Abstract Number: Esoc2026a2428 Impact of Implementing Artificial Intelligence-Supported Large Vessel Occlusion Detection on Stroke Workflow: A Prospective Multicenter Observational Pilot Study
Prospective pilot study evaluates AI’s impact on stroke workflow metrics, indicating modest improvements.
Key Points
The aim is to evaluate the impact of AI-based large vessel occlusion detection on stroke workflow and clinical outcomes.
Prospective, observational multicenter pilot study in South-Eastern Norway.
Patients grouped as pre-AI (n=90), post-AI without AI use (n=80), and post-AI with AI use (n=30).
Primary endpoint: time from CT acquisition to CSC contact; secondary endpoints included various timing metrics and functional independence at 90 days.
Median CT-to-CSC contact times were 24, 29, and 22 minutes for pre-AI, post-AI without use, and post-AI with use respectively (global p=0.039).
CT-to-groin puncture time was significantly shorter in the AI-used group (152 minutes) compared to pre-AI (179 minutes) and post-AI without use (182 minutes) (adjusted p=0.045 and p=0.007).
Functional outcomes at 90 days did not statistically differ among groups.