{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T23:39:29Z","timestamp":1792539569284,"version":"4.5.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T00:00:00Z","timestamp":1792540800000},"content-version":"vor","delay-in-days":92,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82160155"],"award-info":[{"award-number":["82160155"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Adult type 1 diabetes mellitus (T1DM) involves complex diagnosis, treatment, and long-term self-management, creating a need for accurate and accessible health education. Large language models (LLMs) are increasingly used for medical information seeking, yet their accuracy and consistency in adult T1DM-related queries remain insufficiently evaluated. A guideline-based comparative evaluation assessed DeepSeek-V3.2 and ChatGPT-5.0 using 22 English-language prompts derived from the 2021 ADA\/EASD consensus report, covering basic knowledge, diagnosis and differential diagnosis, treatment, and complications. The prompts were submitted to both models twice, two weeks apart. Responses were independently evaluated by two blinded endocrinology specialists using a predefined four-point scoring rubric, with disagreements adjudicated by a third senior endocrinologist. Short-term consistency was assessed by expert judgment and TF-IDF cosine similarity. Inter-rater agreement was good (Cohen\u2019s \u03ba\u2009=\u20090.71). Expert-judged consistency was 95.45% (21\/22) for both models; TF-IDF cosine similarity was 0.52\u2009\u00b1\u20090.09 for DeepSeek and 0.54\u2009\u00b1\u20090.09 for ChatGPT. Overall accuracy scores were 3.59\u2009\u00b1\u20090.59 and 3.77\u2009\u00b1\u20090.43, respectively, with no statistically significant difference (p\u2009=\u20090.102). Comprehensive ratings accounted for 63.64% and 77.27%, respectively, and mixed correct and incorrect or outdated information accounted for 4.55% and 0.00%. Both models may support adult T1DM-related health education, but outputs should be interpreted as supplementary educational material under professional guidance rather than as diagnostic or therapeutic advice.<\/jats:p>","DOI":"10.1038\/s41598-026-62671-4","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T02:33:59Z","timestamp":1784601239000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of the accuracy and consistency of DeepSeek and ChatGPT in addressing type 1 diabetes mellitus-related queries in adults"],"prefix":"10.1038","volume":"16","author":[{"given":"Junyun","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Fei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingyi","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huilan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihuan","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaobin","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Foqiang","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingyan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"62671_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phrs.2022.106588","volume":"187","author":"L Ji","year":"2023","unstructured":"Ji, L. & Guo, W. Single-cell RNA sequencing highlights the roles of C1QB and NKG7 in the pancreatic islet immune microenvironment in type 1 diabetes mellitus. Pharmacol. Res. 187, 106588. https:\/\/doi.org\/10.1016\/j.phrs.2022.106588 (2023).","journal-title":"Pharmacol. Res."},{"key":"62671_CR2","doi-asserted-by":"publisher","first-page":"2609","DOI":"10.1007\/s00125-021-05568-3","volume":"64","author":"RIG Holt","year":"2021","unstructured":"Holt, R. I. G. et al. The management of type 1 diabetes in adults. A consensus report by the American Diabetes Association (ADA) and the European Association for the Study of Diabetes (EASD). Diabetologia 64, 2609\u20132652. https:\/\/doi.org\/10.1007\/s00125-021-05568-3 (2021).","journal-title":"Diabetologia"},{"issue":"Suppl 6","key":"62671_CR3","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1111\/dom.16501","volume":"27","author":"KJ Bell","year":"2025","unstructured":"Bell, K. J. & Lain, S. J. The changing epidemiology of type 1 diabetes: A global perspective. Diabetes Obes. Metab. 