{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T11:10:20Z","timestamp":1779448220783,"version":"3.53.1"},"reference-count":36,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union\u2014NextGeneration EU","award":["BG-RRP-2.004-0007-C01"],"award-info":[{"award-number":["BG-RRP-2.004-0007-C01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neurology International"],"abstract":"<jats:p>Background\/Objectives: Artificial intelligence (AI) tools are increasingly integrated into acute stroke imaging workflows, but real-world performance for ischemia detection on non-contrast CT (NCCT) remains incompletely validated by investigators independent of the developer. This study externally validated the BrainScan AI system in an unselected, consecutively enrolled emergency cohort. Methods: Consecutive adult patients undergoing NCCT under the routine acute stroke protocol at a single tertiary centre between January and December 2025 were prospectively enrolled. The reference standard was the post-consensus radiological diagnosis, supplemented where available by follow-up imaging and clinical course. Primary outcomes were diagnostic accuracy for ischemia and intracranial haemorrhage detection, assessed by sensitivity, specificity, predictive values, likelihood ratios, and area under the ROC curve (AUC; DeLong). Pre-specified secondary analyses included regional sensitivity, confidence-score behaviour, artefact robustness, threshold sensitivity, a cluster-robust bootstrap for within-patient correlation, and a quantitative bias analysis under non-differential reference-standard misclassification. Sample size adequacy was assessed using a precision-based framework. Results: A total of 1419 NCCT examinations from 1260 patients were analysed. Ischemia sensitivity was 59.2% (95% CI 52.1\u201366.1) and specificity was 99.8% (99.4\u2013100), with an AUC of 0.930 (0.906\u20130.954). The Youden-optimal threshold (0.055) recovered sensitivity to 86.1% with negligible specificity loss, reflecting a markedly bimodal score distribution. Regional sensitivity was lower in infratentorial structures. Bias-corrected estimates were stable across all reference-standard parameters consistent with the data. Haemorrhage detection performed substantially better (sensitivity 96.7%; AUC 0.983). Conclusions: The system shows excellent specificity and strong discrimination but moderate sensitivity for ischemia, supporting its role as a rule-in adjunct rather than a stand-alone tool, pending multicentre validation and site-specific threshold recalibration.<\/jats:p>","DOI":"10.3390\/neurolint18060100","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T10:07:47Z","timestamp":1779444467000},"page":"100","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The Role of AI-Based Software BrainScan in the Interpretation of Non-Contrast Head CT in Acute Ischemic Stroke: An External Validation Study"],"prefix":"10.3390","volume":"18","author":[{"given":"Eray","family":"Halil","sequence":"first","affiliation":[{"name":"Department of Neurology, Medical University of Plovdiv, 15A Vasil Aprilov Blvd., 4002 Plovdiv, Bulgaria"},{"name":"Clinic of Neurology, UMHAT \u201cSt George\u201d, 66 Peshtersko Shose Blvd., 4001 Plovdiv, Bulgaria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1326-8211","authenticated-orcid":false,"given":"Ivan","family":"Sitnikov","sequence":"additional","affiliation":[{"name":"Department of Neurology, Medical University of Plovdiv, 15A Vasil Aprilov Blvd., 4002 Plovdiv, Bulgaria"},{"name":"Clinic of Neurology, UMHAT \u201cSt George\u201d, 66 Peshtersko Shose Blvd., 4001 Plovdiv, Bulgaria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8754-5586","authenticated-orcid":false,"given":"Neli","family":"Atanasova","sequence":"additional","affiliation":[{"name":"Department of Radiology, UMHAT \u201cSt George\u201d, 66 Peshtersko Shose Blvd., 4001 Plovdiv, Bulgaria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petra","family":"Popova","sequence":"additional","affiliation":[{"name":"Department of Radiology, UMHAT \u201cSt George\u201d, 66 Peshtersko Shose Blvd., 4001 Plovdiv, Bulgaria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1414-8738","authenticated-orcid":false,"given":"Kostadin","family":"Kostadinov","sequence":"additional","affiliation":[{"name":"Department of Social Medicine and Public Health, Medical University of Plovdiv, 15A Vasil Aprilov Blvd., 4002 Plovdiv, Bulgaria"},{"name":"Environmental Health Division, Research Institute, Medical University of Plovdiv, 15A Vasil Aprilov Blvd., 4002 Plovdiv, Bulgaria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fares","family":"Ezeldin","sequence":"additional","affiliation":[{"name":"Department of Forensic Medicine and Deontology, Medical University of Plovdiv, 15A Vasil Aprilov Blvd., 4002 Plovdiv, Bulgaria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Penka","family":"Atanassova","sequence":"additional","affiliation":[{"name":"Department of Neurology, Medical University of Plovdiv, 15A Vasil Aprilov Blvd., 4002 Plovdiv, Bulgaria"},{"name":"Clinic of Neurology, UMHAT \u201cSt