Predictive models of clinical outcome of endovascular treatment for anterior circulation stroke using machine learning

Abstract

Background and purpose: Mechanical Thrombectomy (MT) has recently become the standard of care for anterior circulation stroke with large vessel occlusion, but predictive factors of successful MT are still not clearly defined. To tailor treatment individually for each patient, the aim of this study was to evaluate the performances of Machine Learning to predict clinical outcome (mRS) at 3 months after MT.

Material and methods: From the ETIS French prospective multicenter registry, data from patients who underwent MT for anterior circulation stroke with large vessel occlusion between January 2018 and December 2020 were extracted. Three machine learning models (Support Vector Machine, Random Forest and XGBoost) have been trained with clinical, biological and brain imaging data available in emergency conditions from the cohort of patients treated from 2018 to 2019. Models' performances to predict good outcome (3-months mRS <3) were evaluated on patients treated in 2020. Performances were evaluated with AUC, accuracy, sensitivity and specificity, then ROC curves AUC were compared with the best performing model.

Results: 4297 patients were included, 1737 (40 %) with good outcome and 2560 (60 %) with bad outcome were used to train models and 599 patients treated in 2020 were used to evaluate their performances. The best model was obtained with XGBoost: AUC = 0.77, accuracy = 69.3 % but no statistically significant difference existed between models.

Conclusion: Our study shows satisfying performances of machine learning to predict clinical outcome after MT using data easily available at initial diagnosis and before the decision to treat.

Keywords: Machine learning; Outcome; Predictive models; Stroke.