Related Experiment Video
Updated: May 5, 2026
Autologous Blood Injection to Model Spontaneous Intracerebral Hemorrhage in Mice
Published on: August 24, 2011
Death risk prediction model for patients with non-traumatic intracerebral hemorrhage
Yidan Chen1, Xuhui Liu2, Mingmin Yan3
1Jianghan University School of Medicine, Wuhan, China.
Insights
A machine learning model effectively predicts death risk in intracerebral hemorrhage (ICH) patients. Key predictors include GCS motor score, age, GCS eye score, LDL, albumin, atrial fibrillation, and gender.
Area of Science:
- Neurology
- Medical Informatics
- Biostatistics
Background:
- Intracerebral hemorrhage (ICH) poses a significant mortality risk.
- Accurate prediction of ICH-related mortality is crucial for patient management.
- Machine learning offers potential for improving risk stratification in ICH.
Purpose of the Study:
- To develop and validate a machine learning model for predicting the risk of death in patients with non-traumatic intracerebral hemorrhage (ICH).
- To identify key clinical and demographic factors associated with mortality in ICH patients.
Main Methods:
- Retrospective analysis of 1274 ICH patients from the MIMIC IV 3.0 database.
- Feature selection using LASSO and multivariable logistic regression.
- Development of an XGBoost machine learning model for mortality prediction.
- External validation using data from the Second Hospital of Lanzhou University.
- Model performance evaluation using ROC, calibration curves, and accuracy metrics.
- Interpretation of model predictions using SHapley Additive exPlanations (SHAP).
Main Results:
- The study included 1274 ICH patients with a mortality rate of 44.9%.
- The XGBoost model demonstrated strong predictive performance with high AUC values in training, validation, and testing datasets.
- Key predictors identified by SHAP analysis included GCS motor score, age, GCS eye score, LDL, albumin, atrial fibrillation, and gender.
Conclusions:
- The developed XGBoost model is effective in predicting the risk of death in ICH patients.
- The SHAP method provides valuable interpretability for the machine learning model's predictions.
- This model can aid in clinical decision-making and risk stratification for ICH.
Background:
This study aimed to assess the risk of death from non-traumatic intracerebral hemorrhage (ICH) using a machine learning model.
Methods:
1274 ICH patients who met the specified inclusion and exclusion criteria were analyzed retrospectively in the MIMIC IV 3.0 database. Patients were randomly divided into training, validation, and testing datasets in a ratio of 6:2:2 based on the outcome distribution. Data from the Second Hospital of Lanzhou University were used as an external validation set. This study used LASSO regression and multivariable logistic regression analysis to screen for features. We then employed XGBoost to construct a machine-learning model. The model's performance was evaluated using ROC curve analysis, calibration curve analysis, clinical decision curve analysis, sensitivity, specificity, accuracy, and F1 score. Conclusively, the SHapley Additive exPlanations (SHAP) method was employed to interpret the model's predictions.
Results:
Deaths occurred in 572 out of the 1274 ICH cases included in the study, resulting in an incidence rate of 44.9%. The XGBoost model achieved a high AUC when predicting deaths in ICH patients (train: 0.814, 95%CI: 0.784 - 0.844; validation: 0.715, 95%CI: 0.653 - 0.777; test: 0.797, 95%CI: 0.743 - 0.851). The importance of SHAP variables in the model ranked from high to low was: 'GCS motor', 'Age', 'GCS eyes', 'Low density lipoprotein (LDL)', ' Albumin', ' Atrial fibrillation', and 'Gender'. The XGBoost model demonstrated good predictive performance in both the validation and external validation datasets.
Conclusions:
The XGBoost machine learning model we built has demonstrated strong performance in predicting the risk of death from ICH. Furthermore, the SHAP provides the possibility of interpreting machine learning results.