George\u201d, 66 Peshtersko Shose Blvd., 4001 Plovdiv, Bulgaria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1177\/17474930241308142","article-title":"World Stroke Organization: Global Stroke Fact Sheet 2025","volume":"20","author":"Feigin","year":"2025","journal-title":"Int. J. Stroke"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e139","DOI":"10.1161\/CIR.0000000000000757","article-title":"Heart Disease and Stroke Statistics\u20142020 Update: A Report From the American Heart Association","volume":"141","author":"Virani","year":"2020","journal-title":"Circulation"},{"key":"ref_3","first-page":"e344","article-title":"Guidelines for the Early Management of Patients with Acute Ischemic Stroke: 2019 Update","volume":"50","author":"Powers","year":"2019","journal-title":"Stroke"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2032","DOI":"10.1161\/STR.0000000000000069","article-title":"Guidelines for the Management of Spontaneous Intracerebral Hemorrhage","volume":"46","author":"Hemphill","year":"2015","journal-title":"Stroke"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"340","DOI":"10.5853\/jos.2016.01424","article-title":"Visibility of CT Early Ischemic Change Is Significantly Associated with Time from Stroke Onset to Baseline Scan beyond the First 3 Hours","volume":"19","author":"Gao","year":"2017","journal-title":"J. Stroke"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"110455","DOI":"10.1016\/j.ejrad.2022.110455","article-title":"Associations between early ischemic signs on non-contrast CT and time since acute ischemic stroke onset: A scoping review","volume":"155","author":"Majoie","year":"2022","journal-title":"Eur. J. Radiol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1148\/radiol.2019192515","article-title":"Assessing Radiology Research on Artificial Intelligence: A Brief Guide for Authors, Reviewers, and Readers","volume":"294","author":"Bluemke","year":"2020","journal-title":"Radiology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"91","DOI":"10.5152\/eurasianjmed.2023.23347","article-title":"Artificial Intelligence in Stroke Imaging: A Comprehensive Review","volume":"55","author":"Koska","year":"2023","journal-title":"Eurasian J. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"100678","DOI":"10.1016\/j.ejro.2025.100678","article-title":"Performance of an artificial intelligence tool for multi-step acute stroke imaging: A multicenter diagnostic study","volume":"15","author":"Agripnidis","year":"2025","journal-title":"Eur. J. Radiol. Open"},{"key":"ref_10","first-page":"1","article-title":"Human Readers versus AI-Based Systems in ASPECTS Scoring for Acute Ischemic Stroke: A Systematic Review and Meta-Analysis","volume":"1","author":"Azzam","year":"2025","journal-title":"ASIDE Intern. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1136\/neurintsurg-2019-015135","article-title":"Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions: A systematic review","volume":"12","author":"Murray","year":"2020","journal-title":"J. Neurointerventional Surg."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kelly, C.J., Karthikesalingam, A., Suleyman, M., Corrado, G., and King, D. (2019). Key challenges for delivering clinical impact with artificial intelligence. BMC Med., 17.","DOI":"10.1186\/s12916-019-1426-2"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1177\/23969873241253366","article-title":"Artificial intelligence to predict individualized outcome of acute ischemic stroke patients: The SIBILLA project","volume":"9","author":"Caliandro","year":"2024","journal-title":"Eur. Stroke J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"7438","DOI":"10.1016\/j.acra.2025.09.010","article-title":"Artificial Intelligence for Ischemic Stroke Detection in Non-contrast CT: A Systematic Review and Meta-analysis","volume":"32","author":"Shen","year":"2025","journal-title":"Acad. Radiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1148\/radiol.2020192224","article-title":"Preparing medical imaging data for machine learning","volume":"295","author":"Willemink","year":"2020","journal-title":"Radiology"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2","DOI":"10.3174\/ajnr.A6883","article-title":"Artificial Intelligence and Acute Stroke Imaging","volume":"42","author":"Soun","year":"2021","journal-title":"AJNR Am. J. Neuroradiol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1072","DOI":"10.1002\/acn3.51790","article-title":"Accuracy of artificial intelligence software for CT angiography in stroke","volume":"10","author":"Mair","year":"2023","journal-title":"Ann. Clin. Transl. Neurol."},{"key":"ref_18","unstructured":"BrainScan S.A. (2025). BrainScan CT\u2014A Decision Support System for the Interpretation of Head Computed Tomography Based on Machine Learning: Instruction for Use, BrainScan S.A."},{"key":"ref_19","unstructured":"Kostadinov, K. (2026, March 02). Kkstatfun: R Toolkit for Medical Statistics and Epidemiology. Available online: https:\/\/zenodo.org\/records\/18936020."