Automated Large Artery Occlusion Detection in Stroke: A Single-Center Validation Study of an Artificial Intelligence Algorithm

• Published in: Cerebrovascular diseases (Basel, Switzerland) Vol. 51; no. 2; p. 259
• Main Authors: Rodrigues, Gabriel, Barreira, Clara M, Bouslama, Mehdi, Haussen, Diogo C, Al-Bayati, Alhamza, Pisani, Leonardo, Liberato, Bernardo, Bhatt, Nirav, Frankel, Michael R, Nogueira, Raul G
• Format: Journal Article
• Language: English
• Published: Switzerland 01-03-2022
• Subjects: Algorithms; Artificial Intelligence; Brain Ischemia - therapy; Cerebral Angiography - methods; Humans; Infarction, Middle Cerebral Artery - diagnostic imaging; Infarction, Middle Cerebral Artery - therapy; Ischemic Stroke; Middle Cerebral Artery; Retrospective Studies; Stroke - diagnostic imaging; Stroke - therapy; Computed tomography angiography; Stroke; Computed tomography scan; Acute ischemic stroke; Artificial intelligence; Large vessel occlusion
• ISSN: 1421-9786
• DOI: 10.1159/000519125

Expediting notification of lesions in acute ischemic stroke (AIS) is critical. Limited availability of experts to assess such lesions and delays in large vessel occlusion (LVO) recognition can negatively affect outcomes. Artificial intelligence (AI) may aid LVO recognition and treatment. This study aims to evaluate the performance of an AI-based algorithm for LVO detection in AIS.
Retrospective analysis of a database of AIS patients admitted in a single center between 2014 and 2019. Vascular neurologists graded computed tomography angiographies (CTAs) for presence and site of LVO. Studies were analyzed by the Viz-LVO Algorithm® version 1.4 - neural network programmed to detect occlusions from the internal carotid artery terminus (ICA-T) to the Sylvian fissure. Comparisons between human versus AI-based readings were done by test characteristic analysis and Cohen's kappa. Primary analysis included ICA-T and/or middle cerebral artery (MCA)-M1 LVOs versus non-LVOs/more distal occlusions. Secondary analysis included MCA-M2 occlusions.
610 CTAs were analyzed. The AI algorithm rejected 2.5% of the CTAs due to poor quality, which were excluded from the analysis. Viz-LVO identified ICA-T and MCA-M1 LVOs with a sensitivity of 87.6%, specificity of 88.5%, and accuracy of 87.9% (AUC 0.88, 95% CI: 0.85-0.92, p < 0.001). Cohen's kappa was 0.74. In the secondary analysis, the algorithm yielded a sensitivity of 80.3%, specificity of 88.5%, and accuracy of 82.7%. The mean run time of the algorithm was 2.78 ± 0.5 min.
Automated AI reading allows for fast and accurate identification of LVO strokes with timely notification to emergency teams, enabling quick decision-making for reperfusion therapies or transfer to specialized centers if needed.