prediction score achieved an AUROC of 0.825, outperforming other predictive measures.
External validation yielded AUROCs of 0.796 and 0.813 at the two other hospitals.
Risk stratification categorized patients into low-, intermediate-, and high-risk groups with varying bacteremia rates.

Abstract

Bacteremia requires early detection and appropriate treatment. High rates of false-positives in blood cultures in emergency departments (EDs) have led to the need for accurate predictive tools. This study developed and validated a bacteremia prediction score to improve patient selection for blood cultures. A multicenter retrospective cohort study used data from a tertiary academic hospital in Republic of Korea (2014–2019) to develop and validate the model, with external validation at two additional hospitals (Hospital A and Hospital B) (2022). The AutoScore method, integrating machine learning and logistic regression, generated the score using initial vital signs and laboratory data. Model performance was assessed via the area under the receiver operating characteristic (AUROC) curve. Of 24,856 patients, 17,373 formed the development cohort, 2491 the validation cohort, and 4992 the test cohort. Bacteremia incidence was 11.39%. The score, incorporating eight variables (procalcitonin, lactate, white blood cell count, c-reactive protein, blood urea nitrogen, body temperature, platelet count, and total bilirubin), achieved an AUROC of 0.825 (95% confidence interval CI, 0.808–0.842), outperforming procalcitonin (0.808; 95% CI, 0.790–0.826), SOFA score (0.718; 95% CI, 0.696–0.741), MEWS score (0.630; 95% CI, 0.606–0.654) and SIRS score (0.583; 95% CI, 0.558–0.608). External validation yielded AUROCs of 0.796 (95% CI, 0.773–0.818) at Hospital A and 0.813 (95% CI, 0.778–0.848) at Hospital B. Risk stratification categorized patients into low-, intermediate-, and high-risk groups with bacteremia rates of 2.6–3.2%, 5.2–9.3%, and 23.7–30.2%. A bacteremia prediction score was developed and validated using AutoScore, integrating machine learning and logistic regression. The model, based on eight clinical variables, stratified patients by risk and showed favorable predictive performance compared with conventional markers.

KI fragen

Bookmark

View Full Paper

Cite This Study

Kim et al. (Wed,) studied this question.

synapsesocial.com/papers/69e1cfe05cdc762e9d858de0 https://doi.org/https://doi.org/10.1038/s41598-026-48275-y

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

KI fragen

Bookmark

View Full Paper