No abstract

Estimating the rupture risk of small intracranial aneurysms (IAs) to determine whether to treat is di cult but crucial. We aimed to construct and external validation a convenient machine learning (ML) model for assessing the rupture risk of small IAs.1004 patients with small IAs recruited from two hospitals were included in our retrospective research. The patients at hospital 1 were strati ed into training (70%) and internal validation set (30%) randomly, and the patients at hospital 2 were used for external validation. We selected predictive features using the least absolute shrinkage and selection operator (LASSO) method, and constructed ve ML models applying diverse algorithms including random forest classi er (RFC), categorical boosting (CatBoost), support vector machine (SVM) with linear kernel, light gradient boosting machine (LightGBM) and extreme gradient boosting (XGBoost). The Shapley Additive Explanations (SHAP) analysis provided interpretation for the best ML model.The training, internal and external validation cohorts included 658, 282, and 64 IAs, respectively. The best performance was presented by SVM as AUC of 0.817 in the internal [95% con dence interval (CI), 0.769-0.866] and 0.893 in the external (95% CI, 0.808-0.979) validation cohorts, overperformed than the PHASES score signi cantly (all P < 0.001). SHAP analysis showed maximum size, location and irregular shape were the top three important features to predict rupture. Our SVM model based on readily accessible features presented satisfying ability of discrimination in predicting the rupture IAs with small size. Morphological parameters made important contributions to prediction result.

Background and purposeFutile recanalization occurs in a significant proportion of patients with basilar artery occlusion (BAO) after endovascular thrombectomy (EVT). Therefore, our goal was to develop a visualized nomogram model to early identify patients with BAO who would be at high risk of futile recanalization, more importantly, to aid neurologists in selecting the most appropriate candidates for EVT.MethodsPatients with BAO with EVT and the Thrombolysis in Cerebral Infarction score of ≥2b were included in the National Advanced Stroke Center of Nanjing First Hospital (China) from October 2016 to June 2021. The exclusion criteria were lacking the 3-month Modified Rankin Scale (mRS), age &lt;18 years, the premorbid mRS score &gt;2, and unavailable baseline CT imaging. Potential predictors were selected for the construction of the nomogram model and the predictive and calibration capabilities of the model were assessed.ResultsA total of 84 patients with BAO were finally enrolled in this study, and patients with futile recanalization accounted for 50.0% (42). The area under the curve (AUC) of the nomogram model was 0.866 (95% CI, 0.786–0.946). The mean squared error, an indicator of the calibration ability of our prediction model, was 0.025. A web-based nomogram model for broader and easier access by clinicians is available online at https://trend.shinyapps.io/DynNomapp/.ConclusionWe constructed a visualized nomogram model to accurately and online predict the risk of futile recanalization for patients with BAO, as well as assist in the selection of appropriate candidates for EVT.

DLC (i.v.), given after an allergen challenge, improved Th1 cytokines level and restrained Th2 responses alleviating the symptoms of AR. Our results indicate that DLC injection may exhibit such effects through the modulation of T-cell responses.