Developing and validating a machine learning model to predict multidrug-resistant Klebsiella pneumoniae-related septic shock
Related Experiment Video
Updated: Jul 11, 2026
Cecal Ligation Puncture Procedure
Published on: May 7, 2011
Shengnan Pan1, Ting Shi2, Jinling Ji1
1Department of Medical Laboratory, The Affiliated Huai'an No. 1 People's Hospital of Nanjing Medical University, Huai'an, Jiangsu, China.
Background:
Multidrug-resistant Klebsiella pneumoniae (MDR-KP) infections pose a significant global healthcare challenge, particularly due to the high mortality risk associated with septic shock. This study aimed to develop and validate a machine learning-based model to predict the risk of MDR-KP-associated septic shock, enabling early risk stratification and targeted interventions.
Methods:
A retrospective analysis was conducted on 1,385 patients with MDR-KP infections admitted between January 2019 and June 2024. The cohort was randomly divided into a training set (n = 969) and a validation set (n = 416). Feature selection was performed using LASSO regression and the Boruta algorithm. Seven machine learning algorithms were evaluated, with logistic regression chosen for its optimal balance between performance and robustness against overfitting.
Results:
The overall incidence of MDR-KP-associated septic shock was 16.32% (226/1,385). The predictive model identified seven key risk factors: procalcitonin (PCT), sepsis, acute kidney injury, intra-abdominal infection, use of vasoactive medications, ventilator weaning failure, and mechanical ventilation. The logistic regression model demonstrated excellent predictive performance, with an area under the receiver operating characteristic curve (AUC) of 0.906 in the training set and 0.865 in the validation set. Calibration was robust, with Hosmer-Lemeshow test results of P = 0.065 (training) and P = 0.069 (validation). Decision curve analysis indicated substantial clinical net benefit.
Conclusion:
This study presents a validated, high-performing predictive model for MDR-KP-associated septic shock, offering a valuable tool for early clinical decision-making. Prospective, multi-center studies are recommended to further evaluate its clinical applicability and effectiveness in diverse settings.
Insights
A new machine learning model accurately predicts septic shock risk in patients with multidrug-resistant Klebsiella pneumoniae infections. This tool aids early intervention for better patient outcomes.
Area of Science:
- Infectious Diseases
- Critical Care Medicine
- Machine Learning in Healthcare
Background:
- Multidrug-resistant Klebsiella pneumoniae (MDR-KP) infections are a major global health concern.
- Septic shock from MDR-KP has a high mortality rate, necessitating early risk stratification.
- Existing prediction methods for MDR-KP-associated septic shock require enhancement.
Purpose of the Study:
- To develop and validate a machine learning model for predicting MDR-KP-associated septic shock risk.
- To enable early identification of high-risk patients for timely interventions.
- To improve clinical decision-making in managing MDR-KP infections.
Main Methods:
- Retrospective analysis of 1,385 patients with MDR-KP infections.
- Feature selection using LASSO regression and Boruta algorithm.
- Evaluation of seven machine learning algorithms, selecting logistic regression for its performance and robustness.
Main Results:
- The incidence of MDR-KP-associated septic shock was 16.32%.
- Key predictors identified: procalcitonin, sepsis, acute kidney injury, intra-abdominal infection, vasoactive medications, ventilator weaning failure, and mechanical ventilation.
- The logistic regression model achieved high predictive performance (AUC 0.906 training, 0.865 validation) with robust calibration.
Conclusions:
- A validated, high-performing predictive model for MDR-KP-associated septic shock has been developed.
- The model serves as a valuable tool for early clinical decision-making.
- Further prospective, multi-center studies are recommended to confirm clinical applicability.
