{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:36:51Z","timestamp":1787017011131,"version":"build-2736575974"},"reference-count":22,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"content-version":"unspecified","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"content-version":"unspecified","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"NHSX AI","award":["AI_AWARD02354"],"award-info":[{"award-number":["AI_AWARD02354"]}]},{"name":"NHSX AI","award":["AI_AWARD02354"],"award-info":[{"award-number":["AI_AWARD02354"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Digit Health"],"accepted":{"date-parts":[[2026,2,3]]},"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To assess whether an artificial intelligence (AI) tool improves the accuracy, speed and confidence of general radiologists, emergency clinicians and radiographers in detecting critical non-contrast CT head (NCCTH) abnormalities and to evaluate its stand-alone performance and factors influencing diagnostic accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and analysis<\/jats:title>\n                    <jats:p>A retrospective dataset of 150 NCCTH (52 normal and 98 with critical abnormalities) was reviewed by 30 readers (10 radiologists, 15 emergency clinicians and 5 radiographers) from four National Health Service trusts. Each interpreted scan is performed unaided and then with the qER EU 2.0 AI tool, separated by a 2-week washout period. Ground truth was established by two neuroradiologists. We measured the AI\u2019s stand-alone performance and its effect on reader accuracy, confidence and speed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The qER algorithm showed strong diagnostic performance (area under the receiver operator curve 0.821\u20130.976). With AI, pooled reader sensitivity for critical abnormalities increased from 82.8% to 89.7% (+6.9%, p&lt;0.001) and for intracranial haemorrhage from 84.6% to 91.6% (+7.0%, p&lt;0.001), while specificity decreased from 84.5% to 78.9% (\u20135.5%, p=0.046). Reader confidence did not change significantly. Emergency department (ED) clinicians with AI achieved sensitivity similar to unaided radiologists.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>AI assistance increased sensitivity for detecting critical abnormalities on NCCTH but reduced specificity. AI-enabled ED clinicians to achieve diagnostic sensitivity comparable to radiologists, supporting its potential to enhance non-radiologist performance. Further studies are needed to confirm these findings in clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Trial registration number<\/jats:title>\n                    <jats:p>\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"clintrialgov\" specific-use=\"clinicaltrial pre-results\" xlink:href=\"NCT06018545\">NCT06018545<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjdh-2026-000071","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T14:45:21Z","timestamp":1773326721000},"page":"e000071","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Artificial intelligence-assisted reader evaluation in acute CT head interpretation (AI-REACT): a multireader multicase study"],"prefix":"10.1136","volume":"2","clinical-trial-number":[{"clinical-trial-number":"nct06018545","registry":"10.18810\/clinical-trials-gov","type":"preResults"},{"clinical-trial-number":"nct06018545","registry":"10.18810\/clinical-trials-gov"},{"clinical-trial-number":"isrctn17560291","registry":"10.18810\/isrctn"},{"clinical-trial-number":"nct06018545","registry":"10.18810\/clinical-trials-gov","type":"preResults"},{"clinical-trial-number":"nct06018545","registry":"10.18810\/clinical-trials-gov"},{"clinical-trial-number":"isrctn17560291","registry":"10.18810\/isrctn"}],"author":[{"given":"Alex","family":"Novak","sequence":"first","affiliation":[{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford University Hospitals NHS Foundation Trust, Oxford, England, UK"},{"name":"Emergency Medicine Research Oxford, Oxford University Hospitals NHS Foundation Trust, Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruchir","family":"Shah","sequence":"additional","affiliation":[{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford University Hospitals NHS Foundation Trust, Oxford, England, UK"},{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford University Hospitals NHS Foundation Trust, Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdala T","family":"Espinosa Morgado","sequence":"additional","affiliation":[{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford University Hospitals NHS Foundation Trust, Oxford, England, UK"},{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford University Hospitals NHS Foundation Trust, Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dennis","family":"Robert","sequence":"additional","affiliation":[{"name":"Qure.ai, Bangalore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shamie","family":"Kumar","sequence":"additional","affiliation":[{"name":"Qure.ai Technologies Limited, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Oke","sequence":"additional","affiliation":[{"name":"Department of Primary Health Care Sciences, University of Oxford, Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kanika","family":"Bhatia","sequence":"additional","affiliation":[{"name":"Oxford University Hospitals NHS Foundation Trust, Oxford, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Romsauerova","sequence":"additional","affiliation":[{"name":"Oxford University Hospitals NHS Foundation Trust, Oxford, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tilak","family":"Das","sequence":"additional","affiliation":[{"name":"Department of Clinical Radiology, Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"The AI-REACT Reader Study Group","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mariapaola","family":"Narbone","sequence":"additional","affiliation":[{"name":"Guy's and St Thomas\u2019 NHS Foundation Trust, London, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahul","family":"Dharmadhikari","sequence":"additional","affiliation":[{"name":"Northumbria Healthcare NHS Foundation Trust, North Shields, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Harrison","sequence":"additional","affiliation":[{"name":"Emergency Department, Northumbria Specialist Emergency Care Hospital, Cramlington, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kavitha","family":"Vimalesvaran","sequence":"additional","affiliation":[{"name":"Guy's and St Thomas\u2019 NHS