Bilateral CSDH was an independent predictor for the recurrence of CSDH. Antiplatelet or anticoagulant drugs might facilitate the growth of CSDH. These results may help to identify patients at high risk for the recurrence of CSDH.

Background and Purpose-Subarachnoid hemorrhage caused by cerebral aneurysm rupture remains a life-threatening emergency despite advances in treatment. However, the mechanisms underlying aneurysm initiation, progression, and rupture remain unclear. We developed a method to induce experimental cerebral aneurysms in rats, monkeys, and mice. Interleukin-1␤ (IL-1␤) is a key inflammatory mediator, and it is thought to be a promising target for the treatment of inflammatory diseases. In the present study, we examined the role of IL-1␤ in cerebral aneurysm development. Methods-Cerebral aneurysms were experimentally induced in 5-week-old male C57BL/6 mice, IL-1␤ gene-deficient (IL-1␤Ϫ/Ϫ) mice, and age-matched control B10 mice (wild-type). Their cerebral arteries were dissected and examined histologically and immunohistochemically. Results-IL-1␤ was expressed in vascular media in mice at an early stage of aneurysmal models' cerebral arteries. No differences were seen in the rate of aneurysm development between IL-1␤Ϫ/Ϫ and wild-type mice, but the percentage of advanced aneurysm change was significantly larger in wild-type animals. Furthermore, in IL-1␤Ϫ/Ϫ mice, increased caspase-1 expression was seen compared with wild-type animals. Additionally, the number of apoptotic cells assessed by single-stranded DNA immunoreactivity and TUNEL was significantly reduced in IL-1␤Ϫ/Ϫ mice compared with wild-type animals. Conclusions-IL-1␤

Background and Purpose— The clinical course of acute ischemic stroke with large vessel occlusion (LVO) is a multifactorial process with various prognostic factors. We aimed to model this process with machine learning and predict the long-term clinical outcome of LVO before endovascular treatment and to compare our method with previously developed pretreatment scoring methods. Methods— The derivation cohort included 387 LVO patients, and the external validation cohort included 115 LVO patients with anterior circulation who were treated with mechanical thrombectomy. The statistical model with logistic regression without regularization and machine learning algorithms, such as regularized logistic regression, linear support vector machine, and random forest, were used to predict good clinical outcome (modified Rankin Scale score of 0–2 at 90 days) with standard and multiple pretreatment clinical variables. Five previously reported pretreatment scoring methods (the Pittsburgh Response to Endovascular Therapy score, the Stroke Prognostication Using Age and National Institutes of Health Stroke Scale index, the Totaled Health Risks in Vascular Events score, the Houston Intra-Arterial Therapy score, and the Houston Intra-Arterial Therapy 2 score) were compared with these models for the area under the receiver operating characteristic curve. Results— The area under the receiver operating characteristic curve of random forest, which was the worst among the machine learning algorithms, was significantly higher than those of the standard statistical model and the best model among the previously reported pretreatment scoring methods in the derivation (the area under the receiver operating characteristic curve were 0.85±0.07 for random forest, 0.78±0.08 for logistic regression without regularization, and 0.77±0.09 for Stroke Prognostication using Age and National Institutes of Health Stroke Scale) and validation cohorts (the area under the receiver operating characteristic curve were 0.87±0.01 for random forest, 0.56±0.07 for logistic regression without regularization, and 0.83±0.00 for Pittsburgh Response to Endovascular Therapy). Conclusions— Machine learning methods with multiple pretreatment clinical variables can predict clinical outcomes of patients with anterior circulation LVO who undergo mechanical thrombectomy more accurately than previously developed pretreatment scoring methods.

Background and Purpose-The rupture of a cerebral aneurysm is a major cause of subarachnoid hemorrhage, but the mechanism of its development remains unclear. Inducible nitric oxide synthase (iNOS) is expressed in human and rat cerebral aneurysms, and aminoguanidine, a relatively selective inhibitor of iNOS, can decrease the number of the aneurysms in rats. In this study we applied our new mouse model of cerebral aneurysms to the iNOS gene knockout mice and observed experimental cerebral aneurysms in these animals to elucidate the role of iNOS in the process of cerebral aneurysm formation. Methods-Eight C57/Bl6 mice and 16 iNOS knockout mice received a cerebral aneurysm induction procedure. Four months after the operation, the mice were killed, their cerebral arteries were dissected, and the region of the bifurcation of the anterior cerebral artery/olfactory artery was examined histologically and immunohistochemically. Results-No significant difference was seen in the incidence of cerebral aneurysms between iNOSϩ/ϩ and iNOSϪ/Ϫ mice. However, the size of advanced cerebral aneurysms and the number of apoptotic smooth muscle cells were significantly greater in iNOSϩ/ϩ mice than in iNOSϪ/Ϫ mice. Conclusions-Inducible NOS is not necessary for the initiation of cerebral aneurysm. However, the results of this study suggest that regulation of iNOS may have therapeutic potential in the prevention of the progression of cerebral aneurysms.

Background and Purpose— For patients with large vessel occlusion, neuroimaging biomarkers that evaluate the changes in brain tissue are important for determining the indications for mechanical thrombectomy. In this study, we applied deep learning to derive imaging features from pretreatment diffusion-weighted image data and evaluated the ability of these features in predicting clinical outcomes for patients with large vessel occlusion. Methods— This multicenter retrospective study included patients with anterior circulation large vessel occlusion treated with mechanical thrombectomy between 2013 and 2018. We designed a 2-output deep learning model based on convolutional neural networks (the convolutional neural network model). This model employed encoder-decoder architecture for the ischemic lesion segmentation, which automatically extracted high-level feature maps in its middle layers, and used its information to predict the clinical outcome. Its performance was internally validated with 5-fold cross-validation, externally validated, and the results compared with those from the standard neuroimaging biomarkers Alberta Stroke Program Early CT Score and ischemic core volume. The prediction target was a good clinical outcome, defined as a modified Rankin Scale score at 90-day follow-up of 0 to 2. Results— The derivation cohort included 250 patients, and the validation cohort included 74 patients. The convolutional neural network model showed the highest area under the receiver operating characteristic curve: 0.81±0.06 compared with 0.63±0.05 and 0.64±0.05 for the Alberta Stroke Program Early CT Score and ischemic core volume models, respectively. In the external validation, the area under the curve for the convolutional neural network model was significantly superior to those for the other 2 models. Conclusions— Compared with the standard neuroimaging biomarkers, our deep learning model derived a greater amount of prognostic information from pretreatment neuroimaging data. Although a confirmatory prospective evaluation is needed, the high-level imaging features derived by deep learning may offer an effective prognostic imaging biomarker.