{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T12:25:28Z","timestamp":1775219128373,"version":"3.50.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","journalofsurgicalresearch.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Surgical Research"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1016\/j.jss.2025.06.026","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T09:37:08Z","timestamp":1752572228000},"page":"66-77","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Evaluating the Performance of Large Language Models on Multispecialty FRCS Section 1 Questions"],"prefix":"10.1016","volume":"313","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1671-8474","authenticated-orcid":false,"given":"H Shafeeq","family":"Ahmed","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.jss.2025.06.026_bib1","doi-asserted-by":"crossref","DOI":"10.1016\/j.isci.2024.109713","article-title":"The application of large language models in medicine: a scoping review","volume":"27","author":"Meng","year":"2024","journal-title":"iScience"},{"key":"10.1016\/j.jss.2025.06.026_bib2","doi-asserted-by":"crossref","first-page":"A1","DOI":"10.1016\/j.mri.2019.12.006","article-title":"Artificial intelligence in medical imaging","volume":"68","author":"Gore","year":"2020","journal-title":"Magn Reson Imaging"},{"key":"10.1016\/j.jss.2025.06.026_bib3","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/s43856-023-00370-1","article-title":"The future landscape of large language models in medicine","volume":"3","author":"Clusmann","year":"2023","journal-title":"Commun Med (Lond)"},{"key":"10.1016\/j.jss.2025.06.026_bib4","doi-asserted-by":"crossref","first-page":"656","DOI":"10.5435\/JAAOS-D-23-00877","article-title":"Evaluating ChatGPT's ability to answer common patient questions regarding hip fracture","volume":"32","author":"Wrenn","year":"2024","journal-title":"J Am Acad Orthop Surg"},{"key":"10.1016\/j.jss.2025.06.026_bib5","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1111\/ans.18834","article-title":"Evaluation of a chat GPT generated patient information leaflet about laparoscopic cholecystectomy","volume":"94","author":"Lockie","year":"2024","journal-title":"ANZ J Surg"},{"key":"10.1016\/j.jss.2025.06.026_bib6","article-title":"Assessing ChatGPT's diagnostic accuracy and therapeutic strategies in oral pathologies: a cross-sectional study","volume":"16","author":"Uranbey","year":"2024","journal-title":"Cureus"},{"key":"10.1016\/j.jss.2025.06.026_bib7","doi-asserted-by":"crossref","DOI":"10.2196\/47621","article-title":"The potential of ChatGPT as a self-diagnostic tool in common orthopedic diseases: exploratory study","volume":"25","author":"Kuroiwa","year":"2023","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.jss.2025.06.026_bib8","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1186\/s13741-024-00469-6","article-title":"The performance of ChatGPT in day surgery and pre-anesthesia risk assessment: a case-control study of 150 simulated patient presentations","volume":"13","author":"Cheng","year":"2024","journal-title":"Perioper Med (Lond)"},{"key":"10.1016\/j.jss.2025.06.026_bib9","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1097\/SAP.0000000000004090","article-title":"Comparing provider and ChatGPT responses to breast reconstruction patient questions in the electronic health record","volume":"93","author":"Soroudi","year":"2024","journal-title":"Ann Plast Surg"},{"key":"10.1016\/j.jss.2025.06.026_bib10","doi-asserted-by":"crossref","DOI":"10.1177\/23821205241238641","article-title":"Can ChatGPT-3.5 Pass a medical exam? A systematic review of ChatGPT's performance in academic testing","volume":"11","author":"Sumbal","year":"2024","journal-title":"J Med Educ Curric Dev"},{"key":"10.1016\/j.jss.2025.06.026_bib11","first-page":"676","article-title":"The Fellowship of the Royal College of Surgeons","volume":"54","year":"1913","journal-title":"Hospital (Lond 1886)"},{"key":"10.1016\/j.jss.2025.06.026_bib12","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1177\/014107680710000906","article-title":"The