- The study investigates "futile recanalization," which happens when endovascular thrombectomy (EVT) is technically successful but does not yield good results for patients with acute ischemic stroke caused by large vessel occlusion (LVO).
- Using machine learning (ML) algorithms, researchers developed predictive models to assess risk factors associated with futile recanalization, with a focus on both baseline and peri-interventional characteristics from 312 patients.
- The "Late" XGBoost model showed high predictive accuracy (AUC of 0.910), identifying key factors like NIHSS after 24 hours and age, highlighting the importance of including peri-interventional data for better predictions.