Table 2_Development and validation of a machine learning–based early warning model for carbapenem-resistant Klebsiella pneumoniae bloodstream infections using non-carbapenem susceptibility profiles.docx

Carbapenem-resistant Klebsiella pneumoniae (CRKP) is a major cause of bloodstream infections with limited therapeutic options. Definitive carbapenem susceptibility results are often obtained late in the laboratory workflow, highlighting the need for early warning tools to support timely risk stratification. We analyzed multicenter surveillance data from the Bloodstream Infection Resistance Surveillance Consortium, including 13,072 K. pneumoniae bloodstream isolates collected from 60 hospitals in China between 2014 and 2023. Non-carbapenem antimicrobial susceptibility interpretations were used as model inputs, while carbapenem results were excluded. Data were split chronologically into training (2014–2021), validation (2022), and test (2023) sets. Logistic regression, XGBoost, and CatBoost models were developed and evaluated using discrimination, calibration, decision curve analysis (DCA), and SHAP-based interpretability. XGBoost demonstrated the best overall performance, achieving higher discrimination with a ROC-AUC of 0.993 and a PR-AUC of 0.973 on the test set, along with superior calibration as reflected by the lowest Brier score (0.018). At a sensitivity-targeted threshold (~0.95), XGBoost maintained high sensitivity (0.924), excellent specificity (0.989), and a favorable positive predictive value (0.944), while preserving a high negative predictive value (0.986). SHAP analysis identified key non-carbapenem susceptibility features contributing to CRKP risk prediction. Non-carbapenem susceptibility profiles enable early identification of CRKP bloodstream infections. A machine learning–based early warning model, particularly XGBoost, may support laboratory-based risk stratification and complement conventional susceptibility testing.