Clinical Implementation and Performance of Real-Time AI System for Device Tracking in Neurointervention: First U.S. Evaluation of Neuro-Vascular Assist

Abstract Purpose To evaluate the first U.S.-based implementation, notification accuracy, and temporal operator response of Neuro-Vascular Assist. Methods In a single-center study, 21 consecutive neurointerventional cases were performed using the AI system integrated with a biplane angiographic system. Procedures were classified as “Standard”, “Coil”, “Filter”, or “Venous”. Neuro-Vascular Assist tracked devices including guidewires, stents, coils, and filters in real-time. Visual and audio notifications were made based on device entry and exit in a determined region of interest. We classified these notifications as true positives (TP), false positives (FP), and false negatives (FN), and further assessed for temporal operator response (TOR). Results The AI system was successfully integrated into the workflow without procedural delays or system failures affecting notification delivery. A total of 232 TPs, 13 FPs, and 17 FNs were recorded, resulting in an overall precision of 94.7% and recall of 93.2%. Among the 59 TP notifications evaluated for TOR, 25 (42.4%) were followed by an observable operator response within 10 s. These 25 positive TOR events represented 10.2% of all 245 notifications. Conclusion Neuro-Vascular Assist was successfully implemented and demonstrated preliminary accuracy and feasibility in a U.S.-based neurointerventional setting. Larger prospective studies are warranted to determine whether real-time AI-assisted device tracking influences procedural decision-making, workflow, safety, or clinical outcomes.