royal college of surgeons","volume":"100","author":"Loudon","year":"2007","journal-title":"J R Soc Med"},{"key":"10.1016\/j.jss.2025.06.026_bib16","author":"Perplexity"},{"key":"10.1016\/j.jss.2025.06.026_bib18","doi-asserted-by":"crossref","first-page":"237","DOI":"10.5694\/mja2.52061","article-title":"This too shall pass: the performance of ChatGPT-3.5, ChatGPT-4 and New Bing in an Australian medical licensing examination","volume":"219","author":"Kleinig","year":"2023","journal-title":"Med J Aust"},{"key":"10.1016\/j.jss.2025.06.026_bib19","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000397","article-title":"How does ChatGPT-4 preform on non-English national medical licensing examination? An evaluation in Chinese language","volume":"2","author":"Fang","year":"2023","journal-title":"PLOS Digit Health"},{"key":"10.1016\/j.jss.2025.06.026_bib20","doi-asserted-by":"crossref","DOI":"10.1136\/bmjhci-2023-100815","article-title":"ChatGPT in Iranian medical licensing examination: evaluating the diagnostic accuracy and decision-making capabilities of an AI-based model","volume":"30","author":"Ebrahimian","year":"2023","journal-title":"BMJ Health Care Inform"},{"key":"10.1016\/j.jss.2025.06.026_bib21","doi-asserted-by":"crossref","DOI":"10.2196\/48002","article-title":"Performance of GPT-3.5 and GPT-4 on the Japanese medical licensing examination: comparison study","volume":"9","author":"Takagi","year":"2023","journal-title":"JMIR Med Educ"},{"key":"10.1016\/j.jss.2025.06.026_bib22","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000416","article-title":"GPT-4 can pass the Korean national licensing examination for Korean medicine doctors","volume":"2","author":"Jang","year":"2023","journal-title":"PLOS Digit Health"},{"key":"10.1016\/j.jss.2025.06.026_bib23","article-title":"ChatGPT conquers the Saudi medical licensing exam: exploring the accuracy of artificial intelligence in medical knowledge assessment and implications for modern medical education","volume":"15","author":"Aljindan","year":"2023","journal-title":"Cureus"},{"key":"10.1016\/j.jss.2025.06.026_bib24","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0307372","article-title":"Evaluating the competency of ChatGPT in MRCP Part 1 and a systematic literature review of its capabilities in postgraduate medical assessments","volume":"19","author":"Vij","year":"2024","journal-title":"PLoS One"},{"key":"10.1016\/j.jss.2025.06.026_bib25","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2023-080558","article-title":"Can ChatGPT pass the MRCP (UK) written examinations? Analysis of performance and errors using a clinical decision-reasoning framework","volume":"14","author":"Maitland","year":"2024","journal-title":"BMJ Open"},{"key":"10.1016\/j.jss.2025.06.026_bib26","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1308\/rcsann.2024.0023","article-title":"The performance of large language models in intercollegiate Membership of the Royal College of Surgeons examination","volume":"106","author":"Chan","year":"2024","journal-title":"Ann R Coll Surg Engl"},{"key":"10.1016\/j.jss.2025.06.026_bib27","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.1136\/bjo-2023-324091","article-title":"Performance of ChatGPT and Bard on the official part 1 FRCOphth practice questions","volume":"108","author":"Fowler","year":"2024","journal-title":"Br J Ophthalmol"},{"key":"10.1016\/j.jss.2025.06.026_bib28","doi-asserted-by":"crossref","first-page":"172.e1","DOI":"10.1016\/j.ajog.2023.04.020","article-title":"ChatGPT outscored human candidates in a virtual objective structured clinical examination in obstetrics and gynecology","volume":"229","author":"Li","year":"2023","journal-title":"Am J Obstet Gynecol"},{"key":"10.1016\/j.jss.2025.06.026_bib29","doi-asserted-by":"crossref","first-page":"2178","DOI":"10.1016\/j.acra.2023.11.026","article-title":"Could ChatGPT pass the UK Radiology fellowship examinations?","volume":"31","author":"Ariyaratne","year":"2024","journal-title":"Acad