{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T06:22:14Z","timestamp":1783750934173,"version":"3.55.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,6]]},"DOI":"10.7759\/cureus.93960","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T20:26:21Z","timestamp":1759782381000},"source":"Crossref","is-referenced-by-count":2,"title":["Poor Performance of Large Language Models Based on the Diabetes and Endocrinology Specialty Certificate Examination of the United Kingdom"],"prefix":"10.7759","author":[{"given":"Ka Siu","family":"Fan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey","family":"Gan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabelle X","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maja","family":"Kaladjiska","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Monique B","family":"Inguanez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gillian L","family":"Garden","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1055\/a-2413-3529","article-title":"The use of large language models such as ChatGPT on delivering patient information relating to surgery","volume":"41","author":"Shamil E","year":"2025","unstructured":"Shamil E, Jaafar M, Fan KS, Ko TK, Schuster-Bruce J, Eynon-Lewis N, Andrews P. The use of large language models such as ChatGPT on delivering patient information relating to surgery. Facial Plast Surg. 2025, 41:554-5. 10.1055\/a-2413-3529","journal-title":"Facial Plast Surg"},{"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":"10.1177\/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 A","year":"2024","unstructured":"Sumbal A, Sumbal R, Amir A. Can ChatGPT-3.5 pass a medical exam? A systematic review of ChatGPT's performance in academic testing. J Med Educ Curric Dev. 2024, 11:23821205241238641. 10.1177\/23821205241238641","journal-title":"J Med Educ Curric Dev"},{"key":"ref4","doi-asserted-by":"publisher","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 J","year":"2024","unstructured":"Chan J, Dong T, Angelini GD. The performance of large language models in intercollegiate Membership of the Royal College of Surgeons examination. Ann R Coll Surg Engl. 2024, 106:700-4. 10.1308\/rcsann.2024.0023","journal-title":"Ann R Coll Surg Engl"},{"key":"ref5","doi-asserted-by":"publisher","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 A","year":"2024","unstructured":"Maitland A, Fowkes R, Maitland S. Can ChatGPT pass the MRCP (UK) written examinations? Analysis of performance and errors using a clinical decision-reasoning framework. BMJ Open. 2024, 14:e080558. 10.1136\/bmjopen-2023-080558","journal-title":"BMJ Open"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/dermato4040013","article-title":"Dermatological knowledge and image analysis performance of large language models based on Specialty Certificate Examination in dermatology","volume":"4","author":"Fan KS","year":"2024","unstructured":"Fan KS, Fan KH. Dermatological knowledge and image analysis performance of large language models based on Specialty Certificate Examination in dermatology. Dermato. 2024, 4:124-35. 10.3390\/dermato4040013","journal-title":"Dermato"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/19322968231203987","article-title":"The scientific knowledge of Bard and ChatGPT in endocrinology, diabetes, and diabetes technology: multiple-choice questions examination-based performance","volume":"19","author":"Meo SA","year":"2025","unstructured":"Meo SA, Al-Khlaiwi T, AbuKhalaf AA, Meo AS, Klonoff DC. The scientific knowledge of Bard and ChatGPT in endocrinology, diabetes, and diabetes technology: multiple-choice questions examination-based performance. J Diabetes Sci Technol. 2025, 19:705-10. 10.1177\/19322968231203987","journal-title":"J Diabetes Sci Technol"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3352\/jeehp.2024.21.6","article-title":"Opportunities, challenges, and future directions of large language models, including ChatGPT in medical education: a systematic scoping review","volume":"21","author":"Xu X","year":"2024","unstructured":"Xu X, Chen Y, Miao J. Opportunities, challenges, and future directions of large language models, including ChatGPT in medical education: a systematic scoping review. J Educ Eval Health Prof. 2024, 21:6. 10.3352\/jeehp.2024.21.6","journal-title":"J Educ Eval Health Prof"},{"key":"ref9","unstructured":"Specialty Certificate Examination in endocrinology and diabetes 2024 selected examination metrics. (2024). Accessed. December 24 2024: https:\/\/www.thefederation.uk\/sites\/default\/files\/uploads\/2024%20SCE%20Endocrinology%20Results%20Report.pdf."},{"key":"ref10","unstructured":"Membership of the Royal Colleges of Physicians of the United Kingdom. Endocrinology and diabetes. (2024). Accessed. December 24 2024: https:\/\/www.thefederation.uk\/examinations\/specialty-certificate-examinations\/specialties\/endocrinology-and-diabetes."