{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:45:52Z","timestamp":1787323552098,"version":"build-2736575974"},"reference-count":24,"publisher":"BMJ","issue":"8","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"unspecified","delay-in-days":20,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Small Business Research Initiative","award":["SBRIH26P3067"],"award-info":[{"award-number":["SBRIH26P3067"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2026,8,6]]},"published-print":{"date-parts":[[2026,8]]},"abstract":"\n Introduction<\/jats:title>\n Fracture misdiagnosis is a common diagnostic error in emergency departments (EDs) and minor injury units (MIUs), leading to poor patient outcomes, unnecessary treatments and significant healthcare costs. Artificial intelligence (AI)-assisted fracture detection tools are now available for use in radiology workflows; however, the impact of these technologies on patient outcomes, experiences and overall care pathways in the real-world clinical setting is limited.<\/jats:p>\n <\/jats:sec>\n \n Methods and analysis<\/jats:title>\n We will conduct a prospective cluster randomised cross-over trial over a 6-month period, assessing the impact of an AI-assisted fracture detection tool in EDs and MIUs across 4 healthcare Trusts in the UK. Patients aged over 2 years old undergoing a plain film radiography for a suspected fracture as part of routine clinical care will be eligible for study enrolment. The trial will deploy Radiobotics\u2019 RBfracture, a CE-approved AI-assisted medical device software for fracture detection at each site for 6\u2009months. Randomisation will be at a cluster-level; a site will be randomised to begin with \u2018AI on\u2019 or \u2018AI off\u2019 for a month, followed by alternating active status each month for the remaining 5 months. The primary outcome will evaluate the incidence of \u2018inappropriate healthcare contacts\u2019 among patients receiving imaging for suspected fractures. This composite metric encompasses inappropriate referrals to fracture clinics, repeated hospital attendances and subsequent follow-up communications regarding missed fractures. The rates of these measures will be compared in the \u2018AI on\u2019 versus \u2018AI off\u2019 stages. Secondary outcomes will include patient-reported outcomes, clinician surveys, a predefined health economic evaluation assessing cost-effectiveness and budget impact and the diagnostic performance of the algorithm.<\/jats:p>\n <\/jats:sec>\n \n Ethics and dissemination<\/jats:title>\n The study has received ethical approval from the South Central\u2014Oxford Research Ethics Committee (Reference: 25\/SC\/0252, approval date: 23 October 2025), and subsequently from the Health Research Authority (IRAS 3\u200957\u2009391-A). The results of this study will be presented at relevant scientific conferences and peer-reviewed publications will be disseminated on wider public forums such as traditional and social media.<\/jats:p>\n <\/jats:sec>\n \n Registration details<\/jats:title>\n \n This is an ongoing, actively recruiting trial (\n ISRCTN23087950<\/jats:ext-link>\n ). Recruitment began in January 2026 and will run for 6\u2009months at each site, with per-patient follow-up of 30 days and subsequent data analysis. This manuscript describes protocol version 1.1. The full protocol and statistical analysis plan are available from the corresponding author on request and will be deposited on the study\u2019s public repository (\n https:\/\/github.com\/Jason-L-Oke\/SAMURAI<\/jats:ext-link>\n ) prior to publication of results.\n <\/jats:p>\n <\/jats:sec>\n \n Trial registration number<\/jats:title>\n \n ISRCTN23087950<\/jats:ext-link>\n .\n <\/jats:p>\n <\/jats:sec>","DOI":"10.1136\/bmjopen-2026-120631","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:08:36Z","timestamp":1787321316000},"page":"e120631","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Systematic assessment of the medical utility of radiology and diagnostic Artificial Intelligence in fracture detection (SAMURAI-fracture): a protocol for a multicentre cluster-randomised controlled trial"],"prefix":"10.1136","volume":"16","clinical-trial-number":[{"clinical-trial-number":"isrctn23087950","registry":"10.18810\/isrctn"},{"clinical-trial-number":"isrctn23087950","registry":"10.18810\/isrctn"}],"author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5880-8235","authenticated-orcid":false,"given":"Alex","family":"Novak","sequence":"first","affiliation":[{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford, UK"},{"name":"Emergency Medicine Research Oxford (EMROx), Oxford University Hospitals NHS Foundation Trust, Oxford, Oxfordshire, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0513-7220","authenticated-orcid":false,"given":"James","family":"Vaz","sequence":"additional","affiliation":[{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0967-3554","authenticated-orcid":false,"given":"Abdala T","family":"Espinosa Morgado","sequence":"additional","affiliation":[{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0988-3458","authenticated-orcid":false,"given":"Sally","family":"Beer","sequence":"additional","affiliation":[{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5204-9688","authenticated-orcid":false,"given":"Katrina","family":"Nash","sequence":"additional","affiliation":[{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford, UK"},{"name":"Oxford