Accuracy of artificial intelligence software for CT angiography in stroke

Mair, G. et al. (2023) Accuracy of artificial intelligence software for CT angiography in stroke. Annals of Clinical and Translational Neurology, 10(7), pp. 1072-1082. (doi: 10.1002/acn3.51790) (PMID:37208850) (PMCID:PMC10351662)

Abstract

Objective: Software developed using artificial intelligence may automatically identify arterial occlusion and provide collateral vessel scoring on CT angiography (CTA) performed acutely for ischemic stroke. We aimed to assess the diagnostic accuracy of e-CTA by Brainomix™ Ltd by large-scale independent testing using expert reading as the reference standard. Methods: We identified a large clinically representative sample of baseline CTA from 6 studies that recruited patients with acute stroke symptoms involving any arterial territory. We compared e-CTA results with masked expert interpretation of the same scans for the presence and location of laterality-matched arterial occlusion and/or abnormal collateral score combined into a single measure of arterial abnormality. We tested the diagnostic accuracy of e-CTA for identifying any arterial abnormality (and in a sensitivity analysis compliant with the manufacturer's guidance that software only be used to assess the anterior circulation). Results: We include CTA from 668 patients (50% female; median: age 71 years, NIHSS 9, 2.3 h from stroke onset). Experts identified arterial occlusion in 365 patients (55%); most (343, 94%) involved the anterior circulation. Software successfully processed 545/668 (82%) CTAs. The sensitivity, specificity and diagnostic accuracy of e-CTA for detecting arterial abnormality were each 72% (95% CI = 66–77%). Diagnostic accuracy was non-significantly improved in a sensitivity analysis excluding occlusions from outside the anterior circulation (76%, 95% CI = 72–80%). Interpretation: Compared to experts, the diagnostic accuracy of e-CTA for identifying acute arterial abnormality was 72–76%. Users of e-CTA should be competent in CTA interpretation to ensure all potential thrombectomy candidates are identified.

• Item Type: Articles
• Additional Information: The authors are grateful to the Stroke Association for commissioning and principally funding RITeS (TSA_CR_2017/01). We also acknowledge the MRC (Medical Research Council) Proximity to Discovery fund (MC_PC_17188) for supporting purchase of an e-ASPECTS software licence. GM is the Stroke Association Edith Murphy Foundation Senior Clinical Lecturer (SA L-SMP 18\1000). PB is Stroke Association Professor of Stroke Medicine and an emeritus NIHR Senior Investigator. JMW is supported by the UK Dementia Research Institute which receives its funding from the MRC, Alzheimer's Research UK and Alzheimer's Society.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Muir, Professor Keith
• Authors: Mair, G., White, P., Bath, P. M., Muir, K., Martin, C., Dye, D., Chappell, F., von Kummer, R., Macleod, M., Sprigg, N., and Wardlaw, J. M.
• College/School: College of Medical Veterinary and Life Sciences > School of Psychology & Neuroscience
• Journal Name: Annals of Clinical and Translational Neurology
• Publisher: Wiley
• ISSN: 2328-9503
• ISSN (Online): 2328-9503
• Published Online: 19 May 2023
• Copyright Holders: Copyright © 2023 The Authors
• First Published: First published in Annals of Clinical and Translational Neurology 10(7):1072-1082
• Publisher Policy: Reproduced under a Creative Commons License