{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T04:01:42Z","timestamp":1775448102004,"version":"3.50.1"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,5]]},"DOI":"10.7759\/cureus.106486","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T02:38:11Z","timestamp":1775443091000},"source":"Crossref","is-referenced-by-count":0,"title":["Comparative Performance of Seven Mainstream Large Language Models on the 2022 American College of Radiology Diagnostic Imaging In-Training Examination"],"prefix":"10.7759","author":[{"given":"Kian A","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Samvelian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Allan L","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ana","family":"Sanchez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haris K","family":"Choudhary","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arindam","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neelesh S","family":"Prakash","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-023-00370-1","article-title":"The future landscape of large language models in medicine","volume":"3","author":"Clusmann J","year":"2023","unstructured":"Clusmann J, Kolbinger FR, Muti HS, et al.. The future landscape of large language models in medicine. Commun Med (Lond). 2023, 3:141. 10.1038\/s43856-023-00370-1","journal-title":"Commun Med (Lond)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2196\/45312","article-title":"How does ChatGPT perform on the United States Medical Licensing Examination (USMLE)? The implications of large language models for medical education and knowledge assessment","volume":"9","author":"Gilson A","year":"2023","unstructured":"Gilson A, Safranek CW, Huang T, Socrates V, Chi L, Taylor RA, Chartash D. How does ChatGPT perform on the United States Medical Licensing Examination (USMLE)? The implications of large language models for medical education and knowledge assessment. JMIR Med Educ. 2023, 9:e45312. 10.2196\/45312","journal-title":"JMIR Med Educ"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-31010-4","article-title":"Benchmarking large language models on the United States medical licensing examination for clinical reasoning and medical licensing scenarios","volume":"16","author":"Siam MK","year":"2025","unstructured":"Siam MK, Varela A, Faruk MJ, Cheng JQ, Gu H, Maruf AA, Aung Z. Benchmarking large language models on the United States medical licensing examination for clinical reasoning and medical licensing scenarios. Sci Rep. 2025, 16:1387. 10.1038\/s41598-025-31010-4","journal-title":"Sci Rep"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/10872981.2025.2534065","article-title":"Large language models in medical education: a comparative cross-platform evaluation in answering histological questions","volume":"30","author":"Mavrych V","year":"2025","unstructured":"Mavrych V, Yousef EM, Yaqinuddin A, Bolgova O. Large language models in medical education: a comparative cross-platform evaluation in answering histological questions. Med Educ Online. 2025, 30:2534065. 10.1080\/10872981.2025.2534065","journal-title":"Med Educ Online"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajoint.2024.100070","article-title":"The performance of artificial intelligence-based large language models on ophthalmology-related questions in Swedish proficiency test for medicine: ChatGPT-4 omni vs Gemini 1.5 Pro","volume":"1","author":"Sabaner MC","year":"2024","unstructured":"Sabaner MC, Hashas ASK, Mutibayraktaroglu KM, Yozgat Z, Klefter ON, Subhi Y. The performance of artificial intelligence-based large language models on ophthalmology-related questions in Swedish proficiency test for medicine: ChatGPT-4 omni vs Gemini 1.5 Pro. AJO Int. 2024, 1:100070. 10.1016\/j.ajoint.2024.100070","journal-title":"AJO Int"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.20944\/preprints202502.0066.v1","article-title":"Optimizing AI language models: a study of ChatGPT-4 vs. ChatGPT-4o [PREPRINT]","author":"Siddiky MNA","year":"2025","unstructured":"Siddiky MNA, Rahman ME, Hossen MFB, Rahman MR, Jaman MS. Optimizing AI language models: a study of ChatGPT-4 vs. ChatGPT-4o [PREPRINT]. Preprints. 2025, 10.20944\/preprints202502.0066.v1","journal-title":"Preprints"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2024.105673","article-title":"Evaluating the effectiveness of advanced large language models in medical knowledge: a comparative study using Japanese national medical examination","volume":"193","author":"Liu M","year":"2025","unstructured":"Liu M, Okuhara T, Dai Z, et al.. Evaluating the effectiveness of advanced large language models in medical knowledge: a comparative study using Japanese national medical examination. Int J Med Inform. 2025, 193:105673. 