Sex Differences in Cerebral Aneurysms and Subarachnoid Hemorrhage

Sex differences in cerebral aneurysm occurrence and characteristics have been well described. Although sex differences in outcomes following ischemic stroke have been identified, the effect of sex on outcomes following hemorrhagic stroke, and in particular, aneurysm treatment has been less studied. We describe the current state of knowledge regarding the impact of sex on treatment and outcomes of cerebral aneurysms. Although prior studies suggest that aneurysm prevalence and progression may be related to sex, we did not find clear evidence that outcomes following subarachnoid hemorrhage vary based on sex. Last, we identify areas for future research that could enhance understanding of the role sex plays in this context.

Robotic-assisted intracranial aneurysm treatment: 1 year follow-up imaging and clinical outcomes

BackgroundThe use of robotics in medicine may enable increased technical accuracy, reduced procedural time and radiation exposure, and remote completion of procedures. We have previously described the first-in-human, robotic-assisted cerebral aneurysm treatment using the CorPath GRX Robotic System. In this report we discuss our early experiences and outcomes using this robotic device for endovascular treatment of intracranial aneurysms using stent-assisted coil embolization and flow diversion.MethodsThe patient and disease characteristics, procedural details, and follow-up imaging and clinical outcomes of consecutive patients undergoing robotically-assisted intracranial aneurysm embolization between November 2019 and February 2020 are presented.ResultsSix patients underwent robotically-assisted embolization of intracranial aneurysms. Four of the patients were treated with a neck-bridging stent (with or without coiling) and two patients were treated with a flow-diverting stent. Two patients were treated in the subacute period of subarachnoid hemorrhage and four patients were treated electively. All of the procedures could be completed robotically and there was no need for unplanned manual intervention. The technical success rate of the procedures was 100%. There was no morbidity or mortality associated with the procedures. One year follow-up imaging showed that four aneurysms were completely obliterated (Raymond-Roy Occlusion Classification (RROC) class I) and the remaining two were occluded with a residual neck (RROC class II).ConclusionsThe Corpath GRX Robotic System demonstrated a precise control over the microcatheter, wire and stent during aneurysm treatment. Robotic neuro-procedures seem to be safe and effective and demonstrate stable occlusion results in the midterm follow-up.

Automated Machine Learning Model Development for Intracranial Aneurysm Treatment Outcome Prediction: A Feasibility Study

Background: The prediction of aneurysm treatment outcomes can help to optimize the treatment strategies. Machine learning (ML) has shown positive results in many clinical areas. However, the development of such models requires expertise in ML, which is not an easy task for surgeons.Objectives: The recently emerged automated machine learning (AutoML) has shown promise in making ML more accessible to non-computer experts. We aimed to evaluate the feasibility of applying AutoML to develop the ML models for treatment outcome prediction.Methods: The patients with aneurysms treated by endovascular treatment were prospectively recruited from 2016 to 2020. Treatment was considered successful if angiographic complete occlusion was achieved at follow-up. A statistical prediction model was developed using multivariate logistic regression. In addition, two ML models were developed. One was developed manually and the other was developed by AutoML. Three models were compared based on their area under the precision-recall curve (AUPRC) and area under the receiver operating characteristic curve (AUROC).Results: The aneurysm size, stent-assisted coiling (SAC), and posterior circulation were the three significant and independent variables associated with treatment outcome. The statistical model showed an AUPRC of 0.432 and AUROC of 0.745. The conventional manually trained ML model showed an improved AUPRC of 0.545 and AUROC of 0.781. The AutoML derived ML model showed the best performance with AUPRC of 0.632 and AUROC of 0.832, significantly better than the other two models.Conclusions: This study demonstrated the feasibility of using AutoML to develop a high-quality ML model, which may outperform the statistical model and manually derived ML models. AutoML could be a useful tool that makes ML more accessible to the clinical researchers.