{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T06:02:46Z","timestamp":1793858566052,"version":"4.6.1"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:00:00Z","timestamp":1793318400000},"content-version":"vor","delay-in-days":115,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02978-8","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T12:08:27Z","timestamp":1783426107000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Human-in-the-loop validation of a sequential multi-LLM medical education pipeline"],"prefix":"10.1038","volume":"9","author":[{"given":"Yoojin","family":"Nam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taein","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung","family":"Il Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chawoong","family":"Jeon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji Won","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juhyun","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong Yeong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pyeong Hwa","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"So Yeon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sungkwan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangwon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwang Hwi","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taehee","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hee Sang","family":"Oh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joon Hyung","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seunghyeon","family":"Shin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongsik","family":"Sim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeong Min","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seunghyun","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pa","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Namkug","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"2978_CR1","doi-asserted-by":"publisher","first-page":"S62","DOI":"10.1097\/ACM.0000000000004291","volume":"96","author":"J Lee","year":"2021","unstructured":"Lee, J., Wu, A. S., Li, D. & Kulasegaram, K. M. Artificial intelligence in undergraduate medical education: a scoping review. Acad. Med. 96, S62\u2013S70 (2021).","journal-title":"Acad. Med."},{"key":"2978_CR2","doi-asserted-by":"publisher","first-page":"e45312","DOI":"10.2196\/45312","volume":"9","author":"A Gilson","year":"2023","unstructured":"Gilson, A. et al. How does ChatGPT perform on the United States Medical Licensing Examination? The implications of large language models for medical education and knowledge assessment. JMIR Med. Educ. 9, e45312 (2023).","journal-title":"JMIR Med. Educ."},{"key":"2978_CR3","doi-asserted-by":"publisher","first-page":"1477898","DOI":"10.3389\/fmed.2024.1477898","volume":"11","author":"S Aydin","year":"2024","unstructured":"Aydin, S., Karabacak, M., Vlachos, V. & Margetis, K. Large language models in patient education: a scoping review of applications in medicine. Front. Med. 11, 1477898 (2024).","journal-title":"Front. Med."},{"key":"2978_CR4","doi-asserted-by":"publisher","first-page":"3872","DOI":"10.1016\/j.acra.2024.06.046","volume":"31","author":"NP Mistry","year":"2024","unstructured":"Mistry, N. P. et al. Large language models as tools to generate radiology board-style multiple-choice questions. Acad. Radio. 31, 3872\u20133878 (2024).","journal-title":"Acad. Radio."},{"key":"2978_CR5","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-025-08085-8","volume":"25","author":"Q Zhang","year":"2025","unstructured":"Zhang, Q. et al. Generative AI in medical education: Feasibility and educational value of LLM-generated clinical cases with MCQs. BMC Med. Educ. 25, 1502 (2025).","journal-title":"BMC Med. Educ."},{"key":"2978_CR6","doi-asserted-by":"publisher","first-page":"e55933","DOI":"10.2196\/55933","volume":"12","author":"L Zhui","year":"2024","unstructured":"Zhui, L. et al. Impact of large language models on medical education and teaching adaptations. JMIR Med. Inf. 12, e55933\u2013e55933 (2024).","journal-title":"JMIR Med. Inf."},{"key":"2978_CR7","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1016\/j.jacr.2025.07.003","volume":"22","author":"SK Lyo","year":"2025","unstructured":"Lyo, S. K. & Cook, T. S. Integrating large language models into radiology education: an interpretation-centric framework for enhanced learning while supporting workflow. J. Am. Coll. Radio. 22, 1271\u20131280 (2025).","journal-title":"J. Am. Coll. Radio."