{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T18:57:00Z","timestamp":1781204220217,"version":"3.54.1"},"reference-count":20,"publisher":"BMJ","issue":"6","license":[{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"unspecified","delay-in-days":10,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2026,5,29]]},"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>This study aims to explore the ability to identify high-grade intracranial arterial stenosis (ICAS) by an artificial intelligence (AI) designed to detect large vessel occlusions (LVO) and the clinical relevance of these \u2018false positive\u2019 findings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>We are presenting a retrospective cohort study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>The study was conducted at a supraregional stroke centre of an urban tertiary care provider.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>Consecutive stroke cases treated between January 2023 and December 2023 of patients &gt;18 years of both sexes and any ethnicity were eligible for inclusion. 934 patients (52.7% male) with a mean age of 71.7\u00b113.6 years (25\u2013101 years) were included.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Interventions<\/jats:title>\n                    <jats:p>CT angiographies were analysed by a deep learning algorithm for LVO detection of the anterior circulation. AI results were compared with radiology reports and secondary focused evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary and secondary outcome measures<\/jats:title>\n                    <jats:p>Diagnostic accuracies for ICAS detection by the AI were calculated.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Primary reports identified 30 ICAS and nine additional ICAS were detected during secondary evaluation (incidence 4.2%). The sensitivity of radiology reports was 77% (95% CI 0.61 to 0.89), the specificity 99% (95% CI 0.98 to 1.00), negative predictive value (NPV) 99% (95% CI 0.98 to 0.99) and positive predictive value (PPV) 79% (95% CI 0.65 to 0.88). The AI identified 13 of 39 ICAS correctly. 18 false positive cases (neither LVO nor ICAS) were flagged by the AI. The sensitivity of the algorithm was 33% (95% CI 0.19 to 0.50), the specificity 98% (95% CI 0.97 to 0.99), the NPV 97% (95% CI 0.96 to 0.98) and PPV 42% (95% CI 0.28 to 0.58).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Detection of high-grade ICAS by an algorithm trained to identify LVO is per se a false positive finding but occurred in 13 of 39 cases. Dedicated training for ICAS might lead to a beneficial tool during the diagnostic work-up for ischaemic stroke.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Trial registration<\/jats:title>\n                    <jats:p>\n                      German Register for Clinical Trials (DRKS: DRKS00034019\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/drks.de\/search\/de\/trial\/DRKS00034019\">https:\/\/drks.de\/search\/de\/trial\/DRKS00034019<\/jats:ext-link>\n                      ).\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2025-113081","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T18:00:10Z","timestamp":1781200810000},"page":"e113081","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Clinical relevance of intracranial stenosis as false-positive findings of a deep learning algorithm trained to detect large vessel occlusions: a retrospective cohort study of a supraregional stroke centre"],"prefix":"10.1136","volume":"16","author":[{"given":"Michel","family":"Jungmann","sequence":"first","affiliation":[{"name":"Anaesthesiology, BG Klinikum Unfallkrankenhaus Berlin gGmbH, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanda","family":"Manschikow","sequence":"additional","affiliation":[{"name":"Institute of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin gGmbH, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"H\u00f6nning","sequence":"additional","affiliation":[{"name":"Center for Clinical Research, BG Klinikum Unfallkrankenhaus Berlin gGmbH, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederik","family":"Spohn","sequence":"additional","affiliation":[{"name":"Institute of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin gGmbH, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Sparenberg","sequence":"additional","affiliation":[{"name":"Neurology, BG Klinikum Unfallkrankenhaus Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sven","family":"Mutze","sequence":"additional","affiliation":[{"name":"Institute of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin gGmbH, Berlin, Germany"},{"name":"Institute for Diagnostic Radiology and Neuroradiology, Universit\u00e4tsmedizin Greifswald, Greifswald, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0011-2382","authenticated-orcid":false,"given":"Leonie","family":"Goelz","sequence":"additional","affiliation":[{"name":"Institute