{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T08:48:30Z","timestamp":1790758110349,"version":"4.1.0"},"reference-count":46,"publisher":"Elsevier BV","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","jacr.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of the American College of Radiology"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.jacr.2026.01.017","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T15:56:32Z","timestamp":1769702192000},"page":"837-848","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"title":["Radiology Board-Style Examinations and Large Language Models: A Scoping Review of Model Performance"],"prefix":"10.1016","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0478-743X","authenticated-orcid":false,"given":"Pilar","family":"L\u00f3pez-\u00dabeda","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teodoro","family":"Mart\u00edn-Noguerol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9358-3396","authenticated-orcid":false,"given":"Antonio","family":"Luna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jacr.2026.01.017_bib1","series-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"10.1016\/j.jacr.2026.01.017_bib2","article-title":"Llama: open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.jacr.2026.01.017_bib3","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.jacr.2026.01.017_bib4","doi-asserted-by":"crossref","first-page":"1271","DOI":"10.1016\/j.jacr.2022.06.016","article-title":"Natural language processing in radiology: update on clinical applications","volume":"19","author":"L\u00f3pez-\u00dabeda","year":"2022","journal-title":"J Am Coll Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib5","doi-asserted-by":"crossref","first-page":"4833","DOI":"10.1016\/j.acra.2024.07.057","article-title":"Role of natural language processing in automatic detection of unexpected findings in radiology reports: a comparative study of RoBERTa, CNN, and ChatGPT","volume":"31","author":"L\u00f3pez-\u00dabeda","year":"2024","journal-title":"Acad Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib6","doi-asserted-by":"crossref","DOI":"10.1111\/liv.70115","article-title":"Large language models for diagnosing focal liver lesions from CT\/MRI reports: a comparative study with radiologists","volume":"45","author":"Sheng","year":"2025","journal-title":"Liver Int"},{"key":"10.1016\/j.jacr.2026.01.017_bib7","article-title":"Performance of ChatGPT on the Brazilian radiology and diagnostic imaging and mammography board examinations","volume":"6","author":"Almeida","year":"2023","journal-title":"Radiol Artif Intell"},{"key":"10.1016\/j.jacr.2026.01.017_bib8","doi-asserted-by":"crossref","first-page":"110551","DOI":"10.1016\/j.clinimag.2025.110551","article-title":"Evaluating ChatGPT\u2019s performance across radiology subspecialties: a meta-analysis of board-style examination accuracy and variability","volume":"125","author":"Nguyen","year":"2025","journal-title":"Clin Imaging"},{"key":"10.1016\/j.jacr.2026.01.017_bib9","doi-asserted-by":"crossref","DOI":"10.2196\/64284","article-title":"Performance evaluation and implications of large language models in radiology board exams: prospective comparative analysis","volume":"11","author":"Wei","year":"2025","journal-title":"JMIR Med Educ"},{"key":"10.1016\/j.jacr.2026.01.017_bib10","doi-asserted-by":"crossref","first-page":"3096","DOI":"10.1016\/j.acra.2024.11.028","article-title":"Large language models with vision on diagnostic radiology board exam style questions","volume":"32","author":"Sun","year":"2025","journal-title":"Acad Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib11","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.1055\/a-2437-2067","article-title":"Large language models (LLMs) in radiology exams for medical students: performance and consequences","volume":"197","author":"Gotta","year":"2025","journal-title":"Rofo"},{"key":"10.1016\/j.jacr.2026.01.017_bib12","doi-asserted-by":"crossref","DOI":"10.2196\/68070","article-title":"Evaluating the potential and accuracy of ChatGPT-3.5 and 4.0 in medical licensing and in-training examinations: systematic review and meta-analysis","volume":"11","author":"Jaleel","year":"2025","journal-title":"JMIR Med Educ"},{"key":"10.1016\/j.jacr.2026.01.017_bib13","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1186\/s13244-023-01507-5","article-title":"Natural language processing for automatic evaluation of free-text answers\u2014a feasibility study based on the European Diploma in Radiology examination","volume":"14","author":"Stoehr","year":"2023","journal-title":"Insights Imaging"},{"key":"10.1016\/j.jacr.2026.01.017_bib14","article-title":"Educational limitations of ChatGPT in neurosurgery board preparation","volume":"16","author":"Powers","year":"2024","journal-title":"Cureus"},{"key":"10.1016\/j.jacr.2026.01.017_bib15","doi-asserted-by":"crossref","first-page":"4347","DOI":"10.1016\/j.acra.2025.04.060","article-title":"Evaluating the performance of reasoning large language models on Japanese Radiology Board Examination questions","volume":"32","author":"Nakaura","year":"2025","journal-title":"Acad Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib16","doi-asserted-by":"crossref","first-page":"2394","DOI":"10.1016\/j.acra.2024.10.035","article-title":"Performance of multimodal large language models in Japanese Diagnostic Radiology Board Examinations (2021-2023)","volume":"32","author":"Nakaura","year":"2025","journal-title":"Acad Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib17","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/s11604-024-01673-6","article-title":"Response accuracy of GPT-4 across languages: insights from an expert-level diagnostic radiology examination in Japan","volume":"43","author":"Harigai","year":"2025","journal-title":"Jpn J Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib18","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/s11604-025-01861-y","article-title":"Assessing accuracy and legitimacy of multimodal large language models on Japan Diagnostic Radiology Board Examination","volume":"44","author":"Hirano","year":"2025","journal-title":"Jpn J Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib19","doi-asserted-by":"crossref","DOI":"10.3389\/fonc.2023.1265024","article-title":"Benchmarking ChatGPT-4 on a radiation oncology in-training exam and Red Journal Gray Zone cases: potentials and challenges for AI-assisted medical education and decision making in radiation oncology","volume":"13","author":"Huang","year":"2023","journal-title":"Front Oncol"},{"key":"10.1016\/j.jacr.2026.01.017_bib23","doi-asserted-by":"crossref","first-page":"1595","DOI":"10.1148\/rg.266065168","article-title":"RadLex: a new method for indexing online educational materials","volume":"26","author":"Langlotz","year":"2006","journal-title":"Radiographics"},{"key":"10.1016\/j.jacr.2026.01.017_bib24","doi-asserted-by":"crossref","first-page":"4974","DOI":"10.1016\/j.acra.2025.05.023","article-title":"Evaluating large language models for enhancing radiology specialty examination: a comparative study with human performance","volume":"32","author":"Liu","year":"2025","journal-title":"Acad Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib25","doi-asserted-by":"crossref","first-page":"4365","DOI":"10.1016\/j.acra.2024.09.005","article-title":"Evaluating GPT-4o\u2019s performance in the official European board of radiology exam: a comprehensive assessment","volume":"31","author":"Be\u015fler","year":"2024","journal-title":"Acad Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib26","doi-asserted-by":"crossref","DOI":"10.5114\/pjr.2023.131215","article-title":"Will ChatGPT pass the Polish specialty exam in radiology and diagnostic imaging? Insights into strengths and limitations","volume":"88","author":"Kufel","year":"2023","journal-title":"Pol J Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib27","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.241489","article-title":"Retrieval-augmented generation for large language models in radiology: another leap forward in board examination performance","volume":"313","author":"Bhayana","year":"2024","journal-title":"Radiology"},{"key":"10.1016\/j.jacr.2026.01.017_bib28","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.241191","article-title":"Llama 3 challenges proprietary state-of-the-art large language models in radiology board-style examination questions","volume":"312","author":"Adams","year":"2024","journal-title":"Radiology"},{"key":"10.1016\/j.jacr.2026.01.017_bib29","article-title":"Comparative analysis of ChatGPT-4o and Gemini advanced performance on diagnostic radiology in-training exams","volume":"17","author":"Huang","year":"2025","journal-title":"Cureus"},{"key":"10.1016\/j.jacr.2026.01.017_bib30","doi-asserted-by":"crossref","first-page":"6981","DOI":"10.1016\/j.acra.2025.09.008","article-title":"Performance comparison of cutting-edge large language models on the ACR in-training examination: An Update for 2025","volume":"32","author":"Young","year":"2025","journal-title":"Acad Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib31","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.232715","article-title":"Evaluation of reliability, repeatability, robustness, and confidence of GPT-3.5 and GPT-4 on a radiology board-style examination","volume":"311","author":"Krishna","year":"2024","journal-title":"Radiology"},{"key":"10.1016\/j.jacr.2026.01.017_bib32","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1007\/s11548-024-03071-9","article-title":"Generative pretrained transformer-4, an artificial intelligence text predictive model, has a high capability for passing novel written radiology exam questions","volume":"19","author":"Sood","year":"2024","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"10.1016\/j.jacr.2026.01.017_bib33","first-page":"1","article-title":"Performance assessment of ChatGPT for the board qualification examination of the Japanese society for oral and maxillofacial radiology","author":"Takeshita","year":"2025","journal-title":"Technol Knowl Learn"},{"key":"10.1016\/j.jacr.2026.01.017_bib34","article-title":"Unveiling GPT-4V\u2019s hidden challenges behind high accuracy on USMLE questions: observational study","volume":"27","author":"Yang","year":"2025","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.jacr.2026.01.017_bib35","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejrad.2024.111842","article-title":"Large language models in radiology: fluctuating performance and decreasing discordance over time","volume":"182","author":"Gupta","year":"2025","journal-title":"Eur J Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib36","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1016\/j.jacr.2023.09.011","article-title":"Enhancing patient communication with Chat-GPT in radiology: evaluating the efficacy and readability of answers to