},{"key":"2978_CR8","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1016\/j.acra.2024.08.009","volume":"32","author":"Y Al-Naser","year":"2025","unstructured":"Al-Naser, Y. et al. Evaluating artificial intelligence competency in education: performance of ChatGPT-4 in the ARRT radiography certification exam. Acad. Radio. 32, 597\u2013603 (2025).","journal-title":"Acad. Radio."},{"key":"2978_CR9","doi-asserted-by":"publisher","first-page":"524","DOI":"10.3348\/kjr.2024.1096","volume":"26","author":"A Choi","year":"2025","unstructured":"Choi, A. et al. Performance of GPT-4 turbo and GPT-4o in korean society of radiology in-training examinations. Korean J. Radio. 26, 524 (2025).","journal-title":"Korean J. Radio."},{"key":"2978_CR10","doi-asserted-by":"publisher","first-page":"101896","DOI":"10.1016\/j.jmir.2025.101896","volume":"56","author":"E Emekli","year":"2025","unstructured":"Emekli, E. & Karahan, B. N. AI in radiography education: evaluating multiple-choice questions difficulty and discrimination. J. Med. Imaging Radiat. Sci. 56, 101896 (2025).","journal-title":"J. Med. Imaging Radiat. Sci."},{"key":"2978_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104620","volume":"151","author":"Q Wei","year":"2024","unstructured":"Wei, Q. et al. Evaluation of ChatGPT-generated medical responses: a systematic review and meta-analysis. J. Biomed. Inf. 151, 104620 (2024).","journal-title":"J. Biomed. Inf."},{"key":"2978_CR12","doi-asserted-by":"publisher","first-page":"1264","DOI":"10.1016\/j.jacr.2025.07.004","volume":"22","author":"J Volin","year":"2025","unstructured":"Volin, J., Van Assen, M., Bala, W., Safdar, N. & Balthazar, P. Artificial intelligence and its effect on radiology residency education: current challenges, opportunities, and future directions. J. Am. Coll. Radio. 22, 1264\u20131270 (2025).","journal-title":"J. Am. Coll. Radio."},{"key":"2978_CR13","doi-asserted-by":"crossref","unstructured":"Madaan, A. et al. Self-refine: iterative refinement with self-feedback. In Advances in Neural Information Processing Systems 36 (NeurIPS 2023) (2023).","DOI":"10.52202\/075280-2019"},{"key":"2978_CR14","doi-asserted-by":"crossref","unstructured":"Manakul, P., Liusie, A. & Gales, M. J. F. SelfCheckGPT: zero-resource black-box hallucination detection for generative large language models. In Proc. 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP) 9004\u20139017 (Association for Computational Linguistics, 2023).","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"2978_CR15","unstructured":"Wu, Q. et al. AutoGen: enabling next-gen LLM applications via multi-agent conversation. In Proc. First Conference on Language Modeling (COLM) (2024)."},{"key":"2978_CR16","unstructured":"Hong, S. et al. MetaGPT: meta programming for a multi-agent collaborative framework. In The Twelfth International Conference on Learning Representations (ICLR) (2024)."},{"key":"2978_CR17","unstructured":"Du, Y., Li, S., Torralba, A., Tenenbaum, J. B. & Mordatch, I. Improving factuality and reasoning in language modelsthrough multiagent debate. In Proc. 41st International Conference on Machine Learning (ICML), Proceedings of Machine Learning Research vol. 235, 11733\u201311763 (PMLR, 2024)."},{"key":"2978_CR18","unstructured":"Wooldridge, M. An Introduction to MultiAgent Systems (Wiley, 2009)."},{"key":"2978_CR19","doi-asserted-by":"publisher","first-page":"888","DOI":"10.3348\/kjr.2025.0370","volume":"26","author":"S Faghani","year":"2025","unstructured":"Faghani, S., Moassefi, M., Rouzrokh, P., Khosravi, B. & Erickson, B. J. Uncover this tech term: agentic artificial intelligence in radiology. Korean J. Radio. 26, 888\u2013892 (2025).","journal-title":"Korean J. Radio."},{"key":"2978_CR20","doi-asserted-by":"publisher","first-page":"1582","DOI":"10.1093\/bjr\/tqaf173","volume":"98","author":"N Dietrich","year":"2025","unstructured":"Dietrich, N. Agentic AI in radiology: emerging potential and unresolved challenges. Br. J. Radio. 98, 1582\u20131584 (2025).","journal-title":"Br. J. Radio."},{"key":"2978_CR21","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.diii.2025.10.002","volume":"107","author":"E Tzanis","year":"2026","unstructured":"Tzanis, E. et al. Agentic systems in radiology: principles, opportunities, privacy risks, regulation, and sustainability concerns. Diagn. Inter. Imaging 107, 7\u201316 (2026).","journal-title":"Diagn. Inter. Imaging"},{"key":"2978_CR22","doi-asserted-by":"crossref","unstructured":"Zheng, L. et al. Judging LLM-as-a-judge with MT-bench and chatbot arena. In Advances in Neural Information Processing Systems 36 (NeurIPS 2023), Datasets and Benchmarks Track (2023).","DOI":"10.52202\/075280-2020"},{"key":"2978_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y. et al. G-eval: NLG evaluation using GPT-4 with better human alignment. In Proc. 2023 Conferenceon Empirical Methods in Natural Language Processing (EMNLP) 2511\u20132522 (Association for Computational Linguistics, 2023).","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"2978_CR24","doi-asserted-by":"publisher","unstructured":"Gu, J. et al. A survey on LLM-as-a-judge. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2411.15594 (2025).","DOI":"10.48550\/arXiv.2411.15594"},{"key":"2978_CR25","doi-asserted-by":"publisher","first-page":"1595","DOI":"10.1007\/s00256-024-04655-x","volume":"53","author":"S Koga","year":"2024","unstructured":"Koga, S. & Du, W. ChatGPT\u2019s limited accuracy in generating anatomical images for medical education. Skelet. Radio. 53, 1595\u20131596 (2024).","journal-title":"Skelet. Radio."},{"key":"2978_CR26","doi-asserted-by":"publisher","first-page":"900","DOI":"10.3348\/kjr.2025.0599","volume":"26","author":"Y Nam","year":"2025","unstructured":"Nam, Y. et al. Multimodal large language models in medical imaging: current state and future directions. Korean J. Radio. 26, 900 (2025).","journal-title":"Korean J. Radio."},{"key":"2978_CR27","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240955","volume":"313","author":"QD Strotzer","year":"2024","unstructured":"Strotzer, Q. D. et al. Toward foundation models in radiology? Quantitative assessment of GPT-4V\u2019s multimodal and multianatomic region capabilities. Radiology 313, e240955 (2024).","journal-title":"Radiology"},{"key":"2978_CR28","doi-asserted-by":"publisher","first-page":"214","DOI":"10.3348\/kjr.2025.1045","volume":"27","author":"PS Suh","year":"2026","unstructured":"Suh, P. S. et al. Evaluating the accuracy and diagnostic reasoning of multimodal large language models in interpreting neuroradiology cases from RadioGraphics. Korean J. Radio. 27, 214\u2013226 (2026).","journal-title":"Korean J. Radio."},{"key":"2978_CR29","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240273","volume":"312","author":"PS Suh","year":"2024","unstructured":"Suh, P. S. et al. Comparing diagnostic accuracy of radiologists versus GPT-4V and Gemini Pro Vision using image inputs from Diagnosis Please cases. Radiology 312, e240273 (2024).","journal-title":"Radiology"},{"key":"2978_CR30","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1177\/0018720810376055","volume":"52","author":"R Parasuraman","year":"2010","unstructured":"Parasuraman, R. & Manzey, D. H. Complacency and bias in human use of automation: an attentional integration. Hum. Factors 52, 381\u2013410 (2010).","journal-title":"Hum. Factors"},{"key":"2978_CR31","doi-asserted-by":"publisher","first-page":"671","DOI":"10.3390\/app15020671","volume":"15","author":"H Seo","year":"2025","unstructured":"Seo, H. et al. Large language models as evaluators in education: verification of feedback consistency and accuracy. Appl. Sci. 15, 671 (2025).","journal-title":"Appl. Sci."},{"key":"2978_CR32","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.241668","volume":"313","author":"PS Suh","year":"2024","unstructured":"Suh, P. S. et al. Comparing large language model and human reader accuracy with New England Journal of Medicine image challenge case image inputs. Radiology 313, e241668 (2024).","journal-title":"Radiology"},{"key":"2978_CR33","doi-asserted-by":"publisher","first-page":"297","DOI":"10.3348\/kjr.2025.1805","volume":"27","author":"PS Suh","year":"2026","unstructured":"Suh, P. S. & Suh, C. H. Do general-purpose multimodal large language models really see radiologic images or rely on text? Korean J. Radio. 27, 297\u2013300 (2026).","journal-title":"Korean J. Radio."},{"key":"2978_CR34","doi-asserted-by":"publisher","first-page":"e0290691","DOI":"10.1371\/journal.pone.0290691","volume":"18","author":"BHH Cheung","year":"2023","unstructured":"Cheung, B. H. H. et al. ChatGPT versus human in generating medical graduate exam multiple choice questions\u2014a multinational prospective study. PLoS ONE 18, e0290691 (2023).","journal-title":"PLoS ONE"},{"key":"2978_CR35","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.251458","volume":"316","author":"T Lee","year":"2025","unstructured":"Lee, T. et al. Using a vision-language model to generate visual abstracts for radiology journals. Radiology 316, e251458 (2025).","journal-title":"Radiology"},{"key":"2978_CR36","doi-asserted-by":"publisher","first-page":"2411","DOI":"10.1016\/j.acra.2025.01.004","volume":"32","author":"YC G\u00fcne\u015f","year":"2025","unstructured":"G\u00fcne\u015f, Y. C. et al. Textual proficiency and visual deficiency: a comparative study of large language models and radiologists in MRI artifact detection and correction. Acad. Radio. 