Search

Estimating the rupture risk of small intracranial aneurysms (IAs) to determine whether to treat is difficult 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 stratified 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 five ML models applying diverse algorithms including random forest classifier (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% confidence 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 significantly (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: Long non-coding RNAs (LncRNAs) have been reported to play important roles in the pathogenesis and development of many diseases, including cerebral ischemia and reperfusion (I/R) injury. In this study, we aimed to investigate the role of LncRNA-Potassium Voltage-Gated Channel Subfamily Q Member 1 opposite strand/antisense transcript 1 (KCNQ1OT1) in cerebral I/R induced neuronal injury, and its underlying mechanisms. Methods: Primary mouse cerebral cortical neurons treated with oxygen-glucose deprivation and reoxygenation (OGD/R) in vitro and mice subjected to middle cerebral artery occlusion (MCAO) and reperfusion were used to mimic cerebral I/R injury. Small inference RNA (siRNA) was used to knockdown KCNQ1OT1 or microRNA-153-3p (miR-153-3p). Dual-luciferase assay was performed to detect the interaction between KCNQ1OT1 and miR-153-3p and interaction between miR-153-3p and Fork head box O3a (Foxo3). Flow cytometry analysis was performed to detect neuronal apoptosis. qRT-PCR and Western blotting were performed to detect RNA and protein expressions. Results: KCNQ1OT1 and Foxo3 expressions were significantly increased in neurons subjected to I/R injury in vitro and in vivo, and miR-153-3p expression were significantly decreased. Knockdown of KCNQ1OT1 or overexpression of miR-153-3p weakened OGD/R-induced neuronal injury and regulated Foxo3 expressions. Dual-luciferase analysis showed that KCNQ1OT1 directly interacted with miR-153-3p and Foxo3 is a direct target of miR-153-3p. Conclusions: Our results indicate that LncRNA-KCNQ1OT1 promotes OGD/R-induced neuronal injury at least partially through acting as a competing endogenous RNA (ceRNA) for miR-153-3p to regulate Foxo3a expression, suggesting LncRNA-KCNQ1OT1 as a potential therapeutic target for cerebral I/R injury.

According to the higher security of higher-dimensional chaotic system, a new scheme of quantum image encryption and decryption based on Lorenz hyper-chaotic system is proposed. The encryption process is mainly divided into two parts: the location information scrambling process and the color information replacement process. In the location information scrambling process, the pseudo-random sequence obtained by the Lorenz hyper-chaotic system is first sorted to obtain the corresponding position index sequence, and then the rows and columns of the position information are scrambled by the index sequence. In the process of color replacement, the change of pixel value is firstly diffused to each pixel through chaotic sequence, and then the information of each pixel is confused, so as to realize the process of color information replacement. Experimental analysis shows that the encryption scheme in this paper has a good effect.

titanium alloy cutting force testing experiment of end-surface turning is made, and spectrum character is analyzed by obtained data of cutting force experiment, and ten the influencing rule of cutting parameter on cutting force character is discovered; using the similarity between tools vibration character and cutting force spectrum character, and based on obtained data of machined surface roughness testing experiment, the two characteristic parameters of vibration frequency and amplitude value relative to work piece is calculated, and the relationship curve between cutting parameters and tools vibration character parameter is established is this paper.