Development and validation of an interpretable machine learning–based model for predicting carbapenem-resistant Acinetobacter baumannii infection in postoperative ICU patients: a retrospective cohort study
Frontiers in Cellular and Infection Microbiology · 2026
DOI: 10.3389/fcimb.2026.1788229 ↗Kurz gefasst
Kohortenstudie in der Zeitschrift Frontiers in Cellular and Infection Microbiology, 2026. Verfasst von Yan Gao und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Disease Prevention and Control, General Hospital of Northern Theater Command, Shenyang, China. Hauptthemen laut MEDLINE: Acinetobacter baumannii, Carbapenems, Machine Learning, Acinetobacter Infections. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Science and Technology of Liaoning Province.
Themen: Künstliche Intelligenz in der Pflege, Intensivpflege
Abstract (Originalsprache)
Background
Carbapenem-resistant Acinetobacter baumannii (CRAB) is a major cause of healthcare-associated infections and is associated with poor outcomes in intensive care units, particularly among postoperative patients. However, predictive tools for early identification of high-risk postoperative intensive care units (ICU) patients remain scarce.
Methods
We conducted a retrospective cohort study including 2,195 postoperative ICU patients. Clinically available demographic, treatment-related, and laboratory variables were used to develop eight machine learning models. Feature selection was performed using Boruta, and model interpretability was enhanced using Shapley Additive Explanations (SHAP) analysis. Model performance was evaluated in an independent test set using the area under the receiver operating characteristic curve (AUC), with sensitivity analyses performed using reduced feature sets.
Results
Among 2,195 postoperative ICU patients, 694 (31.6%) developed CRAB infection. Patients with CRAB infection had significantly longer ICU stays, greater exposure to invasive procedures, higher antimicrobial use, and worse laboratory profiles than non-infected patients. Using 19 features selected by the Boruta algorithm, all eight machine learning models achieved good discrimination in the test set (AUC > 0.83). Gradient Boosting demonstrated the best overall performance, with an AUC of 0.867 (95% CI: 0.836–0.892), good calibration, and the highest net clinical benefit. SHAP analysis identified duration of mechanical ventilation, central venous catheterization, ICU length of stay (LOS), and carbapenem exposure as the most influential predictors. Sensitivity analyses showed that models using only the top 10 or top 5 SHAP-ranked features achieved performance comparable to the full model, supporting the feasibility of feature reduction for clinical application.
Conclusions
This study provides an interpretable and clinically applicable framework for early risk assessment of CRAB infection in postoperative ICU patients, supporting targeted prevention strategies and more rational antimicrobial stewardship.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Disease Prevention and Control, General Hospital of Northern Theater Command, Shenyang, China.
- Key Laboratory of Environmental Stress and Chronic Disease Control & Prevention, China Medical University, Ministry of Education, Shenyang, China.
- Department of Epidemiology, School of Public Health, China Medical University, Shenyang, China.
- Department of Orthopedics, General Hospital of Northern Theater Command, Shenyang, China.
Förderung
- Department of Science and Technology of Liaoning Province
Zitieren
APA
Gao, Y., Gu, G., Wang, R., Jia, C., Zhao, F., Cao, D., Jin, X., Ma, X., Wang, Y., & Li, X. (2026). Development and validation of an interpretable machine learning–based model for predicting carbapenem-resistant Acinetobacter baumannii infection in postoperative ICU patients: a retrospective cohort study. Frontiers in Cellular and Infection Microbiology. https://doi.org/10.3389/fcimb.2026.1788229
Vancouver
Gao Y, Gu G, Wang R, Jia C, Zhao F, Cao D, et al. Development and validation of an interpretable machine learning–based model for predicting carbapenem-resistant Acinetobacter baumannii infection in postoperative ICU patients: a retrospective cohort study. Frontiers in Cellular and Infection Microbiology. 2026. doi:10.3389/fcimb.2026.1788229
BibTeX
@article{Gao2026,
author = {Gao, Yan and Gu, Guangxin and Wang, Ruiwen and Jia, Chen and Zhao, Feng and Cao, Dan and Jin, Xin and Ma, Xiaoyuan and Wang, Yu and Li, Xueyu},
title = {Development and validation of an interpretable machine learning–based model for predicting carbapenem-resistant Acinetobacter baumannii infection in postoperative ICU patients: a retrospective cohort study},
journal = {Frontiers in Cellular and Infection Microbiology},
year = {2026},
doi = {10.3389/fcimb.2026.1788229}
}
EUVIMED