32, 2411\u20132421 (2025).","journal-title":"Acad. Radio."},{"key":"2978_CR37","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1177\/1529100612451018","volume":"13","author":"S Lewandowsky","year":"2012","unstructured":"Lewandowsky, S., Ecker, U. K. H., Seifert, C. M., Schwarz, N. & Cook, J. Misinformation and its correction: continued influence and successful debiasing. Psychol. Sci. Public Interest 13, 106\u2013131 (2012).","journal-title":"Psychol. Sci. Public Interest"},{"key":"2978_CR38","doi-asserted-by":"crossref","unstructured":"Dhuliawala, S. et al. Chain-of-verification reduces hallucination in large language models. In Findings of the Association for Computational Linguistics: ACL 2024 3563\u20133578 (Association for Computational Linguistics, 2024).","DOI":"10.18653\/v1\/2024.findings-acl.212"},{"key":"2978_CR39","doi-asserted-by":"crossref","unstructured":"Shinn, N. et al. Reflexion: language agents with verbal reinforcement learning. In Advances in Neural InformationProcessing Systems 36 (NeurIPS 2023) (2023).","DOI":"10.52202\/075280-0377"},{"key":"2978_CR40","doi-asserted-by":"publisher","first-page":"287","DOI":"10.3348\/kjr.2025.0071","volume":"26","author":"SH Park","year":"2025","unstructured":"Park, S. H. & Langlotz, C. P. Crucial role of understanding in human\u2013artificial intelligence interaction for successful clinical adoption. Korean J. Radio. 26, 287\u2013290 (2025).","journal-title":"Korean J. Radio."},{"key":"2978_CR41","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41746-021-00385-9","volume":"4","author":"S Gaube","year":"2021","unstructured":"Gaube, S. et al. Do as AI say: susceptibility in deployment of clinical decision-aids. NPJ Digit. Med. 4, 31 (2021).","journal-title":"NPJ Digit. Med."},{"key":"2978_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2025.110573","volume":"125","author":"E \u00c7amur","year":"2025","unstructured":"\u00c7amur, E. et al. Evaluating large language models for imaging modality selection: potential to reduce unnecessary contrast agent use and radiation exposure. Clin. Imaging 125, 110573 (2025).","journal-title":"Clin. Imaging"},{"key":"2978_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.sapharm.2023.10.003","volume":"20","author":"IS Um","year":"2024","unstructured":"Um, I. S., Clough, A. & Tan, E. C. K. Dispensing error rates in pharmacy: a systematic review and meta-analysis. Res. Soc. Adm. Pharm. 20, 1\u20139 (2024).","journal-title":"Res. Soc. Adm. Pharm."},{"key":"2978_CR44","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1148\/radiol.2016161174","volume":"283","author":"CD Lehman","year":"2017","unstructured":"Lehman, C. D. et al. National performance benchmarks for modern screening digital mammography: update from the Breast Cancer Surveillance Consortium. Radiology 283, 49\u201358 (2017).","journal-title":"Radiology"},{"key":"2978_CR45","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/0895-4356(90)90158-L","volume":"43","author":"AR Feinstein","year":"1990","unstructured":"Feinstein, A. R. & Cicchetti, D. V. High agreement but low kappa: I. The problems of two paradoxes. J. Clin. Epidemiol. 43, 543\u2013549 (1990).","journal-title":"J. Clin. Epidemiol."},{"key":"2978_CR46","doi-asserted-by":"crossref","unstructured":"Nam, Y. et al. Feasibility and psychometric evaluation of large language model-generated radiology learning materials for board examination preparation: a prospective pilot study. BMC Med. Educ. 26, 9704 (2026).","DOI":"10.1186\/s12909-026-09704-8"},{"key":"2978_CR47","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1038\/s41746-025-01550-0","volume":"8","author":"X Chen","year":"2025","unstructured":"Chen, X. et al. Enhancing diagnostic capability with multi-agents conversational large language models. NPJ Digit. Med. 8, 159 (2025).","journal-title":"NPJ Digit. Med."},{"key":"2978_CR48","doi-asserted-by":"publisher","first-page":"100044","DOI":"10.1016\/j.ejrai.2025.100044","volume":"4","author":"E Tzanis","year":"2025","unstructured":"Tzanis, E. & Klontzas, M. E. mAIstro: an open-source multi-agent system for automated end-to-end development of radiomics and deep learning models for medical imaging. Eur. Radio. Artif. Intell. 4, 100044 (2025).","journal-title":"Eur. Radio. Artif. Intell."