University Clinical Undergraduate School (OUCAGs), University of Oxford, Oxford, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashar","family":"Asif","sequence":"additional","affiliation":[{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Lundemann","sequence":"additional","affiliation":[{"name":"Radiobotics ApS, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1008-3105","authenticated-orcid":false,"given":"David","family":"Metcalfe","sequence":"additional","affiliation":[{"name":"Emergency Department, Oxford University Hospitals NHS Foundation Trust, Oxford, UK"},{"name":"Nuffield Department of Orthopaedics, Rheumatology & Musculoskeletal Sciences, University of Oxford, Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew L","family":"Costa","sequence":"additional","affiliation":[{"name":"Kadoorie Institute for Trauma, Emergency and Critical Care, University of Oxford, Oxford, Oxfordshire, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9598-189X","authenticated-orcid":false,"given":"Nick","family":"Woznitza","sequence":"additional","affiliation":[{"name":"University College London Hospitals NHS Foundation Trust, London, England, UK"},{"name":"University College London, London, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5615-8657","authenticated-orcid":false,"given":"Mamta","family":"Bajre","sequence":"additional","affiliation":[{"name":"Health Innovation Oxford and Thames Valley (HIOTV), Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2952-3176","authenticated-orcid":false,"given":"Niks","family":"Kolosnicins","sequence":"additional","affiliation":[{"name":"PPI Representative, Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Clarke","sequence":"additional","affiliation":[{"name":"Royal Berkshire NHS Foundation Trust, Reading, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4690-9873","authenticated-orcid":false,"given":"Rose","family":"Kunnath","sequence":"additional","affiliation":[{"name":"Royal Berkshire NHS Foundation Trust, Reading, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2277-6069","authenticated-orcid":false,"given":"Ammar","family":"Salem","sequence":"additional","affiliation":[{"name":"Buckinghamshire Healthcare NHS Trust, Amersham, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sachin","family":"Mandalia","sequence":"additional","affiliation":[{"name":"Oxford Health NHS Foundation Trust, Oxford, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8886-9891","authenticated-orcid":false,"given":"Andrew G","family":"Murchison","sequence":"additional","affiliation":[{"name":"Buckinghamshire Healthcare NHS Trust, Amersham, England, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6642-9967","authenticated-orcid":false,"given":"Susan Cheng","family":"Shelmerdine","sequence":"additional","affiliation":[{"name":"Clinical Radiology, Great Ormond Street Hospital for Children, London, UK"},{"name":"UCL Great Ormond Street Institute of Child Health, London, UK"},{"name":"NIHR Great Ormond Street Hospital Biomedical Research Centre, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4866-2049","authenticated-orcid":false,"given":"David","family":"Lowe","sequence":"additional","affiliation":[{"name":"Digital Health Validation Lab, University of Glasgow, Glasgow, Scotland, UK"},{"name":"Emergency Department, NHS Greater Glasgow and Clyde, Glasgow, Scotland, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3467-6677","authenticated-orcid":false,"given":"Jason","family":"Oke","sequence":"additional","affiliation":[{"name":"Oxford Biostatistics Ltd, Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9614-5033","authenticated-orcid":false,"given":"Sarim","family":"Ather","sequence":"additional","affiliation":[{"name":"Oxford Clinical Artificial Intelligence Research (OxCAIR), Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"2026082106551211000_16.8.e120631.1","unstructured":"NHS Resolution . Thematic review 2: missed fractures. 2022 Available: https:\/\/resolution.nhs.uk\/wp-content\/uploads\/2022\/03\/2-NHS-Resolution-ED-report-Missed-Fractures.pdf"},{"key":"2026082106551211000_16.8.e120631.2","unstructured":"TWLMP . The importance of flagging abnormal x-ray findings that are not detected in the emergency department. 2021 Available: https:\/\/www.twlemp.com\/clinical-learning\/2021-06-15-the-importance-of-flagging-abnormal-x-ray-findings-that-are-not-detected-in-the-emergency-department"},{"key":"2026082106551211000_16.8.e120631.3","unstructured":"National Institute of Health and Care Excellence (GES) . Fractures (non-complex): assessment and management (February, 2016)."},{"key":"2026082106551211000_16.8.e120631.4","unstructured":"NHS digital . Hospital accident & emergency activity 2021-22 (Published in September, 2023). Available: https:\/\/digital.nhs.uk\/data-and-information\/publications\/statistical\/hospital-accident--emergency-activity"},{"key":"2026082106551211000_16.8.e120631.5","doi-asserted-by":"publisher","DOI":"10.1136\/emj.18.4.263"},{"key":"2026082106551211000_16.8.e120631.