Background: Prognosis, recurrence rate, and secondary prevention strategies differ by different etiologies in acute ischemic stroke. However, identifying its cause is challenging.Objective: This study aimed to develop a model to identify the cause of stroke using machine learning (ML) methods and test its accuracy.Methods: We retrospectively reviewed the data of patients who had determined etiology defined by the Trial of ORG 10172 in Acute Stroke Treatment (TOAST) from CASE-II (NCT04487340) to train and evaluate six ML models, namely, Random Forests (RF), Logistic Regression (LR), Extreme Gradient Boosting (XGBoost), K-Nearest Neighbor (KNN), Ada Boosting, Gradient Boosting Machine (GBM), for the detection of cardioembolism (CE), large-artery atherosclerosis (LAA), and small-artery occlusion (SAO). Between October 2016 and April 2020, patients were enrolled consecutively for algorithm development (phase one). Between June 2020 and December 2020, patients were enrolled consecutively in a test set for algorithm test (phase two). Area under the curve (AUC), precision, recall, accuracy, and F1 score were calculated for the prediction model.Results: Finally, a total of 18,209 patients were enrolled in phase one, including 13,590 patients (i.e., 6,089 CE, 4,539 LAA, and 2,962 SAO) in the model, and a total of 3,688 patients were enrolled in phase two, including 3,070 patients (i.e., 1,103 CE, 1,269 LAA, and 698 SAO) in the model. Among the six models, the best models were RF, XGBoost, and GBM, and we chose the RF model as our final model. Based on the test set, the AUC values of the RF model to predict CE, LAA, and SAO were 0.981 (95%CI, 0.978–0.986), 0.919 (95%CI, 0.911–0.928), and 0.918 (95%CI, 0.908–0.927), respectively. The most important items to identify CE, LAA, and SAO were atrial fibrillation and degree of stenosis of intracranial arteries.Conclusion: The proposed RF model could be a useful diagnostic tool to help neurologists categorize etiologies of stroke.Clinical Trial Registration: [www.ClinicalTrials.gov], identifier [NCT01274117].

Introduction: The best management strategy still remains strong controversy for acute nonarteritic central retinal artery occlusion (CRAO). We thus performed a meta-analysis to determine the efficacy of intra-arterial thrombolysis (IAT) for visual improvement according to different times from symptom onset. Methods: We searched EMBASE, PubMed, and Web of Science for relevant studies assessing efficiency of IAT in patients with CRAO compared with standard therapy. Fixed-effects and random-effects models were performed. Results: Five eligible studies including 459 patients with acute CRAO were pooled in the meta-analysis. In all, 219 (47.7%) received IAT, and the mean time from symptom onset to IAT was 13 h. The pooled analysis demonstrates odds ratio (OR) for the procedure of IAT and any visual improvement to be 1.520 (95% confidence intervals [CIs] 1.258–1.837; p < 0.001). Subgroup analyses further indicated that the CRAO patients who received IAT achieved any visual improvement more easily within 6 h from symptom onset (OR = 1.703, 95% CI 1.219–2.381; p = 0.002), but not those beyond 6 h (OR = 1.260, 95% CI 0.973–1.632; p = 0.080). Conclusion: Our meta-analysis of available published data supports IAT to be an alternative treatment option for CRAO patients within 6 h from symptom onset.

Background: Uric acid (UA) has both antioxidative and pro-oxidative properties. The study aimed to investigate the relationship between serum UA and hemorrhagic transformation (HT) after intravenous thrombolysis in patients with acute ischemic stroke. Methods: The patients undergoing intravenous thrombolysis from two hospitals in China were retrospectively analyzed. HT was evaluated using computed tomography images reviewed within 24- 36h after thrombolysis. Symptomatic intracranial hemorrhage (sICH) was defined as HT accompanied by worsening neurological function. Multivariate logistic regression and spline regression models were performed to explore the relationship between serum UA levels and the risk of HT and sICH. Results: Among 503 included patients, 60 (11.9%) were diagnosed with HT and 22 (4.4%) developed sICH. Patients with HT had significant lower serum UA levels than those without HT (245 [214-325 vs. 312 [256-370] μmol/L, p < 0.001). Multivariable logistic regression analysis indicated that patients with higher serum UA levels had a lower risk of HT (OR per 10-μmol/L increase 0.96, 95%CI 0.92–0.99, p = 0.015). Furthermore, multiple-adjusted spline regression models showed a Ushaped association between serum UA levels and HT (p < 0.001 for non-linearity). Similar results were present between serum UA and sICH. Restricted cubic spline models predicted the lowest risk of HT and sICH when the serum UA levels were 386μmol/L. Conclusion: The data show the U-shaped relationship between serum UA levels and the risk of HT and sICH after intravenous thrombolysis.

BACKGROUND Here, we present a unique case of mitochondrial encephalomyopathy with lactic acidosis and stroke-like episodes (MELAS) syndrome, which initially appeared to be autoimmune encephalitis and was ultimately confirmed as MELAS with the mitochondrial DNA 3243A>G mutation.CASE SUMMARY A 58-year-old female presented with acute-onset speech impediment and auditory hallucinations, symmetrical bitemporal lobe abnormalities, clinical and laboratory findings, and a lack of relevant prodromal history, which suggested diagnosis of autoimmune encephalitis. Further work-up, in conjunction with the patient's medical history, family history, and lactate peak on brain lesions on magnetic resonance imaging, suggested a mitochondrial disorder. Mitochondrial genome analysis revealed the m.3243A>G variant in the MT-TL1 gene, which led to a diagnosis of MELAS syndrome.CONCLUSION This case underscores the importance of considering MELAS as a potential cause of autoimmune encephalitis even if patients are over 40 years of age, as the symptoms and signs are atypical for MELAS syndrome.

Introduction This study aimed to investigate the association between atrial fibrillation (AF), particularly newly diagnosed AF, and remote intracerebral hemorrhage (rICH) in patients with ischemic stroke who were treated with intravenous thrombolysis (IVT). Methods This observational study was conducted on patients with ischemic stroke who received IVT with recombinant tissue-type plasminogen activator. The data were taken from a multicenter prospective registry of a Chinese population. rICH was defined as any extraischemic hemorrhage detected on computerized tomography (CT) 24 h after intravenous thrombolysis. We collected and compared the demographic data and clinical characteristics of all the patients with rICH to those of patients without any type of hemorrhagic transformation. The association between AF and rICH was analyzed using univariate analysis and binary logistic regression. Results A total of 20,697 patients were included in the study, with 1566 (7.6%) experiencing intracerebral hemorrhage (ICH), 586 (2.8%) experiencing rICH, and 19,131 (92.4%) not experiencing any form of hemorrhagic transformation. Univariate analysis revealed significant differences in age, pre-thrombolysis systolic blood pressure, baseline National Institute of Health Stroke Scale score, previously known AF, newly diagnosed AF, coronary heart disease, congestive heart failure, hyperhomocysteinemia, and history of thrombolysis between the rICH and control groups (P < 0.05). Further multivariate logistic regression analysis indicated that total AF (OR 1.821, 95% CI 1.082–3.065, P < 0.05), previously known AF (OR 1.470, 95% CI 1.170–1.847), and newly diagnosed AF (OR 1.920, 95% CI 1.304–2.825) were independently associated with rICH. Conclusions This study suggests that AF, regardless of whether it is newly diagnosed or previously known, may be associated with the occurrence of rICH following intravenous thrombolysis. Interestingly, our findings suggest that newly diagnosed AF may have a stronger impact on rICH than previously known AF, although confirmation from more studies is needed.