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lash, T.L., Fox, M.P., and Fink, A.K. (2009). Applying Quantitative Bias Analysis to Epidemiologic Data, Springer.","DOI":"10.1007\/978-0-387-87959-8"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.2307\/2531772","article-title":"The Predictive Value of Simple Rules for Combining Two Diagnostic Tests","volume":"45","author":"Marshall","year":"1989","journal-title":"Biometrics"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Bacchetti, P. (2010). Current sample size conventions: Flaws, harms, and alternatives. BMC Med., 8.","DOI":"10.1186\/1741-7015-8-17"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1198\/000313001300339897","article-title":"The Abuse of Power","volume":"55","author":"Hoenig","year":"2001","journal-title":"Am. Stat."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e240775","DOI":"10.1148\/radiol.240775","article-title":"Deep Learning Applications in Imaging of Acute Ischemic Stroke: A Systematic Review and Narrative Summary","volume":"315","author":"Jiang","year":"2025","journal-title":"Radiology"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chiramal, J.A., Johnson, J., Webster, J., Nag, D.R., Robert, D., Ghosh, T., Golla, S., Pawar, S., Krishnan, P., and Drain, P.K. (2024). Artificial Intelligence-based automated CT brain interpretation to accelerate treatment for acute stroke in rural India: An interrupted time series study. PLoS Glob. Public Health, 4.","DOI":"10.2139\/ssrn.4684850"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wen, Z., Wang, Y., Zhong, Y., Wang, J., Hu, Y., Zhou, P., and Guo, S. (2024). Artificial intelligence in ischemic stroke images: Current applications and future directions. Front. Neurol., 15.","DOI":"10.3389\/fneur.2024.1418060"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat. Med."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"107750","DOI":"10.1016\/j.jstrokecerebrovasdis.2024.107750","article-title":"Multicenter comparison using two AI stroke CT perfusion software packages for determining thrombectomy eligibility","volume":"33","author":"Alwood","year":"2024","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wang, D., Jin, R., Shieh, C., Ng, A.Y., Pham, H., Dugal, T., Barnett, M., Winoto, L., Wang, C., and Barnett, Y. (2023). Real world validation of an AI-based CT hemorrhage detection tool. Front. Neurol., 14.","DOI":"10.3389\/fneur.2023.1177723"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ojeda, P., Zawaideh, M., Mossa-Basha, M., and Haynor, D. (2019, January 16\u201321). The utility of deep learning: Evaluation of a convolutional neural network for detection of intracranial bleeds on non-contrast head computed tomography studies. Proceedings of the SPIE Medical Imaging, San Diego, CA, USA.","DOI":"10.1117\/12.2513167"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2388","DOI":"10.1016\/S0140-6736(18)31645-3","article-title":"Deep learning algorithms for detection of critical findings in head CT scans: A retrospective study","volume":"392","author":"Chilamkurthy","year":"2018","journal-title":"Lancet"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1007\/s00062-023-01291-1","article-title":"Systematic Review of Artificial Intelligence for Abnormality Detection in High-volume Neuroimaging and Subgroup Meta-analysis for Intracranial Hemorrhage Detection","volume":"33","author":"Agarwal","year":"2023","journal-title":"Clin. Neuroradiol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e2808","DOI":"10.1002\/brb3.2808","article-title":"Automated detection of intracranial large vessel occlusions using Viz.ai software: Experience in a large, integrated stroke network","volume":"13","author":"Karamchandani","year":"2023","journal-title":"Brain Behav."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"4938","DOI":"10.1038\/s41467-023-40564-8","article-title":"Deep-learning based detection of vessel occlusions on CT-angiography in patients with suspected acute ischemic stroke","volume":"14","author":"Brugnara","year":"2023","journal-title":"Nat. Commun."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"h5527","DOI":"10.1136\/bmj.h5527","article-title":"STARD 2015: An updated list of essential items for reporting diagnostic accuracy studies","volume":"351","author":"Bossuyt","year":"2015","journal-title":"BMJ"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1161\/STROKEAHA.125.052146","article-title":"Artificial Intelligence and Novel Trial Designs for Acute Ischemic Stroke: Opportunities and Challenges","volume":"57","author":"Broderick","year":"2026","journal-title":"Stroke"}],"container-title":["Neurology International"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2035-8377\/18\/6\/100\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T10:58:32Z","timestamp":1779447512000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2035-8377\/18\/6\/100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":36,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["neurolint18060100"],"URL":"https:\/\/doi.org\/10.3390\/neurolint18060100","relation":{},"ISSN":["2035-8377"],"issn-type":[{"value":"2035-8377","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]}}}