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1055\/a-2413-3675","article-title":"Assessing the quality and readability of online patient information: ENT UK patient information e-leaflets versus responses by a generative artificial intellig aence","volume":"41","author":"Shamil E","year":"2025","unstructured":"Shamil E, Ko TK, Fan KS, et al.. Assessing the quality and readability of online patient information: ENT UK patient information e-leaflets versus responses by a generative artificial intellig aence. Facial Plast Surg. 2025, 41:472-81. 10.1055\/a-2413-3675","journal-title":"Facial Plast Surg"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2196\/55535","article-title":"Evaluation of the quality and readability of web-based information regarding foreign bodies of the ear, nose, and throat: qualitative content analysis","volume":"8","author":"Ko TK","year":"2024","unstructured":"Ko TK, Tan DJ, Fan KS. Evaluation of the quality and readability of web-based information regarding foreign bodies of the ear, nose, and throat: qualitative content analysis. JMIR Form Res. 2024, 8:e55535. 10.2196\/55535","journal-title":"JMIR Form Res"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2196\/47762","article-title":"The readability and quality of web-based patient information on nasopharyngeal carcinoma: quantitative content analysis","volume":"7","author":"Tan DJ","year":"2023","unstructured":"Tan DJ, Ko TK, Fan KS. The readability and quality of web-based patient information on nasopharyngeal carcinoma: quantitative content analysis. JMIR Form Res. 2023, 7:e47762. 10.2196\/47762","journal-title":"JMIR Form Res"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000205","article-title":"ChatGPT passing USMLE shines a spotlight on the flaws of medical education","volume":"2","author":"Mbakwe AB","year":"2023","unstructured":"Mbakwe AB, Lourentzou I, Celi LA, Mechanic OJ, Dagan A. ChatGPT passing USMLE shines a spotlight on the flaws of medical education. PLOS Digit Health. 2023, 2:e0000205. 10.1371\/journal.pdig.0000205","journal-title":"PLOS Digit Health"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/asj\/sjad130","article-title":"ChatGPT is equivalent to first-year plastic surgery residents: evaluation of ChatGPT on the plastic surgery in-service examination","volume":"43","author":"Humar P","year":"2023","unstructured":"Humar P, Asaad M, Bengur FB, Nguyen V. ChatGPT is equivalent to first-year plastic surgery residents: evaluation of ChatGPT on the plastic surgery in-service examination. Aesthet Surg J. 2023, 43:NP1085-9. 10.1093\/asj\/sjad130","journal-title":"Aesthet Surg J"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198","article-title":"Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models","volume":"2","author":"Kung TH","year":"2023","unstructured":"Kung TH, Cheatham M, Medenilla A, et al.. Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLOS Digit Health. 2023, 2:e0000198. 10.1371\/journal.pdig.0000198","journal-title":"PLOS Digit Health"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1227\/neu.0000000000002632","article-title":"Performance of ChatGPT and GPT-4 on neurosurgery written board examinations","volume":"93","author":"Ali R","year":"2023","unstructured":"Ali R, Tang OY, Connolly ID, et al.. Performance of ChatGPT and GPT-4 on neurosurgery written board examinations. Neurosurgery. 2023, 93:1353-65. 10.1227\/neu.0000000000002632","journal-title":"Neurosurgery"},{"key":"ref18","unstructured":"Introducing OpenAI o1-preview. (2024). Accessed. December 23 2024: https:\/\/openai.com\/index\/introducing-openai-o1-preview\/ ."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2506.06941","article-title":"The illusion of thinking: understanding the strengths and limitations of reasoning models via the lens of problem complexity","author":"Shojaee P","year":"2025","unstructured":"Shojaee P, Mirzadeh I, Alizadeh K, Horton M, Bengio S, Farajtabar M. The illusion of thinking: understanding the strengths and limitations of reasoning models via the lens of problem complexity. arXiv. 2025, 10.48550\/ARXIV.2506.06941","journal-title":"arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2502.04381","article-title":"Limitations of large language models in clinical problem-solving arising from inflexible reasoning","author":"Kim J","year":"2025","unstructured":"Kim J, Podlasek A, Shidara K, Liu F, Alaa A, Bernardo D. Limitations of large language models in clinical problem-solving arising from inflexible reasoning. arXiv. 2025, 10.48550\/ARXIV.2502.04381","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-024-03169-9","article-title":"'In awe': scientists impressed by latest ChatGPT model o1","volume":"634","author":"Jones N","year":"2024","unstructured":"Jones N. 'In awe': scientists impressed by latest ChatGPT model o1. Nature. 