Jakob Sommer ^1,2 Fiona Dierksen ¹ Tal Zeevi ^1,3 ANH TUAN TRAN ¹ Emily Avery ^1,4 Adrian Mak ^1,5 Ajay Malhotra ¹ Charles C. Matouk ⁶ Guido J. Falcone ^7,8 Victor Torres-Lopez ⁷ Sanjay Aneja ⁹ James Duncan ^1,3 Lauren Sansing ^7,8 Kevin N. Sheth ^7,8 Seyedmehdi Payabvash ^1,8*

• ¹ Department of Radiology and Biomedical Imaging, School of Medicine, Yale University, New Haven, Connecticut, United States
• ² Institute of Clinical Pharmacology, University Hospital RWTH Aachen, Aachen, Germany
• ³ Department of Biomedical Engineering, School of Engineering and Applied Science, Yale University, New Haven, Connecticut, United States
• ⁴ Department of Radiology, School of Medicine, University of California, San Diego, La Jolla, California, United States
• ⁵ Charite Lab for Artificial Intelligence in Medicine, Charite University Medicine Berlin, Berlin, Baden-Württemberg, Germany
• ⁶ Department of Neurosurgery, School of Medicine, Yale University, New Haven, Connecticut, United States
• ⁷ Department of Neurology, School of Medicine, Yale University, New Haven, Connecticut, United States
• ⁸ Center for Brain and Mind Health, School of Medicine, Yale University, New Haven, Connecticut, United States
• ⁹ Department of Radiation Oncology, Yale School of Medicine, New Haven, CT, United States

Computed Tomography Angiography (CTA) is the first line of imaging in the diagnosis of Large Vessel Occlusion (LVO) strokes. We trained and independently validated end-to-end automated deep-learning pipelines to predict 3-month outcomes after anterior circulation LVO thrombectomy based on admission CTAs. We split a dataset of 591 patients into training/cross-validation (n=496) and independent test set (n=95). We trained separate models for outcome prediction based on admission "CTA" images alone, "CTA+Treatment" (including time to thrombectomy and reperfusion success information), and "CTA+Treatment+Clinical" (including admission age, sex, and NIH stroke scale). A binary (favorable) outcome was defined based on a 3-month modified Rankin Scale≤2. The model was trained on our dataset based on the pre-trained ResNet-50 3D Convolutional Neural Network ("MedicalNet") and included CTA preprocessing steps. We generated an ensemble model from the 5-fold cross-validation, and tested it in the independent test cohort, with receiver operating characteristic area under the curve (AUC, 95% confidence interval) of 70 (0.59-0.81) for "CTA", 0.79 (0.70-0.89) for "CTA+Treatment", and 0.86 (0.79-0.94) for "CTA+Treatment+Clinical" input models. A "Treatment+Clinical" logistic regression model achieved an AUC of 0.86 (0.79-0.93). Our results show the feasibility of an end-to-end automated model to predict outcomes from admission and post-thrombectomy reperfusion success. Such a model can facilitate prognostication in telehealth transfer and when a thorough neurological exam is not feasible due to language barrier or pre-existing morbidities.