Predicting Early Seizures After Intracerebral Hemorrhage with Machine Learning

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.