2024, 634:275-6. 10.1038\/d41586-024-03169-9","journal-title":"Nature"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-025-00229-6","article-title":"China's cheap, open AI model DeepSeek thrills scientists","volume":"638","author":"Gibney E","year":"2025","unstructured":"Gibney E. China's cheap, open AI model DeepSeek thrills scientists. Nature. 2025, 638:13-4. 10.1038\/d41586-025-00229-6","journal-title":"Nature"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-024-05630-9","article-title":"Comparative accuracy of ChatGPT-4, Microsoft Copilot and Google Gemini in the Italian entrance test for healthcare sciences degrees: a cross-sectional study","volume":"24","author":"Rossettini G","year":"2024","unstructured":"Rossettini G, Rodeghiero L, Corradi F, et al.. Comparative accuracy of ChatGPT-4, Microsoft Copilot and Google Gemini in the Italian entrance test for healthcare sciences degrees: a cross-sectional study. BMC Med Educ. 2024, 24:694. 10.1186\/s12909-024-05630-9","journal-title":"BMC Med Educ"},{"key":"ref24","unstructured":"Perplexity frequently asked questions. (2024). Accessed. September 26 2024: https:\/\/www.perplexity.ai\/hub\/faq."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-023-04354-6","article-title":"Evaluate the accuracy of ChatGPT's responses to diabetes questions and misconceptions","volume":"21","author":"Huang C","year":"2023","unstructured":"Huang C, Chen L, Huang H, et al.. Evaluate the accuracy of ChatGPT's responses to diabetes questions and misconceptions. J Transl Med. 2023, 21:502. 10.1186\/s12967-023-04354-6","journal-title":"J Transl Med"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2196\/50965","article-title":"Comparison of the performance of GPT-3.5 and GPT-4 with that of medical students on the written German medical licensing examination: observational study","volume":"10","author":"Meyer A","year":"2024","unstructured":"Meyer A, Riese J, Streichert T. Comparison of the performance of GPT-3.5 and GPT-4 with that of medical students on the written German medical licensing examination: observational study. JMIR Med Educ. 2024, 10:e50965. 10.2196\/50965","journal-title":"JMIR Med Educ"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2196\/57054","article-title":"Performance of GPT-4V in answering the Japanese otolaryngology board certification examination questions: evaluation study","volume":"10","author":"Noda M","year":"2024","unstructured":"Noda M, Ueno T, Koshu R, et al.. Performance of GPT-4V in answering the Japanese otolaryngology board certification examination questions: evaluation study. JMIR Med Educ. 2024, 10:e57054. 10.2196\/57054","journal-title":"JMIR Med Educ"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1093\/ckj\/sfae193","article-title":"The potential of ChatGPT in medicine: an example analysis of nephrology specialty exams in Poland","volume":"17","author":"Nicikowski J","year":"2024","unstructured":"Nicikowski J, Szczepa\u0144ski M, Miedziaszczyk M, Kudli\u0144ski B. The potential of ChatGPT in medicine: an example analysis of nephrology specialty exams in Poland. Clin Kidney J. 2024, 17:sfae193. 10.1093\/ckj\/sfae193","journal-title":"Clin Kidney J"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)30259-8","article-title":"The language of biomedical sciences","volume":"387","author":"Rosselli D","year":"2016","unstructured":"Rosselli D. The language of biomedical sciences. Lancet. 2016, 387:1720-1. 10.1016\/S0140-6736(16)30259-8","journal-title":"Lancet"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.818","article-title":"Same task, more tokens: the impact of input length on the reasoning performance of large language models","author":"Levy M","year":"2024","unstructured":"Levy M, Jacoby A, Goldberg Y. Same task, more tokens: the impact of input length on the reasoning performance of large language models. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. Ku L, Martins A, Srikumar V (ed): Association for Computational Linguistics, Bangkok; 2024. 1:15339-53. 10.18653\/v1\/2024.acl-long.818"}],"container-title":["Cureus"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cureus.com\/articles\/381404-poor-performance-of-large-language-models-based-on-the-diabetes-and-endocrinology-specialty-certificate-examination-of-the-united-kingdom","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T20:26:23Z","timestamp":1759782383000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cureus.com\/articles\/381404-poor-performance-of-large-language-models-based-on-the-diabetes-and-endocrinology-specialty-certificate-examination-of-the-united-kingdom"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.7759\/cureus.93960","relation":{},"ISSN":["2168-8184"],"issn-type":[{"value":"2168-8184","type":"print"}],"subject":[],"published":{"date-parts":[[2025,10,6]]}}}