Predicting carbapenem-resistant Pseudomonas aeruginosa infection risk using XGBoost model and explainability
Abstract The prevalence and spread of carbapenem-resistant Pseudomonas aeruginosa (CRPA) is a global public health problem. This study aims to identify the risk factors of CRPA infection and construct a machine learning model to provide a prediction tool for clinical prevention and control. A total...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-06-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-04028-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849469942674489344 |
|---|---|
| author | Yan Jiang Hong-wei Wang Fang-ying Tian Yue Guo Xiu-mei Wang |
| author_facet | Yan Jiang Hong-wei Wang Fang-ying Tian Yue Guo Xiu-mei Wang |
| author_sort | Yan Jiang |
| collection | DOAJ |
| description | Abstract The prevalence and spread of carbapenem-resistant Pseudomonas aeruginosa (CRPA) is a global public health problem. This study aims to identify the risk factors of CRPA infection and construct a machine learning model to provide a prediction tool for clinical prevention and control. A total of 1949 patients with P.aeruginosa health care-associated infections (HAIs) were enrolled in this study. A total of 89 patients with CRPA infection and 89 patients with CSPA infection were matched 1:1. LASSO regression was used to screen the variables, and the XGBoost model was established (136 cases in the training set and 60 cases in the test set). Shapley additive explain (SHAP) method was used to explain the importance of variables. The area under the ROC curve (AUC) and calibration curve were used to evaluate the performance of the model. There were 89 cases of CRPA infection, and the CRPA infection rate was 4.57%. Respiratory tract was the most common source of infection, and ICU and hematology department were the high-risk departments. The AUC value of the XGBoost machine learning model in the training set was 0.987 (95%CI: 0.974-1.000), and the AUC value in the test set was 0.862 (95%CI: 0.750–0.974). The clinical decision curve also showed good results of the model. SHAP results showed that ICU admission, duration of central venous catheterization, use of carbapenems and fluoroquinolones were important factors for predicting CRPA infection. The XGBoost machine learning model is helpful for the early prevention and screening of CRPA infection in medical institutions. Infection control and clinical departments should carry out effective prevention and control for high-risk factors to reduce the occurrence of CRPA infection. |
| format | Article |
| id | doaj-art-47812845e3134b65b4ebb520b454632f |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-47812845e3134b65b4ebb520b454632f2025-08-20T03:25:19ZengNature PortfolioScientific Reports2045-23222025-06-0115111110.1038/s41598-025-04028-xPredicting carbapenem-resistant Pseudomonas aeruginosa infection risk using XGBoost model and explainabilityYan Jiang0Hong-wei Wang1Fang-ying Tian2Yue Guo3Xiu-mei Wang4Department of Nursing, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Third Hospital of Shanxi Medical University, Tongji Shanxi HospitalShanxi Medical UniversityDepartment of Hospital Infection, The Second Hospital of Shanxi Medical UniversityDepartment of Nursing, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Third Hospital of Shanxi Medical University, Tongji Shanxi HospitalDepartment of Nursing, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Third Hospital of Shanxi Medical University, Tongji Shanxi HospitalAbstract The prevalence and spread of carbapenem-resistant Pseudomonas aeruginosa (CRPA) is a global public health problem. This study aims to identify the risk factors of CRPA infection and construct a machine learning model to provide a prediction tool for clinical prevention and control. A total of 1949 patients with P.aeruginosa health care-associated infections (HAIs) were enrolled in this study. A total of 89 patients with CRPA infection and 89 patients with CSPA infection were matched 1:1. LASSO regression was used to screen the variables, and the XGBoost model was established (136 cases in the training set and 60 cases in the test set). Shapley additive explain (SHAP) method was used to explain the importance of variables. The area under the ROC curve (AUC) and calibration curve were used to evaluate the performance of the model. There were 89 cases of CRPA infection, and the CRPA infection rate was 4.57%. Respiratory tract was the most common source of infection, and ICU and hematology department were the high-risk departments. The AUC value of the XGBoost machine learning model in the training set was 0.987 (95%CI: 0.974-1.000), and the AUC value in the test set was 0.862 (95%CI: 0.750–0.974). The clinical decision curve also showed good results of the model. SHAP results showed that ICU admission, duration of central venous catheterization, use of carbapenems and fluoroquinolones were important factors for predicting CRPA infection. The XGBoost machine learning model is helpful for the early prevention and screening of CRPA infection in medical institutions. Infection control and clinical departments should carry out effective prevention and control for high-risk factors to reduce the occurrence of CRPA infection.https://doi.org/10.1038/s41598-025-04028-xCarbapenem resistancePseudomonas aeruginosaMachine learning modelsXGBoostRisk factors |
| spellingShingle | Yan Jiang Hong-wei Wang Fang-ying Tian Yue Guo Xiu-mei Wang Predicting carbapenem-resistant Pseudomonas aeruginosa infection risk using XGBoost model and explainability Scientific Reports Carbapenem resistance Pseudomonas aeruginosa Machine learning models XGBoost Risk factors |
| title | Predicting carbapenem-resistant Pseudomonas aeruginosa infection risk using XGBoost model and explainability |
| title_full | Predicting carbapenem-resistant Pseudomonas aeruginosa infection risk using XGBoost model and explainability |
| title_fullStr | Predicting carbapenem-resistant Pseudomonas aeruginosa infection risk using XGBoost model and explainability |
| title_full_unstemmed | Predicting carbapenem-resistant Pseudomonas aeruginosa infection risk using XGBoost model and explainability |
| title_short | Predicting carbapenem-resistant Pseudomonas aeruginosa infection risk using XGBoost model and explainability |
| title_sort | predicting carbapenem resistant pseudomonas aeruginosa infection risk using xgboost model and explainability |
| topic | Carbapenem resistance Pseudomonas aeruginosa Machine learning models XGBoost Risk factors |
| url | https://doi.org/10.1038/s41598-025-04028-x |
| work_keys_str_mv | AT yanjiang predictingcarbapenemresistantpseudomonasaeruginosainfectionriskusingxgboostmodelandexplainability AT hongweiwang predictingcarbapenemresistantpseudomonasaeruginosainfectionriskusingxgboostmodelandexplainability AT fangyingtian predictingcarbapenemresistantpseudomonasaeruginosainfectionriskusingxgboostmodelandexplainability AT yueguo predictingcarbapenemresistantpseudomonasaeruginosainfectionriskusingxgboostmodelandexplainability AT xiumeiwang predictingcarbapenemresistantpseudomonasaeruginosainfectionriskusingxgboostmodelandexplainability |