Diagnostic Value of Artificial Intelligence—Based Software in Detection of Large Vessel Occlusion in Acute Ischemic Stroke

Background: Aim of the study was to test accuracy AI-based software for detection large vessel occlusion (LVO) with computed tomography angiography (CTA) in stroke patients using an experienced neuroradiologist’s evaluation as reference. Methods: Consecutive who underwent multimodal brain CT suspected acute ischemic were retrospectively identified. The presence and site (classified proximal distal) LVO assessed CTA by neuroradiologist a reference compared readings three medical students software, e-CTA. Results: One-hundred-eight participants mean age 70 years (±12.6); 55 (50.9%) females included. Neuroradiologist found (64.8%) cases: 45 (41.7%) proximal, 25 (23.1%) distal. overall sensitivity e-CTA 0.67 (95%CI 0.55–0.78); 0.84 0.71–0.94) 0.36 0.18–0.57) distal LVOs. Overall specificity 0.95 0.82–0.99) 0.77 0.68–0.84), respectively. student’s performance similar Conclusions: tested software’s is acceptable LVOs, while it appears be not accurate enough