Related Experiment Videos
Explainable Machine Learning Integrating Patient and Environmental Factors for Predicting Multidrug-Resistant
Genying Gu1, Yan Ji2, Xinglin Xiong3
1Department of Neurosurgical Intensive Care Unit, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing, Jiangsu, 210019, People's Republic of China.
Objective:
Multidrug-resistant organisms (MDROs) pose a serious threat to global public health, particularly in intensive care units (ICU). Few studies have employed machine learning (ML) to capture complex clinical interactions. This study aimed to develop an explainable ML model for early risk stratification of MDRO colonization or infection by integrating patient-specific clinical features with environmental exposure factors.
Methods:
We analyzed the data of 420 ICU patients (210 MDRO-positive cases and 210 matched controls) admitted between January 2020 and October 2023. Predictors were selected using least absolute shrinkage and selection operator (LASSO) regression. Six ML models-Logistic Regression, Random Forest, Gradient Boosting, AdaBoost, XGBoost, and LightGBM-were developed and evaluated using internal validation on a randomly split test set. The best performing model was interpreted using SHapley Additive exPlanations (SHAP), and a web-based tool was developed for clinical applications.
Results:
Five predictors were identified through LASSO regression and were independently associated with the composite endpoint in subsequent multivariable logistic regression, including residence in a long-term care facility, MDRO-positive status of the prior bed occupant, central venous catheterization, surgery prior to infection, and duration of arterial catheterization. The XGBoost model demonstrated the highest performance, with an area under the curve of 0.926 for the training set and 0.862 for the validation set. SHAP analysis improved interpretability by quantifying feature contributions and illustrating the rationale behind individual predictions. A web-based tool was developed to facilitate real-time clinical risk assessment.
Conclusion:
This study demonstrates the utility of integrating environmental risk factors into a ML framework for improved MDRO prediction, resulting in a web-based tool with the potential for clinical decision support and enhancing infection control workflows.
Insights
This study developed an explainable machine learning model to predict multidrug-resistant organism (MDRO) colonization or infection in intensive care units (ICUs). The model integrates clinical and environmental factors for early risk stratification.
Area of Science:
- Infectious Diseases
- Medical Informatics
- Machine Learning in Healthcare
Background:
- Multidrug-resistant organisms (MDROs) are a significant global health threat, especially in intensive care units (ICUs).
- Existing methods struggle to capture complex interactions for early MDRO risk prediction.
- Machine learning (ML) offers potential for advanced clinical decision support.
Purpose of the Study:
- To develop an explainable ML model for early risk stratification of MDRO colonization or infection.
- To integrate patient-specific clinical features with environmental exposure factors for improved prediction.
- To create a clinically applicable tool for real-time risk assessment.
Main Methods:
- Analysis of 420 ICU patients (210 MDRO-positive, 210 controls) from January 2020 to October 2023.
- Predictor selection using LASSO regression, followed by development and validation of six ML models (Logistic Regression, Random Forest, Gradient Boosting, AdaBoost, XGBoost, LightGBM).
- Model interpretability using SHapley Additive exPlanations (SHAP) and development of a web-based tool.
Main Results:
- Five key predictors identified: long-term care facility residence, prior bed occupant's MDRO status, central venous catheterization, prior surgery, and arterial catheterization duration.
- XGBoost model achieved the highest performance (AUC 0.926 training, 0.862 validation).
- SHAP analysis enhanced model interpretability, and a web tool was created for clinical application.
Conclusions:
- Integrating environmental risk factors into an ML framework improves MDRO prediction.
- The developed web-based tool can aid clinical decision support.
- This approach has the potential to enhance infection control workflows in ICUs.
Related Concept Videos
01:26Healthcare Associated Infections I: Iatrogenic, Exogenic and Endogenic
HAIs significantly increase the cost of health care. Extended stays in healthcare institutions, increased disability, increased costs of medications, including specialized antibiotics, and prolonged recovery times add to the patient's expenses and the healthcare institution and funding bodies. Common...
01:25Transmission-based Precautions II: Airborne and Protective Environment
Airborne precautions:
Use airborne precautions when treating patients known or suspected to have diseases that spread through the air—for example, tuberculosis or measles. These organisms are present in smaller droplets expelled by an infected person and...
01:22Healthcare Associated Infections II: Preventive Measures
The best practices for preventing healthcare-associated infections include hand hygiene, patient risk...
01:18Steps in Outbreak Investigation
01:26Factors Affecting the Risk of Infection
The integrity and count of the white blood cells help the body resist pathogens and fight infection. When impaired, it reduces the body's resistance to pathogens. The acidic pH levels of the gastrointestinal, genitourinary tracts, and skin create...