Artificial Intelligence for Automated Detection of Large Vessel Occlusion: State of the Art, Clinical Applications and Future Perspectives

Abstract

Background: Large vessel occlusion (LVO) is a major cause of morbidity and mortality in acute ischemic stroke (AIS) and a common indication for mechanical thrombectomy. Rapid detection is critical because the benefit of treatment is highly time-dependent. Artificial intelligence (AI)-based imaging systems have emerged as decision-support tools for automated LVO identification, image prioritisation, and rapid stroke-team notification. Objective: To critically review current evidence on AI-assisted LVO detection, including diagnostic accuracy, clinical and workflow implications, commercially available platforms, barriers to implementation, and future perspectives. Methods: This narrative review covers literature published from January 2015 to June 2026 on AI-based LVO identification using computed tomography angiography (CTA) and multimodal stroke imaging. Evidence relating to diagnostic performance, external validation, workflow impact, commercial platforms, implementation, and emerging technologies was reviewed. Results: AI systems demonstrate high diagnostic accuracy for proximal anterior circulation LVO, with reported sensitivities of 85-97% and specificities above 90%. Clinical implementation has improved image triage, specialist notification, thrombectomy activation, and interhospital coordination. However, performance is less consistent for distal and posterior circulation occlusions, while heterogeneity in study design, imaging methods, and outcome measures limits comparisons between platforms. Additional challenges include false-positive alerts, missed occlusions, limited generalisability, algorithmic bias, explainability, regulatory oversight, interoperability, and cost. Conclusion: AI-assisted LVO detection has the potential to improve the speed and coordination of acute stroke care, particularly for proximal anterior circulation occlusions, but should augment rather than replace clinician interpretation. Its long-term clinical value requires prospective multicentre validation, standardised comparative studies, transparent reporting, and evaluation of patient-centred outcomes. Keywords: Artificial Intelligence; Large Vessel Occlusion; Acute Ischemic Stroke; Mechanical Thrombectomy; Computed Tomography Angiography; Stroke Imaging; Clinical Decision Support; Machine Learning.