of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin gGmbH, Berlin, Germany"},{"name":"Institute for Diagnostic Radiology and Neuroradiology, Universit\u00e4tsmedizin Greifswald, Greifswald, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"key":"2026061111000660000_16.6.e113081.1","doi-asserted-by":"crossref","unstructured":"Arenillas JF . Intracranial atherosclerosis: current concepts. Stroke 2011. doi:10.1136\/neurintsurg-2019-015135","DOI":"10.1161\/STROKEAHA.110.597278"},{"key":"2026061111000660000_16.6.e113081.2","doi-asserted-by":"publisher","DOI":"10.1007\/s00234-022-02978-x"},{"key":"2026061111000660000_16.6.e113081.3","doi-asserted-by":"publisher","DOI":"10.1159\/000519125"},{"key":"2026061111000660000_16.6.e113081.4","doi-asserted-by":"publisher","DOI":"10.1136\/neurintsurg-2021-017842"},{"key":"2026061111000660000_16.6.e113081.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.crad.2022.10.007"},{"key":"2026061111000660000_16.6.e113081.6","doi-asserted-by":"crossref","first-page":"1182","DOI":"10.1001\/jamaneurol.2023.3206","article-title":"Automated Large Vessel Occlusion Detection Software and Thrombectomy Treatment Times: A Cluster Randomized Clinical Trial","volume":"80","author":"Martinez-Gutierrez","year":"2023","journal-title":"JAMA Neurol"},{"key":"2026061111000660000_16.6.e113081.7","doi-asserted-by":"crossref","first-page":"15910199231209080","DOI":"10.1177\/15910199231209080","article-title":"Artificial intelligence improves transfer times and ischemic stroke workflow metrics","volume":"17","author":"Field","year":"2023","journal-title":"Interv Neuroradiol"},{"key":"2026061111000660000_16.6.e113081.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.wneu.2021.12.004"},{"key":"2026061111000660000_16.6.e113081.9","doi-asserted-by":"crossref","first-page":"4347","DOI":"10.1007\/s00330-024-11332-z","article-title":"Implementing an AI algorithm in the clinical setting: a case study for the accuracy paradox","volume":"35","author":"Scaringi","year":"2025","journal-title":"Eur Radiol"},{"key":"2026061111000660000_16.6.e113081.10","doi-asserted-by":"publisher","DOI":"10.1177\/1971400921998952"},{"key":"2026061111000660000_16.6.e113081.11","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.119.026259"},{"key":"2026061111000660000_16.6.e113081.12","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.110.597278"},{"key":"2026061111000660000_16.6.e113081.13","doi-asserted-by":"publisher","DOI":"10.1016\/s1474-4422(21)00376-8"},{"key":"2026061111000660000_16.6.e113081.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2007.11.008"},{"key":"2026061111000660000_16.6.e113081.15","doi-asserted-by":"crossref","unstructured":"He K , Zhang X , Ren S , et al . Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Las Vegas, NV, USA, 2016:770\u20138. doi:10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2026061111000660000_16.6.e113081.16","doi-asserted-by":"crossref","unstructured":"Long J , Shelhamer E , Darrell T . Fully convolutional networks for semantic segmentation. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Boston, MA, USA, 2014 doi:10.1109\/CVPR.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2026061111000660000_16.6.e113081.17","unstructured":"Kingma DP , Ba J . Adam: a method for stochastic optimization. CoRR; 2014."},{"key":"2026061111000660000_16.6.e113081.18","doi-asserted-by":"crossref","unstructured":"Bossuyt PM , Reitsma JB , Bruns DE , et al . Standards for Reporting of Diagnostic Accuracy. Towards complete and accurate reporting of studies of diagnostic accuracy: The STARD Initiative. Radiology 2003;24\u20138. doi:10.1148\/radiol.2261021292","DOI":"10.1148\/radiol.2261021292"},{"key":"2026061111000660000_16.6.e113081.19","doi-asserted-by":"crossref","first-page":"143","DOI":"10.4103\/bc.bc_5_25","article-title":"A retrospective analysis comparing AIDoc and RAPIDAI in the detection of large vessel occlusions","volume":"11","author":"Bankston","year":"2025","journal-title":"Brain Circ"},{"key":"2026061111000660000_16.6.e113081.20","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1148\/radiol.2021202734","article-title":"High-Performance Automated Anterior Circulation CT Angiographic Clot Detection in Acute Stroke: A Multireader Comparison","volume":"298","author":"Dehkharghani","year":"2021","journal-title":"Radiology"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2025-113081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T18:00:16Z","timestamp":1781200816000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2025-113081"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":20,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,11]]},"published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1136\/bmjopen-2025-113081"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2025-113081","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}