Radiol"},{"key":"10.1016\/j.jss.2025.06.026_bib30","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.surge.2023.07.001","article-title":"Assessing ChatGPT's ability to pass the FRCS orthopaedic part A exam: a critical analysis","volume":"21","author":"Saad","year":"2023","journal-title":"Surgeon"},{"key":"10.1016\/j.jss.2025.06.026_bib31","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.surge.2024.11.008","article-title":"Enhancements in artificial intelligence for medical examinations: a leap from ChatGPT 3.5 to ChatGPT 4.0 in the FRCS trauma & orthopaedics examination","volume":"23","author":"Khan","year":"2025","journal-title":"Surgeon"},{"key":"10.1016\/j.jss.2025.06.026_bib32","doi-asserted-by":"crossref","first-page":"865","DOI":"10.3348\/kjr.2024.0843","article-title":"Minimum reporting Items for clear evaluation of accuracy Reports of Large Language Models in healthcare (MI-CLEAR-LLM)","volume":"25","author":"Park","year":"2024","journal-title":"Korean J Radiol"},{"key":"10.1016\/j.jss.2025.06.026_bib33","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"},{"key":"10.1016\/j.jss.2025.06.026_bib34","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.21873\/invivo.13534","article-title":"Artificial intelligence and ChatGPT in abdominopelvic surgery: a systematic review of applications and impact","volume":"38","author":"Goglia","year":"2024","journal-title":"In Vivo"},{"key":"10.1016\/j.jss.2025.06.026_bib35","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-024-66821-4","article-title":"Inconsistent advice by ChatGPT influences decision making in various areas","volume":"14","author":"Ikeda","year":"2024","journal-title":"Sci Rep"},{"key":"10.1016\/j.jss.2025.06.026_bib36","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1093\/oncolo\/oyae009","article-title":"Comparison of Large Language Models in answering immuno-oncology questions: a cross-sectional study","volume":"29","author":"Iannantuono","year":"2024","journal-title":"Oncologist"},{"key":"10.1016\/j.jss.2025.06.026_bib37","doi-asserted-by":"crossref","first-page":"3239","DOI":"10.2147\/OPTH.S488232","article-title":"Comparison of Large Language Models in diagnosis and management of challenging clinical cases","volume":"18","author":"Shanmugam","year":"2024","journal-title":"Clin Ophthalmol"},{"key":"10.1016\/j.jss.2025.06.026_bib38","doi-asserted-by":"crossref","first-page":"1543","DOI":"10.1097\/JS9.0000000000000387","article-title":"Artificial intelligence in surgical education and training: opportunities, challenges, and ethical considerations - correspondence","volume":"109","author":"Satapathy","year":"2023","journal-title":"Int J Surg"},{"key":"10.1016\/j.jss.2025.06.026_bib39","doi-asserted-by":"crossref","DOI":"10.3389\/fsurg.2024.1393898","article-title":"Current and future applications of artificial intelligence in surgery: implications for clinical practice and research","volume":"11","author":"Morris","year":"2024","journal-title":"Front Surg"},{"key":"10.1016\/j.jss.2025.06.026_bib40","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1308\/rcsann.2023.0085","article-title":"Performance of large language models at the MRCS Part A: a tool for medical education?","volume":"107","author":"Yiu","year":"2023","journal-title":"Ann R Coll Surg Engl"},{"key":"10.1016\/j.jss.2025.06.026_bib41","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1016\/j.mjafi.2023.06.009","article-title":"ChatGPT for scientific community: boon or bane?","volume":"79","author":"Jain","year":"2023","journal-title":"Med J Armed Forces India"},{"key":"10.1016\/j.jss.2025.06.026_bib42","doi-asserted-by":"crossref","first-page":"1110","DOI":"10.1093\/postmj\/qgad053","article-title":"Artificial intelligence in orthopaedics: can chat generative pre-trained transformer (ChatGPT) pass section 1 of the fellowship of the royal college of surgeons (trauma & orthopaedics) examination?","volume":"99","author":"Cuthbert","year":"2023","journal-title":"Postgrad