Accuracy of artificial intelligence software for CT angiography in stroke.
Accuracy of artificial intelligence software for CT angiography in stroke.
复制标题
DOI：
10.1002/acn3.51790
复制
发表时间：
2023-07
影响因子：
5.3
通讯作者：
RITeS Collaborat
中科院分区：
文献类型：
--
作者：
Mair, Grant;White, Philip M.;Bath, Philip;Muir, Keith;Martin, Chloe;Dye, David;Chappell, Francesca;von Kummer, Rudiger;Macleod, Malcolm;Sprigg, Nikola M.;Wardlaw, Joanna;RITeS Collaborat
使用人工智能开发的软件可以自动识别动脉闭塞，并在急性缺血性卒中的CT血管造影（CTA）上提供侧支血管评分。我们旨在通过大规模独立测试，使用专家阅读作为参考标准，评估Brainomix™ Ltd的e-CTA的诊断准确性。我们从6项研究中确定了大量具有临床代表性的基线CTA样本，这些研究招募了涉及任何动脉区域的急性卒中症状患者。我们将e-CTA结果与相同扫描的设盲专家解释进行了比较，以确定是否存在偏侧匹配的动脉闭塞和/或异常侧支评分，并将其合并为动脉异常的单一指标。我们测试了e-CTA识别任何动脉异常的诊断准确性（并在符合制造商指南的敏感性分析中，软件仅用于评估前循环）。我们纳入了668例患者的CTA（50%为女性;中位年龄：71岁，NIHSS 9，卒中发作后2.3小时）。专家确定了365例患者（55%）的动脉闭塞;大多数（343，94%）涉及前循环。软件成功处理了545/668（82%）例CTA。e-CTA检测动脉异常的敏感性、特异性和诊断准确性均为72%（95% CI = 66-77%）。在排除前循环外闭塞的敏感性分析中，诊断准确性无显著改善（76%，95% CI = 72-80%）。 与专家相比，e-CTA识别急性动脉异常的诊断准确率为72- 76%。e-CTA的用户应能够进行CTA解读，以确保识别出所有潜在的血栓切除术候选者。
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. 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). 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%). 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.
登录
查看更多内容
DOI：
10.12688/amrcopenres.12904.1
发表时间：
2020-04-28
期刊：
AMRC open research
影响因子：
--
作者：
Mair G;Chappell F;Martin C;Dye D;Bath PM;Muir KW;von Kummer R;Al-Shahi Salman R;Sandercock PAG;Macleod M;Sprigg N;White P;Wardlaw JM
通讯作者：
Wardlaw JM
影响因子：
11.2
作者：
Mair, Grant;White, Philip;Bath, Philip M.;Muir, Keith W.;Salman, Rustam Al-Shahi;Martin, Chloe;Dye, David;Chappell, Francesca M.;Vacek, Adam;von Kummer, Rudiger;Macleod, Malcolm;Sprigg, Nikola;Wardlaw, Joanna M.
通讯作者：
Wardlaw, Joanna M.
影响因子：
6.7
作者：
El-Tawil, Salwa;Wardlaw, Joanna;Muir, Keith W.
通讯作者：
Muir, Keith W.
影响因子：
168.9
作者：
Emberson, Jonathan;Lees, Kennedy R.;Lyden, Patrick;Blackwell, Lisa;Albers, Gregory;Bluhmki, Erich;Brott, Thomas;Cohen, Geoff;Davis, Stephen;Donnan, Geoffrey;Grotta, James;Howard, George;Kaste, Markku;Koga, Masatoshi;von Kummer, Ruediger;Lansberg, Maarten;Lindley, Richard I.;Murray, Gordon;Olivot, Jean Marc;Parsons, Mark;Tilley, Barbara;Toni, Danilo;Toyoda, Kazunori;Wahlgren, Nils;Wardlaw, Joanna;Whiteley, William;del Zoppo, Gregory J.;Baigent, Colin;Sandercock, Peter;Hacke, Werner
通讯作者：
Hacke, Werner
影响因子：
105.7
作者：
Bossuyt, Patrick M.;Reitsma, Johannes B.;Cohen, Jeremie F.
通讯作者：
Cohen, Jeremie F.