Machine learning prediction of malignant middle cerebral artery infarction after mechanical thrombectomy for anterior circulation large vessel occlusion.

OBJECTIVE: Prediction of malignant middle cerebral artery infarction (MMI) could identify patients for early intervention. We trained and internally validated a ML model that predicts MMI following mechanical thrombectomy (MT) for ACLVO. METHODS: All patients who underwent MT for ACLVO between 2015 - 2021 at a single institution were reviewed. Data was divided into 80% training and 20% test sets. 10 models were evaluated on the training set. The top 3 models underwent hyperparameter tuning using grid search with nested 5-fold CV to optimize the area under the receiver operating curve (AUROC). Tuned models were evaluated on the test set and compared to logistic regression. RESULTS: A total of 381 patients met the inclusion criteria. There were 50 (13.1%) patients who developed MMI. Out of the 10 ML models screened on the training set, the top 3 performing were neural network (median AUROC 0.78, IQR 0.72 - 0.83), support vector machine ([SVM] median AUROC 0.77, IQR 0.72 - 0.83), and random forest (median AUROC 0.75, IQR 0.68 - 0.81). On the test set, random forest (median AUROC 0.78, IQR 0.73 - 0.83) and neural network (median AUROC 0.78, IQR 0.73 - 0.83) were the top performing models, followed by SVM (median AUROC 0.77, IQR 0.70 - 0.83). These scores were significantly better than those for logistic regression (AUROC 0.72, IQR 0.66 - 0.78), individual risk factors, and the Malignant Brain Edema score (p < 0.001 for all). CONCLUSION: ML models predicted MMI with good discriminative ability. They outperformed standard statistical techniques and individual risk factors.

Outcomes After Endovascular Treatment of Direct Carotid Cavernous Fistulas: Systematic Review and Meta-Analysis.

BACKGROUND: Direct carotid cavernous fistulas (dCCF) involve pathologic shunting from the internal carotid artery into the cavernous sinus. We systematically reviewed the methods and outcomes of endovascular therapy for dCCF. METHODS: PubMed, Scopus, and EMBASE were used to identify studies that reported outcomes for patients undergoing embolization of dCCF. Outcomes included rates of occlusion, complications, symptom improvement, and recurrence. Pooled rates for each outcome were obtained with random effects models. The influence of embolization method on outcomes was assessed with meta-regressions. RESULTS: There were 16 studies comprising 270 patients. The mean age was 39.6 years, there were 36.3% females, and the mean follow-up was 19.7 months. Coils were the most common method of embolization (69.3%), followed by Onyx (31.1%), covered stent (22.2%), N-butyl cyanoacrylate (6.7%), and flow diversion (4.8%). The pooled overall occlusion rate was 92.1% (95% confidence interval [CI], 86.3-95.6; I2 = 29.2%). The pooled complication rate was 10.9% (95% CI, 7.3-16; I2 = 0%). Use of coils were associated with a slightly lower odds of overall complications (odds ratio, 0.98; 95% CI, 0.97-0.99) and cranial nerve palsy (odds ratio, 0.98; 95% CI, 0.97-0.99). The pooled fistula recurrence rate was 8.3% (95% CI, 4.3-15.4; I2 = 30.9%). CONCLUSIONS: Endovascular therapy for dCCF is associated with high occlusion and low complication rates. Recurrence is not uncommon, highlighting the need for close follow-up.