common imaging-related questions","volume":"21","author":"Gordon","year":"2024","journal-title":"J Am Coll Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib37","doi-asserted-by":"crossref","DOI":"10.1016\/j.clinimag.2024.110193","article-title":"Evaluation of responses to cardiac imaging questions by the artificial intelligence large language model ChatGPT","volume":"112","author":"Monroe","year":"2024","journal-title":"Clin Imaging"},{"key":"10.1016\/j.jacr.2026.01.017_bib38","doi-asserted-by":"crossref","first-page":"12312","DOI":"10.64912\/RADT.2025.JDYI8440","article-title":"Comparative analysis of LLMs\u2019 performance on a practice radiography certification exam","volume":"96","author":"Clark","year":"2025","journal-title":"Radiol Technol"},{"key":"10.1016\/j.jacr.2026.01.017_bib39","doi-asserted-by":"crossref","first-page":"3872","DOI":"10.1016\/j.acra.2024.06.046","article-title":"Large language models as tools to generate radiology board-style multiple-choice questions","volume":"31","author":"Mistry","year":"2024","journal-title":"Acad Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib40","doi-asserted-by":"crossref","DOI":"10.1016\/j.jmir.2025.101896","article-title":"AI in radiography education: evaluating multiple-choice questions difficulty and discrimination","volume":"56","author":"Emekli","year":"2025","journal-title":"J Med Imaging Radiat Sci"},{"key":"10.1016\/j.jacr.2026.01.017_bib41","doi-asserted-by":"crossref","first-page":"5635","DOI":"10.1016\/j.acra.2025.06.019","article-title":"Leveraging ChatGPT for enhancing learning in radiology resident education","volume":"32","author":"Zheng","year":"2025","journal-title":"Acad Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib42","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.230582","article-title":"Performance of ChatGPT on a radiology board-style examination: insights into current strengths and limitations","volume":"307","author":"Bhayana","year":"2023","journal-title":"Radiology"},{"key":"10.1016\/j.jacr.2026.01.017_bib43","doi-asserted-by":"crossref","first-page":"918","DOI":"10.1007\/s11604-024-01561-z","article-title":"GPT-4 Turbo with vision fails to outperform text-only GPT-4 Turbo in the Japan Diagnostic Radiology Board Examination","volume":"42","author":"Hirano","year":"2024","journal-title":"Jpn J Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib44","doi-asserted-by":"crossref","first-page":"1392","DOI":"10.1007\/s11604-024-01633-0","article-title":"Diagnostic accuracy of vision-language models on Japanese diagnostic radiology, nuclear medicine, and interventional radiology specialty board examinations","volume":"42","author":"Oura","year":"2024","journal-title":"Jpn J Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib45","doi-asserted-by":"crossref","DOI":"10.1016\/j.clinimag.2024.110276","article-title":"Encouragement vs. liability: how prompt engineering influences ChatGPT-4\u2019s radiology exam performance","volume":"115","author":"Nguyen","year":"2024","journal-title":"Clin Imaging"},{"key":"10.1016\/j.jacr.2026.01.017_bib46","doi-asserted-by":"crossref","DOI":"10.1016\/j.jmir.2024.04.019","article-title":"ChatGPT performance on radiation technologist and therapist entry to practice exams","volume":"55","author":"Duggan","year":"2024","journal-title":"J Med Imaging Radiat Sci"},{"key":"10.1016\/j.jacr.2026.01.017_bib47","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/s11604-023-01491-2","article-title":"Performance evaluation of ChatGPT, GPT-4, and Bard on the official board examination of the Japan Radiology Society","volume":"42","author":"Toyama","year":"2024","journal-title":"Jpn J Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib48","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1016\/j.acra.2024.08.009","article-title":"Evaluating artificial intelligence competency in education: performance of ChatGPT-4 in the American Registry of Radiologic Technologists (ARRT) radiography certification exam","volume":"32","author":"Al-Naser","year":"2025","journal-title":"Acad Radiol"},{"key":"10.1016\/j.jacr.2026.01.017_bib49","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1177\/08465371231193716","article-title":"Comparative performance of ChatGPT and Bard in a text-based radiology knowledge assessment","volume":"75","author":"Patil","year":"2024","journal-title":"Can Assoc Radiol J"}],"container-title":["Journal of the American College of Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1546144026000396?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1546144026000396?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T04:18:18Z","timestamp":1778818698000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1546144026000396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":46,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["S1546144026000396"],"URL":"https:\/\/doi.org\/10.1016\/j.jacr.2026.01.017","relation":{},"ISSN":["1546-1440"],"issn-type":[{"value":"1546-1440","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Radiology Board-Style Examinations and Large Language Models: A Scoping Review of Model Performance","name":"articletitle","label":"Article Title"},{"value":"Journal of the American College of Radiology","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jacr.2026.01.017","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 American College of Radiology. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}