Foundation Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jane","family":"Gooch","sequence":"additional","affiliation":[{"name":"College of Health, Psychology & Social Care, University of Derby, Derby, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nick","family":"Woznitza","sequence":"additional","affiliation":[{"name":"University College London NHS Foundation Trust, London, UK"},{"name":"School of Allied and Public Health Professions, Canterbury Christ Church University, Canterbury, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Lowe","sequence":"additional","affiliation":[{"name":"Digital Health Validation Lab, University of Glasgow, Glasgow, UK"},{"name":"Emergency Department, NHS Greater Glasgow & Clyde, Glasgow, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haris","family":"Shuaib","sequence":"additional","affiliation":[{"name":"Guy's and St Thomas\u2019 NHS Foundation Trust, London, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarim","family":"Ather","sequence":"additional","affiliation":[{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford University Hospitals NHS Foundation Trust, Oxford, England, UK"},{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford University Hospitals NHS Foundation Trust, Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,3,12]]},"reference":[{"key":"2026070610203704000_2.1.e000071.1","doi-asserted-by":"publisher","DOI":"10.1093\/neuonc\/noad001"},{"key":"2026070610203704000_2.1.e000071.2","doi-asserted-by":"publisher","DOI":"10.1136\/emj.2004.021717"},{"key":"2026070610203704000_2.1.e000071.3","doi-asserted-by":"publisher","DOI":"10.5812\/traumamon.12023"},{"key":"2026070610203704000_2.1.e000071.4","unstructured":"Richards M . Diagnostics: recovery and renewal \u2013 report of the independent review of diagnostic services for NHS England. NHS England. Available: https:\/\/www.england.nhs.uk\/publication\/diagnostics-recovery-and-renewal-report-of-the-independent-review-of-diagnostic-services-for-nhs-england\/ [Accessed 3 Feb 2024]."},{"key":"2026070610203704000_2.1.e000071.5","doi-asserted-by":"publisher","DOI":"10.1067\/j.cpradiol.2020.10.007"},{"key":"2026070610203704000_2.1.e000071.6","doi-asserted-by":"crossref","first-page":"20546","DOI":"10.1038\/s41598-020-77441-z","article-title":"Detection and classification of intracranial haemorrhage on CT images using a novel deep-learning algorithm","volume":"10","author":"Lee","year":"2020","journal-title":"Sci Rep"},{"key":"2026070610203704000_2.1.e000071.7","article-title":"Deep Learning System Boosts Radiologist Detection of Intracranial Hemorrhage","volume":"14","author":"Warman","year":"2022","journal-title":"Cureus"},{"key":"2026070610203704000_2.1.e000071.8","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-023-10074-8"},{"key":"2026070610203704000_2.1.e000071.9","doi-asserted-by":"crossref","DOI":"10.1259\/bjr.20190840","article-title":"Artificial intelligence in diagnostic imaging: impact on the radiography profession","volume":"93","author":"Hardy","year":"2020","journal-title":"Br J Radiol"},{"key":"2026070610203704000_2.1.e000071.10","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(18)31645-3"},{"key":"2026070610203704000_2.1.e000071.11","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2023-078227","article-title":"Assessing the effectiveness of artificial intelligence (AI) in prioritising CT head interpretation: study protocol for a stepped-wedge cluster randomised trial (ACCEPT-AI)","volume":"14","author":"Vimalesvaran","year":"2024","journal-title":"BMJ Open"},{"key":"2026070610203704000_2.1.e000071.12","doi-asserted-by":"publisher","DOI":"10.1007\/s00234-022-03075-9"},{"key":"2026070610203704000_2.1.e000071.13","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgph.0003351","article-title":"Artificial Intelligence-based automated CT brain interpretation to accelerate treatment for acute stroke in rural India: An interrupted time series study","volume":"4","author":"Chiramal","year":"2024","journal-title":"PLOS Glob Public Health"},{"key":"2026070610203704000_2.1.e000071.14","article-title":"A retrospective audit of an artificial intelligence software for the detection of intracranial haemorrhage used by a teleradiology company in the United Kingdom","volume":"6","author":"Pettet","year":"2024","journal-title":"BJR Open"},{"key":"2026070610203704000_2.1.e000071.15","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2023-079824","article-title":"AI assisted reader evaluation in acute CT head interpretation (AI-REACT): protocol for a multireader multicase study","volume":"14","author":"Fu","year":"2024","journal-title":"BMJ Open"},{"key":"2026070610203704000_2.1.e000071.16","doi-asserted-by":"publisher","DOI":"10.1136\/emermed-2023-213620"},{"key":"2026070610203704000_2.1.e000071.17","doi-asserted-by":"crossref","DOI":"10.1186\/s13054-025-05566-6","article-title":"Evaluation of the impact of artificial intelligence-assisted image interpretation on the diagnostic performance of clinicians in identifying endotracheal tube position on plain chest X-ray: a multi-case multi-reader study","volume":"29","author":"Novak","year":"2025","journal-title":"Crit Care"},{"key":"2026070610203704000_2.1.e000071.18","article-title":"Multireader sample size program for diagnostic studies: demonstration and methodology","volume":"5","author":"Hillis","year":"2018","journal-title":"J Med Imaging (Bellingham)"},{"key":"2026070610203704000_2.1.e000071.19","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.211593"},{"key":"2026070610203704000_2.1.e000071.20","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2004.04.014"},{"key":"2026070610203704000_2.1.e000071.21","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A8387"},{"key":"2026070610203704000_2.1.e000071.22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1117\/1.JMI.5.4.045503","article-title":"Multireader sample size program for diagnostic studies: demonstration and methodology","volume":"5","author":"Hillis","year":"2018","journal-title":"J Med Imag"}],"container-title":["BMJ Digital Health &amp; AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjdh-2026-000071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T17:22:12Z","timestamp":1783358532000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjdigitalhealth.bmj.com\/lookup\/doi\/10.1136\/bmjdh-2026-000071"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1136\/bmjdh-2026-000071"],"URL":"https:\/\/doi.org\/10.1136\/bmjdh-2026-000071","relation":{},"ISSN":["3049-575X"],"issn-type":[{"value":"3049-575X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}