Background and Purpose: The clinical use of tirofiban for patients with acute ischemic stroke (AIS) who underwent mechanical thrombectomy (MT) remains controversial. We aimed to evaluate the safety and efficacy of tirofiban combined with MT in AIS patients.Methods: Patients with AIS who underwent MT from January 2014 to December 2018 were enrolled in three stroke units in China. Subgroup analyses were performed based on stroke etiology which was classified according to the Trial of ORG 10172 in Acute Stroke Treatment (TOAST) criteria. Safety outcomes were in-hospital intracerebral hemorrhage (ICH), symptomatic intracerebral hemorrhage (sICH) and mortality at 3-month. Efficacy outcomes were favorable functional outcome and functional independence at 3-month and neurological improvement at 24 h, 3 d and discharge.Results: In patients with large artery atherosclerosis (LAA) stroke, multivariate analyses revealed that tirofiban significantly decreased the odds of in-hospital ICH (adjusted OR = 0.382, 95% CI 0.180–0.809) and tended to increase the odds of favorable functional outcome at 3-month (adjusted OR = 3.050, 95% CI 0.969–9.598). By contrast, in patients with cardioembolism (CE) stroke, tirofiban was not associated with higher odds of favorable functional outcome at 3-month (adjusted OR = 0.719, 95% CI 0.107–4.807), but significantly decreased the odds of neurological improvement at 24 h and 3d (adjusted OR = 0.185, 95% CI 0.047–0.726; adjusted OR = 0.268, 95% CI 0.087–0.825).Conclusions: Tirofiban combined with MT appears to be safe and effective in LAA patients, but has no beneficial effect on CE patients.

Background and Purpose: Accurate prediction of functional outcome after stroke would provide evidence for reasonable post-stroke management. This study aimed to develop a machine learning-based prediction model for 6-month unfavorable functional outcome in Chinese acute ischemic stroke (AIS) patient. Methods: We collected AIS patients at National Advanced Stroke Center of Nanjing First Hospital (China) between September 2016 and March 2019. The unfavorable outcome was defined as modified Rankin Scale score (mRS) 3-6 at 6-month. We developed five machine-learning models (logistic regression, support vector machine, random forest classifier, extreme gradient boosting, and fully-connected deep neural network) and assessed the discriminative performance by the area under the receiver-operating characteristic curve. We also compared them to the Houston Intra-arterial Recanalization Therapy (HIAT) score, the Totaled Health Risks in Vascular Events (THRIVE) score, and the NADE nomogram. Results: A total of 1,735 patients were included into this study, and 541 (31.2%) of them had unfavorable outcomes. Incorporating age, National Institutes of Health Stroke Scale score at admission, premorbid mRS, fasting blood glucose, and creatinine, there were similar predictive performance between our machine-learning models, while they are significantly better than HIAT score, THRIVE score, and NADE nomogram. Conclusions: Compared with the HIAT score, the THRIVE score, and the NADE nomogram, the RFC model can improve the prediction of 6-month outcome in Chinese AIS patients.

No abstract