Acute ischemic stroke outcomes in patients with COVID-19: a systematic review and meta-analysis.

BACKGROUND: Although patients with COVID-19 have a higher risk of acute ischemic stroke (AIS), the impact on stroke outcomes remains uncertain. AIMS: To determine the clinical outcomes of patients with AIS and COVID-19 (AIS-COVID+). METHODS: We performed a systematic review and meta-analysis following the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines. Our protocol was registered with the International Prospective Register of Systematic Reviews (CRD42020211977). Systematic searches were last performed on June 3, 2021 in EMBASE, PubMed, Web-of-Science, Scopus, and CINAHL Databases. INCLUSION CRITERIA: (1) studies reporting outcomes on AIS-COVID+; (2) original articles published in 2020 or later; (3) study participants aged ≥18 years. EXCLUSION CRITERIA: (1) case reports with <5 patients, abstracts, review articles; (2) studies analyzing novel interventions. Risk of bias was assessed using the Mixed Methods Appraisal Tool. Random-effects models estimated the pooled OR and 95% confidence intervals (95% CI) for mortality, modified Rankin Scale (mRS) score, length of stay (LOS), and discharge disposition. RESULTS: Of the 43 selected studies, 46.5% (20/43) reported patients with AIS without COVID-19 (AIS-COVID-) for comparison. Random-effects model included 7294 AIS-COVID+ and 158 401 AIS-COVID-. Compared with AIS-COVID-, AIS-COVID+ patients had higher in-hospital mortality (OR=3.87 (95% CI 2.75 to 5.45), P<0.001), less mRS scores 0-2 (OR=0.53 (95% CI 0.46 to 0.62), P<0.001), longer LOS (mean difference=4.21 days (95% CI 1.96 to 6.47), P<0.001), and less home discharge (OR=0.31 (95% CI 0.21 to 0.47), P<0.001). CONCLUSIONS: Patients with AIS-COVID had worse outcomes, with almost fourfold increased mortality, half the odds of mRS scores 0-2, and one-third the odds of home discharge. These findings confirm the significant impact of COVID-19 on early stroke outcomes.

Prediction of bleb formation in intracranial aneurysms using machine learning models based on aneurysm hemodynamics, geometry, location, and patient population.

BACKGROUND: Bleb presence in intracranial aneurysms (IAs) is a known indication of instability and vulnerability. OBJECTIVE: To develop and evaluate predictive models of bleb development in IAs based on hemodynamics, geometry, anatomical location, and patient population. METHODS: Cross-sectional data (one time point) of 2395 IAs were used for training bleb formation models using machine learning (random forest, support vector machine, logistic regression, k-nearest neighbor, and bagging). Aneurysm hemodynamics and geometry were characterized using image-based computational fluid dynamics. A separate dataset with 266 aneurysms was used for model evaluation. Model performance was quantified by the area under the receiving operating characteristic curve (AUC), true positive rate (TPR), false positive rate (FPR), precision, and balanced accuracy. RESULTS: The final model retained 18 variables, including hemodynamic, geometrical, location, multiplicity, and morphology parameters, and patient population. Generally, strong and concentrated inflow jets, high speed, complex and unstable flow patterns, and concentrated, oscillatory, and heterogeneous wall shear stress patterns together with larger, more elongated, and more distorted shapes were associated with bleb formation. The best performance on the validation set was achieved by the random forest model (AUC=0.82, TPR=91%, FPR=36%, misclassification error=27%). CONCLUSIONS: Based on the premise that aneurysm characteristics prior to bleb formation resemble those derived from vascular reconstructions with their blebs virtually removed, machine learning models can identify aneurysms prone to bleb development with good accuracy. Pending further validation with longitudinal data, these models may prove valuable for assessing the propensity of IAs to progress to vulnerable states and potentially rupturing.