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajem.2009.07.011"},{"key":"2026082106551211000_16.8.e120631.7","doi-asserted-by":"crossref","DOI":"10.1259\/bjr.20120112","article-title":"The impact of immediate reporting on interpretive discrepancies and patient referral pathways within the emergency department: a randomised controlled trial","volume":"86","author":"Hardy","year":"2013","journal-title":"Br J Radiol"},{"key":"2026082106551211000_16.8.e120631.8","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1016\/j.crad.2020.02.019","article-title":"Getting it right first time in radiology","volume":"75","author":"Halliday","year":"2020","journal-title":"Clin Radiol"},{"key":"2026082106551211000_16.8.e120631.9","doi-asserted-by":"crossref","DOI":"10.5334\/jbsr.3574","article-title":"Radiographic Detection of Post-Traumatic Bone Fractures: Contribution of Artificial Intelligence Software to the Analysis of Senior and Junior Radiologists","volume":"108","author":"Dell\u2019Aria","year":"2024","journal-title":"J Belg Soc Radiol"},{"key":"2026082106551211000_16.8.e120631.10","doi-asserted-by":"crossref","first-page":"1675","DOI":"10.1007\/s00247-023-05621-w","article-title":"Comparison of diagnostic performance of a deep learning algorithm, emergency physicians, junior radiologists and senior radiologists in the detection of appendicular fractures in children","volume":"53","author":"Gasmi","year":"2023","journal-title":"Pediatr Radiol"},{"key":"2026082106551211000_16.8.e120631.11","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1007\/s00256-019-03317-7","article-title":"Reporting Discrepancy Resolved by Findings and time in 2947 emergency department ankle x-rays","volume":"49","author":"York","year":"2020","journal-title":"Skeletal Radiol"},{"key":"2026082106551211000_16.8.e120631.12","doi-asserted-by":"crossref","DOI":"10.1186\/1471-227X-6-4","article-title":"Errors in fracture diagnoses in the emergency department--characteristics of patients and diurnal variation","volume":"6","author":"Hallas","year":"2006","journal-title":"BMC Emerg Med"},{"key":"2026082106551211000_16.8.e120631.13","unstructured":"England N . Diagnostic imaging reporting turnaround times. Available: https:\/\/www.england.nhs.uk\/lead\/diagnostic-imaging-reporting-turnaround-times\/"},{"key":"2026082106551211000_16.8.e120631.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.radi.2014.10.001"},{"key":"2026082106551211000_16.8.e120631.15","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.22.27873"},{"key":"2026082106551211000_16.8.e120631.16","doi-asserted-by":"crossref","unstructured":"Kuo RYL , Harrison C , Curran T-A , et al . Artificial Intelligence in Fracture Detection: A Systematic Review and Meta-Analysis. Radiology 2022;50\u201362. doi:10.1148\/radiol.211785","DOI":"10.1148\/radiol.211785"},{"key":"2026082106551211000_16.8.e120631.17","doi-asserted-by":"crossref","unstructured":"Guermazi A , Tannoury C , Kompel AJ , et al . Improving Radiographic Fracture Recognition Performance and Efficiency Using Artificial Intelligence. Radiology 2022;627\u201336. doi:10.1148\/radiol.210937","DOI":"10.1148\/radiol.210937"},{"key":"2026082106551211000_16.8.e120631.18","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2021203886"},{"key":"2026082106551211000_16.8.e120631.19","doi-asserted-by":"crossref","first-page":"e216","DOI":"10.1016\/S2589-7500(22)00030-9","article-title":"Building an evidence standards framework for artificial intelligence-enabled digital health technologies","volume":"4","author":"Unsworth","year":"2022","journal-title":"The Lancet Digital Health"},{"key":"2026082106551211000_16.8.e120631.20","unstructured":"National institute of health and care excellence . Artificial Intelligence (AI) derived software to help clinical decision making in strok. 2024 Available: https:\/\/www.nice.org.uk\/guidance\/ds57"},{"key":"2026082106551211000_16.8.e120631.21","unstructured":"Vimalanathan K , Robert D , Kumar S , et al . Assessing the effectiveness of artificial intelligence (AI) in prioritising CT head interpretation: study protocol for a stepped-wedge cluster randomised trial (ACCEPT-AI). BMJ Open 2024. doi:10.1136\/bmjopen-2023-071347"},{"key":"2026082106551211000_16.8.e120631.22","article-title":"Determining the impact of an artificial intelligence tool on the management of pulmonary nodules detected incidentally on CT (DOLCE) study protocol: a prospective, non-interventional multicentre UK study","volume":"14","author":"O\u2019Dowd","year":"2024","journal-title":"BMJ Open"},{"key":"2026082106551211000_16.8.e120631.23","unstructured":"Health Research Authority . RADICAL: radiograph accelerated detection and identification of cancer. 2023 Available: https:\/\/www.hra.nhs.uk\/planning-and-improving-research\/application-summaries\/research-summaries\/radical-radiograph-accelerated-detection-and-identification-of-cancer\/"},{"key":"2026082106551211000_16.8.e120631.24","unstructured":"Jason-L-Oke . SAMURAI GitHub. 2026 Available: https:\/\/github.com\/Jason-L-Oke\/SAMURAI Contributions"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2026-120631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:08:44Z","timestamp":1787321324000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2026-120631"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":24,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,21]]},"published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1136\/bmjopen-2026-120631"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2026-120631","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}