Related Experiment Video
Updated: Jun 20, 2025
A Data-Driven Approach to Quantifying Immune States in Sepsis
Published on: February 7, 2025
Development and validation of an interpretable machine learning for mortality prediction in patients with sepsis
1Department of Neurology, Third People's Hospital of Hubei Province, Wuhan, China.
Introduction:
Sepsis is a leading cause of death. However, there is a lack of useful model to predict outcome in sepsis. Herein, the aim of this study was to develop an explainable machine learning (ML) model for predicting 28-day mortality in patients with sepsis based on Sepsis 3.0 criteria.
Methods:
We obtained the data from the Medical Information Mart for Intensive Care (MIMIC)-III database (version 1.4). The overall data was randomly assigned to the training and testing sets at a ratio of 3:1. Following the application of LASSO regression analysis to identify the modeling variables, we proceeded to develop models using Extreme Gradient Boost (XGBoost), Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest (RF) techniques with 5-fold cross-validation. The optimal model was selected based on its area under the curve (AUC). Finally, the Shapley additive explanations (SHAP) method was used to interpret the optimal model.
Results:
A total of 5,834 septic adults were enrolled, the median age was 66 years (IQR, 54-78 years) and 2,342 (40.1%) were women. After feature selection, 14 variables were included for developing model in the training set. The XGBoost model (AUC: 0.806) showed superior performance with AUC, compared with RF (AUC: 0.794), LR (AUC: 0.782) and SVM model (AUC: 0.687). SHAP summary analysis for XGBoost model showed that urine output on day 1, age, blood urea nitrogen and body mass index were the top four contributors. SHAP dependence analysis demonstrated insightful nonlinear interactive associations between factors and outcome. SHAP force analysis provided three samples for model prediction.
Conclusion:
In conclusion, our study successfully demonstrated the efficacy of ML models in predicting 28-day mortality in sepsis patients, while highlighting the potential of the SHAP method to enhance model transparency and aid in clinical decision-making.
Insights
This study developed an explainable machine learning model to predict 28-day sepsis mortality. The XGBoost model demonstrated superior performance, identifying key predictors for improved clinical decision-making.
Area of Science:
- Computational biology
- Medical informatics
- Clinical research
Background:
- Sepsis is a significant cause of mortality globally.
- Effective prediction models for sepsis outcomes are currently lacking.
- Sepsis 3.0 criteria provide a standardized definition for patient cohorts.
Purpose of the Study:
- To develop an explainable machine learning (ML) model for predicting 28-day mortality in sepsis patients.
- To identify key predictors of mortality using ML techniques.
- To enhance transparency in ML model predictions for clinical utility.
Main Methods:
- Utilized the MIMIC-III database (version 1.4) for patient data.
- Applied LASSO regression for feature selection, followed by XGBoost, RF, LR, and SVM model development.
- Employed 5-fold cross-validation and AUC for model optimization.
- Interpreted the optimal model using Shapley Additive Explanations (SHAP).
Main Results:
- The XGBoost model achieved the highest AUC (0.806), outperforming RF, LR, and SVM.
- Top predictors identified by SHAP analysis included urine output on day 1, age, blood urea nitrogen, and BMI.
- SHAP analysis revealed nonlinear interactions between factors and patient outcomes.
Conclusions:
- Machine learning models, particularly XGBoost, are effective for predicting 28-day sepsis mortality.
- The SHAP method enhances the interpretability of ML models, supporting clinical decision-making.
- Explainable AI holds significant potential for improving patient care in critical conditions like sepsis.
More Related Videos
Related Concept Videos
01:24Kaplan-Meier Approach
01:15Assumptions of Survival Analysis