We report our experience in treating patients with seizures associated with brain arteriovenous malformations (AVM) without a clinical history of intracranial hemorrhage. Between 2001 and 2003, the neurovascular unit at Beijing Tiantan Hospital treated 109 patients with brain AVM endovascularly. Thirty patients (27.5%) experienced seizures before treatment. We studied the following factors: sex, age, AVM size, AVM location, seizure type, duration of seizure history, endovascular treatment and AVM obliteration. Clinical follow-up was via telephone interview. Thirty patients with seizure disorders due to brain AVMs were endovascularly treated. The age of the patients ranged from eight to 55 years. There were 22 males and eight females. The AVMs were smaller than 3 cm in five patients, between 3 cm and 6 cm in 22, and larger than 6 cm in three. The most frequent location of the AVMs was in the frontal, followed by the parietal, temporal and occipital lobes. Sixty-seven embolization procedures were performed and total obliteration was achieved in four patients. Two patients developed a hemiparesis and three suffered temporary dysphasia after embolization. Two patients had visual field deficits. There were no deaths. The results of post-embolization seizure control during the average follow-up period of 80 months were excellent in 21 patients, good in four, fair in two and poor in three. Successful seizure control can be obtained with endovascular embolization.

BACKGROUND: Evaluating rupture risk in cerebral arteriovenous malformations currently lacks quantitative hemodynamic and angioarchitectural features necessary for predicting subsequent hemorrhage. We aimed to derive rupture-related hemodynamic and angioarchitectural features of arteriovenous malformations and construct an ensemble model for predicting subsequent hemorrhage. METHODS: This retrospective study included 3 data sets, as follows: training and test data sets comprising consecutive patients with untreated cerebral arteriovenous malformations who were admitted from January 2015 to June 2022 and a validation data set comprising patients with unruptured arteriovenous malformations who received conservative treatment between January 2009 and December 2014. We extracted rupture-related features and developed logistic regression (clinical features), decision tree (hemodynamic features), and support vector machine (angioarchitectural features) models. These 3 models were combined into an ensemble model using a weighted soft-voting strategy. The performance of the models in discriminating ruptured arteriovenous malformations and predicting subsequent hemorrhage was evaluated with confusion matrix-related metrics in the test and validation data sets. RESULTS: A total of 896 patients (mean±SD age, 28±14 years; 404 women) were evaluated, with 632, 158, and 106 patients in the training, test, and validation data sets, respectively. From the training set, 9 clinical, 10 hemodynamic, and 2912 pixel-based angioarchitectural features were extracted. A logistic regression model was built using 4 selected clinical features (age, nidus size, location, and venous aneurysm), whereas a decision-tree model was constructed from 4 hemodynamic features (outflow time, stasis index, cerebral blood flow, and outflow volume ratio). A support vector machine model was designed using 5 pixel-based angioarchitectural features. In the validation data set, the accuracy, sensitivity, specificity, and area under the curve of the ensemble model for predicting subsequent hemorrhages were 0.840, 0.889, 0.823, and 0.911, respectively. CONCLUSIONS: The ensemble model incorporating clinical, hemodynamic, and angioarchitectural features showed favorable performance in predicting subsequent hemorrhage of cerebral arteriovenous malformations.