{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T07:32:13Z","timestamp":1794036733064,"version":"4.8.0"},"reference-count":43,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"content-domain":{"domain":["academicradiology.org","clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Academic Radiology"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.acra.2025.10.043","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T21:06:37Z","timestamp":1763067997000},"page":"337-347","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":7,"title":["Performance of Large Language Models on Radiology Residency In-Training Examination Questions"],"prefix":"10.1016","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6157-6367","authenticated-orcid":false,"given":"Ali","family":"Salbas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Murat","family":"Yogurtcu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.acra.2025.10.043_bib1","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat Med"},{"issue":"3","key":"10.1016\/j.acra.2025.10.043_bib2","doi-asserted-by":"crossref","first-page":"932","DOI":"10.1038\/s41591-024-03416-6","article-title":"A generalist medical language model for disease diagnosis assistance","volume":"31","author":"Liu","year":"2025","journal-title":"Nat Med"},{"issue":"1","key":"10.1016\/j.acra.2025.10.043_bib3","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s12911-024-02838-z","article-title":"Enhancing doctor-patient communication using large language models for pathology report interpretation","volume":"25","author":"Yang","year":"2025","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"10.1016\/j.acra.2025.10.043_bib4","doi-asserted-by":"crossref","first-page":"193","DOI":"10.52312\/jdrs.2025.1961","article-title":"Evaluation of ChatGPT-4o\u2019s answers to questions about hip arthroscopy from the patient perspective","volume":"36","author":"Ay\u0131k","year":"2025","journal-title":"Jt Dis Relat Surg"},{"key":"10.1016\/j.acra.2025.10.043_bib5","article-title":"Diagnostic precision of a deep learning algorithm for the classification of non-contrast brain CT reports","volume":"5","author":"G\u00fczel","year":"2025","journal-title":"Front\u00a0Radiol"},{"issue":"2","key":"10.1016\/j.acra.2025.10.043_bib6","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.230205","article-title":"Generative large language models for detection of speech recognition errors in radiology reports","volume":"6","author":"Schmidt","year":"2024","journal-title":"Radiol Artif Intell"},{"issue":"11","key":"10.1016\/j.acra.2025.10.043_bib7","first-page":"1276","article-title":"A systematic review of large language models and their implications in medical education","volume":"58","author":"Lucas","year":"2024","journal-title":"Med Educ. John Wiley and Sons Inc."},{"issue":"5","key":"10.1016\/j.acra.2025.10.043_bib8","doi-asserted-by":"crossref","first-page":"635","DOI":"10.3390\/diagnostics15050635","article-title":"Comparing ChatGPT 4.0\u2032s performance in interpreting thyroid nodule ultrasound reports using ACR-TI-RADS 2017: analysis across different levels of ultrasound user experience","volume":"15","author":"Wakonig","year":"2025","journal-title":"Diagnostics"},{"issue":"8","key":"10.1016\/j.acra.2025.10.043_bib9","doi-asserted-by":"crossref","first-page":"1583","DOI":"10.1007\/s00256-024-04638-y","article-title":"Validity of ChatGPT-generated musculoskeletal images","volume":"53","author":"Ajmera","year":"2024","journal-title":"Skeletal Radiol"},{"key":"10.1016\/j.acra.2025.10.043_bib10","doi-asserted-by":"crossref","DOI":"10.1016\/j.acra.2025.07.058","article-title":"Multimodal large language models for pediatric bone-age assessment: a comparative accuracy analysis","author":"B\u00fcy\u00fcktoka","year":"2025","journal-title":"Acad Radiol"},{"issue":"5","key":"10.1016\/j.acra.2025.10.043_bib11","doi-asserted-by":"crossref","first-page":"2589","DOI":"10.1007\/s00330-024-11107-6","article-title":"Large language models for structured reporting in radiology: past, present, and future","volume":"35","author":"Busch","year":"2024","journal-title":"Eur Radiol"},{"key":"10.1016\/j.acra.2025.10.043_bib12","article-title":"RadGPT: a system based on a large language model that generates sets of patient-centered materials to explain radiology report