10.1016\/j.ijmedinf.2024.105673","journal-title":"Int J Med Inform"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00296-025-06053-5","article-title":"Comparative evaluation of large language models on multiple-choice and image-based rheumatology questions","volume":"46","author":"Nakaphan P","year":"2025","unstructured":"Nakaphan P, Damara I, Lerttiendamrong B, Shotelersuk V, Chaisrimaneepan N. Comparative evaluation of large language models on multiple-choice and image-based rheumatology questions. Rheumatol Int. 2025, 46:9. 10.1007\/s00296-025-06053-5","journal-title":"Rheumatol Int"},{"key":"ref9","doi-asserted-by":"publisher","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 DL","year":"2024","unstructured":"Payne DL, Purohit K, Borrero WM, et al.. Performance of GPT-4 on the American College of Radiology In-training Examination: evaluating accuracy, model drift, and fine-tuning. Acad Radiol. 2024, 31:3046-54. 10.1016\/j.acra.2024.04.006","journal-title":"Acad Radiol"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2025.10.026","article-title":"Artificial intelligence in radiology: performance of ChatGPT-4v and GPT-4o on diagnostic radiology in-training (DXIT) examination questions","author":"Martini RS","year":"2025","unstructured":"Martini RS, Sang A, Saunders P, Bala W, Li H, Moon JT, Balthazar P. Artificial intelligence in radiology: performance of ChatGPT-4v and GPT-4o on diagnostic radiology in-training (DXIT) examination questions. J Am Coll Radiol. 2025, 10.1016\/j.jacr.2025.10.026","journal-title":"J Am Coll Radiol"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.80874","article-title":"Comparative analysis of ChatGPT-4o and Gemini advanced performance on diagnostic radiology in-training exams","volume":"17","author":"Huang KA","year":"2025","unstructured":"Huang KA, Choudhary HK, Hardin WM, Prakash N. Comparative analysis of ChatGPT-4o and Gemini advanced performance on diagnostic radiology in-training exams. Cureus. 2025, 17:e80874. 10.7759\/cureus.80874","journal-title":"Cureus"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s13534-025-00484-6","article-title":"Vision-language foundation models for medical imaging: a review of current practices and innovations","volume":"15","author":"Ryu JS","year":"2025","unstructured":"Ryu JS, Kang H, Chu Y, Yang S. Vision-language foundation models for medical imaging: a review of current practices and innovations. Biomed Eng Lett. 2025, 15:809-30. 10.1007\/s13534-025-00484-6","journal-title":"Biomed Eng Lett"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1186\/s41747-024-00422-8","article-title":"AI applications in musculoskeletal imaging: a narrative review","volume":"8","author":"Gitto S","year":"2024","unstructured":"Gitto S, Serpi F, Albano D, Risoleo G, Fusco S, Messina C, Sconfienza LM. AI applications in musculoskeletal imaging: a narrative review. Eur Radiol Exp. 2024, 8:22. 10.1186\/s41747-024-00422-8","journal-title":"Eur Radiol Exp"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-64827-6","article-title":"OpenMedLM: prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models","volume":"14","author":"Maharjan J","year":"2024","unstructured":"Maharjan J, Garikipati A, Singh NP, et al.. OpenMedLM: prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models. Sci Rep. 2024, 14:14156. 10.1038\/s41598-024-64827-6","journal-title":"Sci Rep"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2196\/60501","article-title":"Prompt engineering paradigms for medical applications: scoping review","volume":"26","author":"Zaghir J","year":"2024","unstructured":"Zaghir J, Naguib M, Bjelogrlic M, N\u00e9v\u00e9ol A, Tannier X, Lovis C. Prompt engineering paradigms for medical applications: scoping review. J Med Internet Res. 2024, 26:e60501. 10.2196\/60501","journal-title":"J Med Internet Res"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3348\/kjr.2025.0599","article-title":"Multimodal large language models in medical imaging: current state and future directions","volume":"26","author":"Nam Y","year":"2025","unstructured":"Nam Y, Kim DY, Kyung S, et al.. Multimodal large language models in medical imaging: current state and future directions. Korean J Radiol. 2025, 26:900-23. 10.3348\/kjr.2025.0599","journal-title":"Korean J Radiol"}],"container-title":["Cureus"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cureus.com\/articles\/468819-comparative-performance-of-seven-mainstream-large-language-models-on-the-2022-american-college-of-radiology-diagnostic-imaging-in-training-examination","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T02:38:11Z","timestamp":1775443091000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cureus.com\/articles\/468819-comparative-performance-of-seven-mainstream-large-language-models-on-the-2022-american-college-of-radiology-diagnostic-imaging-in-training-examination"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,5]]},"references-count":16,"URL":"https:\/\/doi.org\/10.7759\/cureus.106486","relation":{},"ISSN":["2168-8184"],"issn-type":[{"value":"2168-8184","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4,5]]}}}