BACKGROUND AND PURPOSE: Current stroke care recommendations for patient selection for mechanical thrombectomy in the extended time window demand advanced imaging to determine the stroke core volume and hypoperfusion mismatch, which may not be available at every center. We aimed to determine outcomes in patients selected for mechanical thrombectomy solely on the basis of noncontrast CT and CTA in the early (,6-hour) and extended ($6-hour) time windows. MATERIALS AND METHODS:Consecutive mechanical thrombectomies performed for acute large-vessel occlusion ischemic (ICA, M1, M2) stroke between February 2016 and August 2020 were retrospectively reviewed. Eligibility was based solely on demographics and noncontrast CT (ASPECTS) and CTA, due to the limited availability of perfusion imaging during the study period. Propensity score matching was performed to compare outcomes between time windows. RESULTS:Of 417 mechanical thrombectomies performed, 337 met the inclusion criteria, resulting in 205 (60.8%) and 132 (39.2%) patients in the 0-to 6-and 6-to 24-hour time windows, respectively. The ASPECTS was higher in the early time window (9; interquartile range ¼ 8-10) than the extended time window (9; interquartile range ¼ 7-10; P ¼ .005). Propensity score matching yielded 112 well-matched pairs. Equal rates of TICI 2b/3 revascularization and symptomatic intracranial hemorrhage were observed. A favorable functional outcome (mRS 0-2) at 90 days was numerically more frequent in the early window (45.5% versus 33.9%, P ¼ .091). Mortality was numerically more frequent in the early window (25.9% versus 17.0%, P ¼ .096).CONCLUSIONS: Patients selected for mechanical thrombectomy in the extended time window solely on the basis of noncontrast CT and CTA still achieved decent rates of favorable 90-day functional outcomes, not statistically different from patients in the early time window.
Background and Purpose: Hospital readmissions impose a substantial burden on the healthcare system. Reducing readmissions after stroke could lead to improved quality of care especially since stroke is associated with a high rate of readmission. The goal of this study is to enhance our understanding of the predictors of 30-day readmission after ischemic stroke and develop models to identify high-risk individuals for targeted interventions.Methods: We used patient-level data from electronic health records (EHR), five machine learning algorithms (random forest, gradient boosting machine, extreme gradient boosting–XGBoost, support vector machine, and logistic regression-LR), data-driven feature selection strategy, and adaptive sampling to develop 15 models of 30-day readmission after ischemic stroke. We further identified important clinical variables.Results: We included 3,184 patients with ischemic stroke (mean age: 71 ± 13.90 years, men: 51.06%). Among the 61 clinical variables included in the model, the National Institutes of Health Stroke Scale score above 24, insert indwelling urinary catheter, hypercoagulable state, and percutaneous gastrostomy had the highest importance score. The Model's AUC (area under the curve) for predicting 30-day readmission was 0.74 (95%CI: 0.64–0.78) with PPV of 0.43 when the XGBoost algorithm was used with ROSE-sampling. The balance between specificity and sensitivity improved through the sampling strategy. The best sensitivity was achieved with LR when optimized with feature selection and ROSE-sampling (AUC: 0.64, sensitivity: 0.53, specificity: 0.69).Conclusions: Machine learning-based models can be designed to predict 30-day readmission after stroke using structured data from EHR. Among the algorithms analyzed, XGBoost with ROSE-sampling had the best performance in terms of AUC while LR with ROSE-sampling and feature selection had the best sensitivity. Clinical variables highly associated with 30-day readmission could be targeted for personalized interventions. Depending on healthcare systems' resources and criteria, models with optimized performance metrics can be implemented to improve outcomes.
BackgroundTenecteplase (TNK) is a genetically modified variant of alteplase (TPA) and has been established as a non-inferior alternative to TPA in acute ischemic stroke (AIS). Whether TNK exerts distinct benefits in large vessel occlusion (LVO) AIS is still being investigated.ObjectiveTo describe our first-year experience after a healthcare system-wide transition from TPA to TNK as the primary thrombolytic.MethodsPatients with AIS who received intravenous thrombolytics between January 2020 and August 2022 were retrospectively reviewed. All patients with LVO considered for mechanical thrombectomy (MT) were included in this analysis. Spontaneous recanalization (SR) after TNK/TPA was a composite variable of reperfusion >50% of the target vessel territory on cerebral angiography or rapid, significant neurological recovery averting MT. Propensity score matching (PSM) was performed to compare SR rates between TNK and TPA.ResultsA total of 148 patients were identified; 51/148 (34.5%) received TNK and 97/148 (65.5%) TPA. The middle cerebral arteries M1 (60.8%) and M2 (29.7%) were the most frequent occlusion sites. Baseline demographics were comparable between TNK and TPA groups. Spontaneous recanalization was significantly more frequently observed in the TNK than in the TPA groups (unmatched: 23.5% vs 10.3%, P=0.032). PSM substantiated the observed SR rates (20% vs 10%). Symptomatic intracranial hemorrhage, 90-day mortality, and functional outcomes were similar.ConclusionsThe preliminary experience from a real-world setting demonstrates the effectiveness and safety of TNK before MT. The higher spontaneous recanalization rates with TNK are striking. Additional studies are required to investigate whether TNK is superior to TPA in LVO AIS.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.