Related Experiment Video
Updated: Sep 5, 2025
Optimized Management of Endovascular Treatment for Acute Ischemic Stroke
Published on: January 18, 2018
Multivariable Prediction Model for Futile Recanalization Therapies in Patients With Acute Ischemic Stroke
Thomas Raphael Meinel1, Christine Lerch2, Urs Fischer2
1From the Department of Neurology (T.M., C.L., M.B., B.S., A.S., M.M., M.G., D.S., S.J., M.A.), University Hospital Bern, Inselspital, University of Bern; Department of Neurology and Stroke Center (U.F.), University Hospital Basel and University of Basel; University Institute of Diagnostic and Interventional Neuroradiology (A.M., C.K., N.F.B., T.D., J.G., R.W., R.M., J.K.), Support Center for Advanced Neuroimaging (R.W., R.M., J.K.), and Department of Diagnostic, Paediatric and Interventional Radiology (J.K.), University Hospital Bern, Inselspital, University of Bern, Switzerland. thomas.meinel@insel.ch.
Background And Objectives:
Very poor outcome despite IV thrombolysis (IVT) and mechanical thrombectomy (MT) occurs in approximately 1 of 4 patients with ischemic stroke and is associated with a high logistic and economic burden. We aimed to develop and validate a multivariable prognostic model to identify futile recanalization therapies (FRTs) in patients undergoing those therapies.
Methods:
Patients from a prospectively collected observational registry of a single academic stroke center treated with MT and/or IVT were included. The data set was split into a training (N = 1,808, 80%) and internal validation (N = 453, 20%) cohort. We used gradient boosted decision tree machine learning models after k-nearest neighbor imputation of 32 variables available at admission to predict FRT defined as modified Rankin scale 5-6 at 3 months. We report feature importance, ability for discrimination, calibration, and decision curve analysis.
Results:
A total of 2,261 patients with a median (interquartile range) age of 75 years (64-83 years), 46% female, median NIH Stroke Scale 9 (4-17), 34% IVT alone, 41% MT alone, and 25% bridging were included. Overall, 539 (24%) had FRT, more often in MT alone (34%) as compared with IVT alone (11%). Feature importance identified clinical variables (stroke severity, age, active cancer, prestroke disability), laboratory values (glucose, C-reactive protein, creatinine), imaging biomarkers (white matter hyperintensities), and onset-to-admission time as the most important predictors. The final model was discriminatory for predicting 3-month FRT (area under the curve 0.87, 95% CI 0.87-0.88) and had good calibration (Brier 0.12, 0.11-0.12). Overall performance was moderate (F1-score 0.63 ± 0.004), and decision curve analyses suggested higher mean net benefit at lower thresholds of treatment (up to 0.8).
Conclusions:
This FRT prediction model can help inform shared decision making and identify the most relevant features in the emergency setting. Although it might be particularly useful in low resource healthcare settings, incorporation of further multifaceted variables is necessary to further increase the predictive performance.
