Interpretable Machine Learning for Early Risk Stratification of Carbapenem Resistance Among ICU Patients with Sterile-Site Pseudomonas aeruginosa Isolates: Development and Internal Validation Using MIMIC-IV

Lu Liu

doi:10.1016/j.jgar.2026.06.004

Interpretable Machine Learning for Early Risk Stratification of Carbapenem Resistance Among ICU Patients with Sterile-Site Pseudomonas aeruginosa Isolates: Development and Internal Validation Using MIMIC-IV

2026-06-19

0

OA

AI

L

Lu Liu

Y

Yanbin Chang

X

Xiaolan Gu

W

Wanpeng Xu *

DOI：10.1016/j.jgar.2026.06.004

Original

Original request for help

Save

Abstract

En 中文

• XGBoost model predicts carbapenem resistance in sterile-site P. aeruginosa isolates • AUROC of 0.865 achieved using 15 clinical predictors from first 24h of ICU stay • SHAP analysis identifies age, respiratory rate, and thrombocytopenia as key drivers

Keywords:

Pseudomonas aeruginosa

carbapenem resistance

sterile-site isolate

risk stratification

machine learning

antimicrobial stewardship

Interpretable Machine Learning for Early Risk Stratification of Carbapenem Resistance Among ICU Patients with Sterile-Site Pseudomonas aeruginosa Isolates: Development and Internal Validation Using MIMIC-IV

Abstract

Journal

Organization