Objectives: This study aimed to assess the accuracy of artificial intelligence (AI) models in predicting the prognosis of stroke.Methods: We searched PubMed, Embase, and Web of Science databases to identify studies using AI for acute stroke prognosis prediction from the database inception to February 2023. Selected studies were designed cohorts and had complete data. We used the Quality Assessment of Diagnostic Accuracy Studies tool to assess the qualities and bias of included studies and used a random-effects model to summarize and analyze the data. We used the area under curve (AUC) as an indicator of the predictive accuracy of AI models.Results: We retrieved a total of 1,241 publications and finally included seven studies. There was a low risk of bias and no significant heterogeneity in the final seven studies. The total pooled AUC under the fixed-effects model was 0.872 with a 95% CI of (0.862–0.881). The DL subgroup showed its AUC of 0.888 (95%CI 0.872–0.904). The LR subgroup showed its AUC 0.852 (95%CI 0.835–0.869). The RF subgroup showed its AUC 0.863 (95%CI 0.845–0.882). The SVM subgroup showed its AUC 0.905 (95%CI 0.857–0.952). The Xgboost subgroup showed its AUC 0.905 (95%CI 0.805–1.000).Conclusion: The accuracy of AI models in predicting the outcomes of ischemic stroke is good from our study. It could be an assisting tool for physicians in judging the outcomes of stroke patients. With the update of AI algorithms and the use of big data, further AI predictive models will perform better.

Objective: To identify risk factors for haemorrhagic transformation in Chinese patients with acute ischaemic stroke treated with recombinant tissue plasminogen activator. Methods: We searched electronic databases including PubMed, EMBASE, CNKI and WanFang Data for studies reporting risk factors of haemorrhagic transformation after intravenous thrombolysis. Pooled OR, weighted mean difference (WMD) and 95% CI were estimated. Meta-analysis was performed by using Stata V.14.0 software. Results: A total of 14 studies were included. The results indicated that older age (WMD=3.46, 95% CI 2.26 to 4.66, I²=47), atrial fibrillation (OR 2.66, 95% CI 1.85 to 3.81, I²=28), previous stroke (OR 1.68, 95% CI 1.08 to 2.60, I²=14), previous antiplatelet treatment (OR 1.67, 95% CI 1.17 to 2.38, I²=0), higher National Institute of Health stroke scale scores (OR 1.10, 95% CI 1. 05 to 1.15, I²=36), systolic (WMD=4.75, 95% CI 2.50 to 7.00, I²=42) or diastolic (WMD=2.67, 95% CI 1.08 to 4.26, I²=35) pressure, and serum glucose level (WMD=1.44, 95% CI 0.62 to 2.26, I²=66) were associated with increased risk of post-thrombolysis haemorrhagic transformation. Conclusion: The current meta-analysis identified eight risk factors for post-thrombolysis haemorrhagic transformation in Chinese patients with acute ischaemic stroke. Given the risk of bias, these results should be explained with caution and do not justify withholding intravenous thrombolysis.

Background: Mutations of cyclooxygenase gene (COX gene) may increase the susceptibility of ischemic stroke. We investigated five variants (rs5788, rs1330344, rs3842788, rs20417, and rs689466) of two COX genes in order to explaining the association between these polymorphisms and we also investigated the association between these variants and ischemic stroke risk to determine whether gene–gene interaction between these genes increases the susceptibility of ischemic stroke or its subtypes. Methods: A total of 1981 study subjects (1078 cases and 903 control subjects) were recruited. The interaction of multiple factors was investigated using Multifactor Dimensionality Reduction. The additive effect of single nucleotide polymorphisms on ischemic stroke or its subtypes were analyzed by multiple factor logistic regression. Results: At COX-1(rs1330344), AA genotype carriers had a lower susceptibility of ischemic stroke (OR = 0.657, 95%CI = 0.437–0.988, P = 0.044), and A allele carriers had a lower susceptibility of ischemic stroke (OR = 0.812, 95%CI = 0.657–0.978, P = 0.029). At COX-1(rs3842788), AA genotype carriers had a higher susceptibility of ischemic stroke (OR = 5.203, 95% CI = 1.519–5.159, P = 0.016). At COX-2 (rs689466), AA genotype carriers had a higher susceptibility of large-artery atherosclerosis (OR = 1.404, 95% CI = 1.019–1.934, P = 0.038). COX-1(rs1330344, rs3842788) and COX-2 rs689466 interacted in SVO, but had no additive effect with ischemic stroke and other subtypes. Conclusions: At rs1330344, AA genotype may reduce the susceptibility of ischemic stroke. At rs3842788, AA genotype may increase the susceptibility of ischemic stroke. At rs689466, AA genotype may increase the susceptibility of large-artery atherosclerosis (LAA). COX − 1(rs1330344, rs3842788) and COX-2 rs689466 interacted in small vessel occlusion (SVO), but had no additive effect with ischemic stroke and other subtypes.

Injection of autologous fat on the face is a commonly performed procedure in plastic surgery. However, it can lead to rare but devastating complications due to fat embolism. In this study, we presented two cases of cerebral infarction and/or sudden vision loss after cosmetic injections of autologous fat on the face. Two women underwent injections into the temporal and frontal areas, respectively. In case 1, the patient underwent decompressive craniectomy as her condition deteriorated continuously and died. In case 2, the patient's vision had not improved at the 3-month follow-up visit. Imaging examinations showed occlusion of the right external carotid artery in case 1, and multiple retinal arterioles were segmentally occluded in case 2. We also screened relevant studiesviaa systematic search of PubMed (last updated on May 9, 2020) and performed a narrative review due to the significant heterogeneity between the studies. To prevent this catastrophic event, the autologous fat injection should be performed carefully. If embolization does occur, early diagnosis and timely treatment may help improve functional outcomes.

NGF is involved in the process of autophagy; however, the underlying mechanisms of proNGF/NGF on autophagy in cerebral ischemia‐reperfusion (CIR) remain unclear. This study explored the potential pathway of proNGF/NGF in mediating autophagy and apoptosis and thereby contributed to poststroke neurological rehabilitation. In this study, PC12 cell lines and male SD rats were used to simulate CIR; it was found that within 24 h reperfusion, proNGF was the predominant form of Ngf while after 24 h NGF was produced by proNGF transformation. The mature NGF was found to protect neurons against autophagic and apoptotic damage caused by CIR, but proNGF can cause both autophagic and apoptotic neuronal damage. The protective effect of NGF is associated with the activation of the PI3K/Akt/mTOR and ERK pathway and, as well as the change of autophagy‐related proteins. On the other hand, proNGF promoted the ERK pathway increasing autophagy and affected the apoptosis‐related proteins in vivo and in vitro. These results were also verified in male SD rats with CIR that neurological deficit caused by CIR can be rescued by recombinant and wild‐type NGF, and vice‐versa by proNGF.