information","author":"Herwald","year":"2025","journal-title":"J\u00a0Am\u00a0Coll\u00a0Radiol"},{"key":"10.1016\/j.acra.2025.10.043_bib13","doi-asserted-by":"crossref","DOI":"10.1016\/j.acra.2024.06.046","article-title":"Large language models as tools to generate radiology board-style multiple-choice questions","author":"Mistry","year":"2024","journal-title":"Acad Radiol"},{"issue":"5","key":"10.1016\/j.acra.2025.10.043_bib14","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.acra.2025.10.043_bib15","doi-asserted-by":"crossref","first-page":"e","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"},{"issue":"2","key":"10.1016\/j.acra.2025.10.043_bib16","doi-asserted-by":"crossref","first-page":"304","DOI":"10.52312\/jdrs.2025.1958","article-title":"Assessing the performance of ChatGPT-4o on the Turkish Orthopedics and Traumatology Board Examination","volume":"36","author":"Ya\u011far","year":"2025","journal-title":"Jt Dis Relat Surg"},{"issue":"8","key":"10.1016\/j.acra.2025.10.043_bib17","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.acra.2025.10.043_bib18","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"8706","article-title":"Investigating data contamination in modern benchmarks for large language models","author":"Deng","year":"2024"},{"issue":"7","key":"10.1016\/j.acra.2025.10.043_bib19","doi-asserted-by":"crossref","first-page":"3046","DOI":"10.1016\/j.acra.2024.04.006","article-title":"Performance of GPT-4 on the American College of Radiology In-training Examination: evaluating accuracy, model drift, and fine-tuning","volume":"31","author":"Payne","year":"2024","journal-title":"Acad Radiol"},{"issue":"3","key":"10.1016\/j.acra.2025.10.043_bib20","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.240153","article-title":"Performance of GPT-4 with vision on text- and image-based ACR diagnostic radiology in-training examination questions","volume":"312","author":"Hayden","year":"2024","journal-title":"Radiology"},{"key":"10.1016\/j.acra.2025.10.043_bib21","unstructured":"Google. Gemini. 2025. Accessed July 5, 2025. \u3008https:\/\/gemini.google.com\/\u3009."},{"key":"10.1016\/j.acra.2025.10.043_bib22","unstructured":"OpenAI. ChatGPT-4o web platform. 2025. Accessed July 5, 2025. \u3008https:\/\/chat.openai.com\u3009."},{"key":"10.1016\/j.acra.2025.10.043_bib23","unstructured":"Anthropic. Claude.ai official interface. 2025. Accessed July 5, 2025. \u3008https:\/\/claude.ai\u3009."},{"key":"10.1016\/j.acra.2025.10.043_bib24","article-title":"Comparative Analysis of ChatGPT-4o and gemini advanced performance on diagnostic radiology in-training exams","author":"Huang","year":"2025","journal-title":"Cureus"},{"issue":"6","key":"10.1016\/j.acra.2025.10.043_bib25","doi-asserted-by":"crossref","first-page":"524","DOI":"10.3348\/kjr.2024.1096","article-title":"Performance of GPT-4 Turbo and GPT-4o in Korean Society of Radiology In-Training Examinations","volume":"26","author":"Choi","year":"2025","journal-title":"Korean J Radiol"},{"key":"10.1016\/j.acra.2025.10.043_bib26","doi-asserted-by":"crossref","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"},{"issue":"2","key":"10.1016\/j.acra.2025.10.043_bib27","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"},{"issue":"11","key":"10.1016\/j.acra.2025.10.043_bib28","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1007\/s11604-024-01619-y","article-title":"Diagnostic performances of GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro in \u201cDiagnosis Please\u201d cases","volume":"42","author":"Sonoda","year":"2024","journal-title":"Jpn J Radiol"},{"issue":"2","key":"10.1016\/j.acra.2025.10.043_bib29","doi-asserted-by":"crossref","first-page":"571","DOI":"10.3390\/jcm14020571","article-title":"Evaluation of advanced artificial intelligence algorithms\u2019 diagnostic efficacy in acute ischemic stroke: a comparative analysis of ChatGPT-4o and Claude 3.5 Sonnet models","volume":"14","author":"Koyun","year":"2025","journal-title":"J Clin Med"},{"issue":"4","key":"10.1016\/j.acra.2025.10.043_bib30","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1111\/1754-9485.13858","article-title":"Comparative performance of anthropic claude and OpenAI GPT models in basic radiological imaging tasks","volume":"69","author":"Nguyen","year":"2025","journal-title":"J Med Imaging Radiat Oncol"},{"key":"10.1016\/j.acra.2025.10.043_bib31","doi-asserted-by":"crossref","DOI":"10.1007\/s00330-024-10902-5","article-title":"ChatGPT\u2019s