},{"key":"2978_CR49","doi-asserted-by":"crossref","unstructured":"Li, G. et al. CAMEL: communicative agents for mind exploration of large language model society. In Advances in Neural Information Processing Systems 36 (NeurIPS 2023) 51991\u201352008 (2023).","DOI":"10.52202\/075280-2264"},{"key":"2978_CR50","doi-asserted-by":"publisher","first-page":"e252282","DOI":"10.1148\/radiol.252282","volume":"316","author":"CH Suh","year":"2025","unstructured":"Suh, C. H. & Suh, P. S. Evolving multimodal large language models in radiology: a year of diagnostic progress. Radiology 316, e252282 (2025).","journal-title":"Radiology"},{"key":"2978_CR51","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1007\/s40670-023-01826-8","volume":"33","author":"MM Gilbert","year":"2023","unstructured":"Gilbert, M. M. et al. A cohort study assessing the impact of Anki as a spaced repetition tool on academic performance in medical school. Med. Sci. Educ. 33, 955\u2013962 (2023).","journal-title":"Med. Sci. Educ."},{"key":"2978_CR52","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-024-05479-y","volume":"24","author":"SF Durrani","year":"2024","unstructured":"Durrani, S. F. et al. Effectiveness of spaced repetition for clinical problem solving amongst undergraduate medical students studying paediatrics in Pakistan. BMC Med. Educ. 24, 676 (2024).","journal-title":"BMC Med. Educ."},{"key":"2978_CR53","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.3348\/kjr.2025.1522","volume":"26","author":"SH Park","year":"2025","unstructured":"Park, S. H. et al. Minimum reporting items for clear evaluation of accuracy reports of large language models in healthcare (MI-CLEAR-LLM): 2025 updates. Korean J. Radio. 26, 1123 (2025).","journal-title":"Korean J. Radio."},{"key":"2978_CR54","doi-asserted-by":"publisher","unstructured":"Mese, I. et al. Reporting checklist for foundation and large language models in medical research (REFINE): an international consensus guideline. Diagn. Interv. Radiol. https:\/\/doi.org\/10.4274\/dir.2026.263812 (2026).","DOI":"10.4274\/dir.2026.263812"},{"key":"2978_CR55","doi-asserted-by":"publisher","first-page":"5287","DOI":"10.1007\/s00330-025-11492-6","volume":"35","author":"T Lee","year":"2025","unstructured":"Lee, T., Lee, J. H., Yoon, S. H., Park, S. H. & Kim, H. Availability and transparency of artificial intelligence models in radiology: a meta-research study. Eur. Radio. 35, 5287\u20135298 (2025).","journal-title":"Eur. Radio."},{"key":"2978_CR56","doi-asserted-by":"publisher","DOI":"10.1007\/s11934-025-01277-1","volume":"26","author":"RAM Thompson","year":"2025","unstructured":"Thompson, R. A. M. et al. Artificial intelligence use in medical education: best practices and future directions. Curr. Urol. Rep. 26, 45 (2025).","journal-title":"Curr. Urol. Rep."},{"key":"2978_CR57","doi-asserted-by":"publisher","first-page":"519","DOI":"10.3348\/kjr.2025.0257","volume":"26","author":"SH Park","year":"2025","unstructured":"Park, S. H., Dean, G., Ortiz, E. M. & Choi, J.-I. Overview of South Korean guidelines for approval of large language or multimodal models as medical devices: key features and areas for improvement. Korean J. Radio. 26, 519\u2013523 (2025).","journal-title":"Korean J. Radio."},{"key":"2978_CR58","doi-asserted-by":"crossref","unstructured":"Rosenthal, R. Meta-Analytic Procedures for Social Research (Sage Publications, Newbury Park, CA, 1991).","DOI":"10.4135\/9781412984997"},{"key":"2978_CR59","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","volume":"31","author":"J Gallifant","year":"2025","unstructured":"Gallifant, J. et al. The TRIPOD-LLM reporting guideline for studies using large language models. Nat. Med. 31, 60\u201369 (2025).","journal-title":"Nat. Med."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02978-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02978-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02978-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T23:37:46Z","timestamp":1793317066000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02978-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,7]]},"references-count":59,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2978"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02978-8","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,7]]},"assertion":[{"value":"20 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"T.L. received a research grant from Dasol Life Science (unrelated to the present work) and lecture honoraria from Dongkook Lifescience and Canon Medical Systems Korea; T.L. serves as Assistant Editor of the American Journal of Roentgenology and as a board member of the Korean Society of Thoracic Radiology and the Korean Society of Artificial Intelligence in Medicine. The other authors declare no competing financial or non-financial interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"823"}}