Med J"},{"key":"10.1016\/j.jss.2025.06.026_bib43","doi-asserted-by":"crossref","first-page":"8236","DOI":"10.1038\/s41467-024-52415-1","article-title":"Evaluating the use of large language models to provide clinical recommendations in the Emergency Department","volume":"15","author":"Williams","year":"2024","journal-title":"Nat Commun"},{"key":"10.1016\/j.jss.2025.06.026_bib44","doi-asserted-by":"crossref","DOI":"10.1093\/jamiaopen\/ooae128","article-title":"Does one size fit all? Developing an evaluation strategy to assess large language models for patient safety event report analysis","volume":"7","author":"Fong","year":"2024","journal-title":"JAMIA Open"},{"key":"10.1016\/j.jss.2025.06.026_bib45","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1007\/s10439-023-03306-x","article-title":"A domain-specific next-generation Large Language model (LLM) or ChatGPT is required for biomedical engineering and research","volume":"52","author":"Pal","year":"2024","journal-title":"Ann Biomed Eng"},{"key":"10.1016\/j.jss.2025.06.026_bib46","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1007\/978-3-030-52237-7_20","article-title":"A conceptual framework for human\u2013AI hybrid adaptivity in education","volume":"12163","author":"Holstein","year":"2020","journal-title":"Artif Intelligence Edu"},{"key":"10.1016\/j.jss.2025.06.026_bib47","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1038\/s41746-023-00873-0","article-title":"The imperative for regulatory oversight of large language models (or generative AI) in healthcare","volume":"6","author":"Mesk\u00f3","year":"2023","journal-title":"NPJ Digit Med"},{"key":"10.1016\/j.jss.2025.06.026_bib48","doi-asserted-by":"crossref","first-page":"e428","DOI":"10.1016\/S2589-7500(24)00061-X","article-title":"Ethical and regulatory challenges of large language models in medicine","volume":"6","author":"Ong","year":"2024","journal-title":"Lancet Digit Health"},{"key":"10.1016\/j.jss.2025.06.026_bib49","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1136\/amiajnl-2011-000089","article-title":"Automation bias: a systematic review of frequency, effect mediators, and mitigators","volume":"19","author":"Goddard","year":"2012","journal-title":"J Am Med Inform Assoc"},{"key":"10.1016\/j.jss.2025.06.026_bib50","first-page":"1","article-title":"Drawbacks of artificial intelligence and their potential solutions in the healthcare sector","author":"Khan","year":"2023","journal-title":"Biomed Mater Devices"},{"key":"10.1016\/j.jss.2025.06.026_bib51","doi-asserted-by":"crossref","first-page":"860","DOI":"10.1093\/cid\/ciad633","article-title":"Black box warning: large Language Models and the future of infectious diseases consultation","volume":"78","author":"Schwartz","year":"2024","journal-title":"Clin Infect Dis"},{"key":"10.1016\/j.jss.2025.06.026_bib52","doi-asserted-by":"crossref","DOI":"10.2196\/47532","article-title":"The accuracy and potential racial and ethnic biases of GPT-4 in the diagnosis and triage of health conditions: evaluation study","volume":"9","author":"Ito","year":"2023","journal-title":"JMIR Med Educ"}],"container-title":["Journal of Surgical Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0022480425003609?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0022480425003609?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:46:18Z","timestamp":1756773978000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0022480425003609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":48,"alternative-id":["S0022480425003609"],"URL":"https:\/\/doi.org\/10.1016\/j.jss.2025.06.026","relation":{},"ISSN":["0022-4804"],"issn-type":[{"value":"0022-4804","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Evaluating the Performance of Large Language Models on Multispecialty FRCS Section 1 Questions","name":"articletitle","label":"Article Title"},{"value":"Journal of Surgical Research","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jss.2025.06.026","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}