diagnostic performance based on textual vs. visual information compared to radiologists\u2019 diagnostic performance in musculoskeletal radiology","author":"Horiuchi","year":"2024","journal-title":"Eur Radiol"},{"issue":"5","key":"10.1016\/j.acra.2025.10.043_bib32","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"},{"issue":"5","key":"10.1016\/j.acra.2025.10.043_bib33","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.230987","article-title":"GPT-4 in radiology: improvements in advanced reasoning","volume":"307","author":"Bhayana","year":"2023","journal-title":"Radiology"},{"key":"10.1016\/j.acra.2025.10.043_bib34","doi-asserted-by":"crossref","DOI":"10.1590\/0100-3984.2023.0083-en","article-title":"Performance of ChatGPT on questions from the Brazilian College of Radiology annual resident evaluation test","volume":"57","author":"Leit\u00e3o","year":"2024","journal-title":"Radiol Bras"},{"key":"10.1016\/j.acra.2025.10.043_bib35","doi-asserted-by":"crossref","DOI":"10.2196\/60807","article-title":"Performance of ChatGPT across different versions in medical licensing examinations worldwide: systematic review and meta-analysis","volume":"26","author":"Liu","year":"2024","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.acra.2025.10.043_bib36","unstructured":"OpenAI. GPT-5 System Card. August 13, 2025. Accessed September 6, 2025. \u3008https:\/\/cdn.openai.com\/gpt-5-system-card.pdf\u3009."},{"issue":"15","key":"10.1016\/j.acra.2025.10.043_bib37","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.3390\/diagnostics15151919","article-title":"Performance of large language models in recognizing brain MRI sequences: a comparative analysis of ChatGPT-4o, Claude 4 Opus, and Gemini 2.5 Pro","volume":"15","author":"Salbas","year":"2025","journal-title":"Diagnostics"},{"key":"10.1016\/j.acra.2025.10.043_bib38","article-title":"ChatGPT efficacy for answering musculoskeletal anatomy questions: a study evaluating quality and consistency between raters and timepoints","author":"Mantzou","year":"2024","journal-title":"Surg\u00a0Radiol\u00a0Anat"},{"issue":"1","key":"10.1016\/j.acra.2025.10.043_bib39","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.232756","article-title":"Chatbots and large language models in radiology: a practical primer for clinical and research applications","volume":"310","author":"Bhayana","year":"2024","journal-title":"Radiology"},{"issue":"1","key":"10.1016\/j.acra.2025.10.043_bib40","article-title":"Fine-tuning large language models for specialized use cases","volume":"3","author":"Anisuzzaman","year":"2025","journal-title":"Mayo Clinic Proc\u00a0Digital health"},{"issue":"2","key":"10.1016\/j.acra.2025.10.043_bib41","doi-asserted-by":"crossref","first-page":"126","DOI":"10.3348\/kjr.2023.0997","article-title":"Large language models: a guide for radiologists","volume":"25","author":"Kim","year":"2024","journal-title":"Korean J Radiol"},{"issue":"7972","key":"10.1016\/j.acra.2025.10.043_bib42","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"issue":"2","key":"10.1016\/j.acra.2025.10.043_bib43","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.243774","article-title":"Comparison of a specialized large language model with GPT-4o for CT and MRI radiology report summarization","volume":"316","author":"Zheng","year":"2025","journal-title":"Radiology"}],"container-title":["Academic Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1076633225010232?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1076633225010232?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T19:43:22Z","timestamp":1768938202000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1076633225010232"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["S1076633225010232"],"URL":"https:\/\/doi.org\/10.1016\/j.acra.2025.10.043","relation":{},"ISSN":["1076-6332"],"issn-type":[{"value":"1076-6332","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Performance of Large Language Models on Radiology Residency In-Training Examination Questions","name":"articletitle","label":"Article Title"},{"value":"Academic Radiology","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.acra.2025.10.043","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Association of Academic 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"}]}}