Stroke is the leading cause of disability-adjusted life years (DALYs) in China, imposing a heavy burden on society and families. Endovascular therapy (EVT) has opened the 2.0 era of acute ischemic stroke (AIS) treatment, but still up to 1/3 of patients have poor neurological prognosis. The results of several studies at home and abroad and by our team indicate that anesthesia method and perioperative management are one of the key factors affecting the neurological prognosis of EVT treatment in AIS patients. Based on machine learning big data analysis methods, a prognostic model for EVT treatment of AIS patients can be established to guide individualized treatment decisions. Current prediction models only include patients' baseline variables, and lack the inclusion of intraoperative (anesthesia management and interventional process) and postoperative (intensive monitoring treatment) variables, which limits the clinical application of prediction tools. We will establish a large prospective cohort database including preoperative, intraoperative, and postoperative variables, integrate heterogeneous information from multiple sources based on artificial intelligence machine learning algorithms, and build prognostic prediction models with better clinical applicability and calibration, with the aim of optimizing perioperative management of endovascular therapy, guiding individualized clinical decision-making, and improving patients' clinical prognosis.