Search

Background Identification of futile recanalisation following endovascular therapy (EVT) in patients with acute ischaemic stroke is both crucial and challenging. Here, we present a novel risk stratification system based on hybrid machine learning method for predicting futile recanalisation.Methods Hybrid machine learning models were developed to address six clinical scenarios within the EVT and perioperative management workflow. These models were trained on a prospective database using hybrid feature selection technique to predict futile recanalisation following EVT. The optimal model was validated and compared with existing models and scoring systems in a multicentre prospective cohort to develop a hybrid machine learning-based risk stratification system for futile recanalisation prediction.Results Using a hybrid feature selection approach, we trained and tested multiple classifiers on two independent patient cohorts (n=1122) to develop a hybrid machine learning-based prediction model. The model demonstrated superior discriminative ability compared with other models and scoring systems (area under the curve=0.80, 95% CI 0.73 to 0.87) and was transformed into a web application (RESCUE-FR Index) that provides a risk stratification system for individual prediction (accessible online at fr-index.biomind.cn/RESCUE-FR/).Conclusions The proposed hybrid machine learning approach could be used as an individualised risk prediction model to facilitate adherence to clinical practice guidelines and shared decision-making for optimal candidate selection and prognosis assessment in patients undergoing EVT.

Background and purpose In-stent restenosis (ISR) is one of the long-term adverse outcomes of endovascular angioplasty and stenting for symptomatic intracranial arterial stenosis. In this study, we try to evaluate the safety and efficacy of endovascular treatment for intracranial ISR. Methods We retrospectively collected patients with intracranial ISR who underwent endovascular treatment from June 2012 to August 2019 at a high-volume stroke center. Successful recanalization was defined as ≤30% residual stenosis. Stroke, myocardial infarction, and death after stenting within 30 days were used to evaluate periprocedural safety. Recurrent stroke in the territory of the culprit vessel and re-ISR in patients with clinical and vascular imaging follow-up data were used to evaluate the long-term outcome. Results 32 patients (59.6±7.2 years old) with ISR were recruited, including 22 patients (68.8%) treated with balloon dilatation, 8 patients (25%) with stenting, and 2 patients (6.3%) with failed procedures. Successful recanalization was achieved in 71.9% (23/32) of patients. There was no stroke, myocardial infarction or death within 30 days after the procedure. Recurrent stroke was found in 10.7% (3/28) of the patients, and re-ISR was found in 42.1% (8/19) of the patients. The re-ISR rate was lower in patients with stenting than in those with balloon dilatation (0% vs 57.1%, p=0.090), and in patients with successful recanalization than in those with unsuccessful recanalization (33.3% vs 75.0%, p=0.352), but with no statistically significant difference. Conclusions The periprocedural safety of endovascular treatment for intracranial ISR may be acceptable, but the long-term rates of recurrent stroke and re-ISR remain at high levels. [ABSTRACT FROM AUTHOR]