Related Experiment Video
Updated: Sep 30, 2025
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Predicting Early Seizures After Intracerebral Hemorrhage with Machine Learning
Gabrielle Bunney1, Julianne Murphy2, Katharine Colton3
1Department of Emergency Medicine, Northwestern University, 625 N Michigan Ave Suite 1150, Chicago, IL, 60611, USA. gabrielle.bunney@northwestern.edu.
Insights
Machine learning models can predict early seizures after intracerebral hemorrhage (ICH). The XGBoost model demonstrated superior accuracy in identifying patients at risk for seizures, improving patient selection for treatment.
Area of Science:
- Neurology
- Medical Informatics
Background:
- Seizures are a significant complication of acute intracerebral hemorrhage (ICH), increasing the risk of patient deterioration.
- Early seizures (within the first week) are associated with adverse outcomes, including herniation.
Purpose of the Study:
- To develop and validate machine learning (ML) models for predicting early seizures following ICH.
- To identify key predictors for early seizure occurrence in ICH patients.
Main Methods:
- Two large datasets were used to train and validate ML models, including logistic regression, lasso regression, support vector machines, boosted trees (Xgboost), and random forest.
- The "CAV" model utilized cortical hematoma location, age (<65 years), and hematoma volume (>10 mL). The "CAV+" model incorporated additional variables like anticoagulant use and Glasgow Coma Scale.
- Model performance was assessed using the area under the receiver operating characteristic curve (AUC) on an independent test set.
Main Results:
- The "CAV" model predicted early seizures with an AUC of 0.72.
- The Xgboost ML model demonstrated improved prediction accuracy (AUC 0.79) compared to the "CAV" model (p=0.04).
- Models incorporating more variables showed enhanced predictive performance.
Conclusions:
- Early seizures following ICH are predictable using ML models.
- The developed models, particularly Xgboost, can aid in identifying high-risk patients.
- Improved prediction can optimize patient selection for seizure monitoring and prophylactic medication.
Background:
Seizures are a harmful complication of acute intracerebral hemorrhage (ICH). "Early" seizures in the first week after ICH are a risk factor for deterioration, later seizures, and herniation. Ideally, seizure medications after ICH would only be administered to patients with a high likelihood to have seizures. We developed and validated machine learning (ML) models to predict early seizures after ICH.
Methods:
We used two large datasets to train and then validate our models in an entirely independent test set. The first model ("CAV") predicted early seizures from a subset of variables of the CAVE score (a prediction rule for later seizures)-cortical hematoma location, age less than 65 years, and hematoma volume greater than 10 mL-whereas early seizure was the dependent variable. We attempted to improve on the "CAV" model by adding anticoagulant use, antiplatelet use, Glasgow Coma Scale, international normalized ratio, and systolic blood pressure ("CAV + "). For each model we used logistic regression, lasso regression, support vector machines, boosted trees (Xgboost), and random forest models. Final model performance was reported as the area under the receiver operating characteristic curve (AUC) using receiver operating characteristic models for the test data. The setting of the study was two large academic institutions: institution 1, 634 patients; institution 2, 230 patients. There were no interventions.
Results:
Early seizures were predicted across the ML models by the CAV score in test data, (AUC 0.72, 95% confidence interval 0.62-0.82). The ML model that predicted early seizure better in the test data was Xgboost (AUC 0.79, 95% confidence interval 0.71-0.87, p = 0.04) compared with the CAV model AUC.
Conclusions:
Early seizures after ICH are predictable. Models using cortical hematoma location, age less than 65 years, and hematoma volume greater than 10 mL had a good accuracy rate, and performance improved with more independent variables. Additional methods to predict seizures could improve patient selection for monitoring and prophylactic seizure medications.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
08:20Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings
Published on: June 6, 2015
