Identifying Potential (re)hemorrhage Among Sporadic Cerebral Cavernous Malformations Using Machine Learning

This study utilized a dataset of 731 patients with sporadic cerebral cavernous malformations (CCM) to evaluate the risk of hemorrhage and (re)hemorrhage in follow-up. The study used support vector machine and extreme gradient boosting algorithms to analyze the data and found that age, sex, and CCM volume were significant predictors of (re)hemorrhage risk.