27(Suppl 6), 3\u201314. https:\/\/doi.org\/10.1111\/dom.16501 (2025).","journal-title":"Diabetes Obes. Metab."},{"key":"62671_CR4","doi-asserted-by":"publisher","first-page":"2987","DOI":"10.2337\/db11-1625","volume":"61","author":"RG Miller","year":"2012","unstructured":"Miller, R. G., Secrest, A. M., Sharma, R. K., Songer, T. J. & Orchard, T. J. Improvements in the life expectancy of type 1 diabetes: the Pittsburgh Epidemiology of Diabetes Complications study cohort. Diabetes 61, 2987\u20132992. https:\/\/doi.org\/10.2337\/db11-1625 (2012).","journal-title":"Diabetes"},{"key":"62671_CR5","doi-asserted-by":"publisher","first-page":"140","DOI":"10.4093\/dmj.2021.0322","volume":"47","author":"I Laspe","year":"2023","unstructured":"Laspe, I., Meier, J. J. & Nauck, M. A. Comparison of insulin-treated patients with ambiguous diabetes type with definite type 1 and type 2 diabetes mellitus subjects: A clinical perspective. Diabetes Metab. J. 47, 140\u2013146. https:\/\/doi.org\/10.4093\/dmj.2021.0322 (2023).","journal-title":"Diabetes Metab. J."},{"issue":"Suppl 6","key":"62671_CR6","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1111\/dom.16402","volume":"27","author":"C Evans-Molina","year":"2025","unstructured":"Evans-Molina, C. & Oram, R. A. Type 1 diabetes presenting in adults: Trends, diagnostic challenges and unique features. Diabetes Obes. Metab. 27(Suppl 6), 57\u201368. https:\/\/doi.org\/10.1111\/dom.16402 (2025).","journal-title":"Diabetes Obes. Metab."},{"key":"62671_CR7","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1038\/s41574-023-00853-0","volume":"19","author":"MJ Redondo","year":"2023","unstructured":"Redondo, M. J. & Morgan, N. G. Heterogeneity and endotypes in type 1 diabetes mellitus. Nat. Rev. Endocrinol. 19, 542\u2013554. https:\/\/doi.org\/10.1038\/s41574-023-00853-0 (2023).","journal-title":"Nat. Rev. Endocrinol."},{"key":"62671_CR8","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1231240","volume":"11","author":"Y Lai","year":"2023","unstructured":"Lai, Y. et al. The quality and reliability of TikTok videos on non-alcoholic fatty liver disease: A propensity score matching analysis. Front. Public Health 11, 1231240. https:\/\/doi.org\/10.3389\/fpubh.2023.1231240 (2023).","journal-title":"Front. Public Health"},{"key":"62671_CR9","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.783909","volume":"13","author":"HK Kim","year":"2022","unstructured":"Kim, H. K. & Tandoc, E. C. Jr. Consequences of online misinformation on COVID-19: Two potential pathways and disparity by eHealth literacy. Front. Psychol. 13, 783909. https:\/\/doi.org\/10.3389\/fpsyg.2022.783909 (2022).","journal-title":"Front. Psychol."},{"key":"62671_CR10","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.82310","volume":"17","author":"A Mishra","year":"2025","unstructured":"Mishra, A. et al. Role of generative artificial intelligence in personalized medicine: A systematic review. Cureus 17, e82310. https:\/\/doi.org\/10.7759\/cureus.82310 (2025).","journal-title":"Cureus"},{"key":"62671_CR11","doi-asserted-by":"publisher","first-page":"2211","DOI":"10.1001\/jama.2017.18152","volume":"318","author":"DSW Ting","year":"2017","unstructured":"Ting, D. S. W. et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 318, 2211\u20132223. https:\/\/doi.org\/10.1001\/jama.2017.18152 (2017).","journal-title":"JAMA"},{"key":"62671_CR12","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","volume":"316","author":"V Gulshan","year":"2016","unstructured":"Gulshan, V. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316, 2402\u20132410. https:\/\/doi.org\/10.1001\/jama.2016.17216 (2016).","journal-title":"JAMA"},{"key":"62671_CR13","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.946915","volume":"13","author":"X Huang","year":"2022","unstructured":"Huang, X. et al. Artificial intelligence promotes the diagnosis and screening of diabetic retinopathy. Front Endocrinol (Lausanne) 13, 946915. https:\/\/doi.org\/10.3389\/fendo.2022.946915 (2022).","journal-title":"Front Endocrinol (Lausanne)"},{"key":"62671_CR14","doi-asserted-by":"publisher","DOI":"10.1080\/07853890.2025.2461679","volume":"57","author":"C Lei","year":"2025","unstructured":"Lei, C. et al. Artificial intelligence-assisted diagnosis of early gastric cancer: Present practice and future prospects. Ann. Med. 57, 2461679. https:\/\/doi.org\/10.1080\/07853890.2025.2461679 (2025).","journal-title":"Ann. Med."},{"issue":"1","key":"62671_CR15","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1186\/s12903-025-06034-x","volume":"25","author":"\u00d6F Kaygisiz","year":"2025","unstructured":"Kaygisiz, \u00d6. F. & Teke, M. T. Can deepseek and ChatGPT be used in the diagnosis of oral pathologies?. BMC Oral Health 25638. https:\/\/doi.org\/10.1186\/s12903-025-06034-x (2025).","journal-title":"BMC Oral Health"},{"key":"62671_CR16","doi-asserted-by":"publisher","first-page":"2550","DOI":"10.1038\/s41591-025-03726-3","volume":"31","author":"M Tordjman","year":"2025","unstructured":"Tordjman, M. et al. Comparative benchmarking of the DeepSeek large language model on medical tasks and clinical reasoning. Nat. Med. 31, 2550\u20132555. https:\/\/doi.org\/10.1038\/s41591-025-03726-3 (2025).","journal-title":"Nat. Med."},{"key":"62671_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-025-02213-z","volume":"49","author":"J Wu","year":"2025","unstructured":"Wu, J., Wang, Z. & Qin, Y. Performance of DeepSeek-R1 and ChatGPT-4o on the Chinese National Medical Licensing Examination: A comparative study. J. Med. Syst. 49, 74. https:\/\/doi.org\/10.1007\/s10916-025-02213-z (2025).","journal-title":"J. Med. Syst."},{"key":"62671_CR18","doi-asserted-by":"publisher","first-page":"1887","DOI":"10.12669\/pjms.41.7.12183","volume":"41","author":"SA Meo","year":"2025","unstructured":"Meo, S. A., Abukhalaf, F. A., ElToukhy, R. A. & Sattar, K. Exploring the role of DeepSeek-R1, ChatGPT-4, and Google Gemini in medical education: How valid and reliable are they?. Pak. J. Med. Sci. 41, 1887\u20131892. https:\/\/doi.org\/10.12669\/pjms.41.7.12183 (2025).","journal-title":"Pak. J. Med. Sci."},{"key":"62671_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/s11695-025-08249-x","author":"S Guo","year":"2025","unstructured":"Guo, S. et al. Evaluating artificial intelligence-generated patient education materials for bariatric surgery: Comparative analysis of response quality, reliability, and readability across ChatGPT and DeepSeek models. Obes. Surg. https:\/\/doi.org\/10.1007\/s11695-025-08249-x (2025).","journal-title":"Obes. Surg."},{"key":"62671_CR20","doi-asserted-by":"publisher","DOI":"10.1111\/odi.70087","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Liang, R. & Lai, P. Comment on \u201cDiagnostic Performance of ChatGPT-4o and DeepSeek-3 Differential Diagnosis of Complex Oral Lesions: A Multimodal Imaging and Case Difficulty Analysis\u201d. Oral Dis https:\/\/doi.org\/10.1111\/odi.70087 (2025).","journal-title":"Oral Dis"},{"key":"62671_CR21","doi-asserted-by":"publisher","first-page":"4056","DOI":"10.1097\/js9.0000000000002386","volume":"111","author":"L Chan","year":"2025","unstructured":"Chan, L., Xu, X. & Lv, K. DeepSeek-R1 and GPT-4 are comparable in a complex diagnostic challenge: A historical control study. Int. J. Surg. 111, 4056\u20134059. https:\/\/doi.org\/10.1097\/js9.0000000000002386 (2025).","journal-title":"Int. J. Surg."},{"key":"62671_CR22","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1001\/jama.2023.8288","volume":"330","author":"Z Kanjee","year":"2023","unstructured":"Kanjee, Z., Crowe, B. & Rodman, A. Accuracy of a generative artificial intelligence model in a complex diagnostic challenge. JAMA 330, 78\u201380. https:\/\/doi.org\/10.1001\/jama.2023.8288 (2023).","journal-title":"JAMA"},{"key":"62671_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2025.105871","volume":"198","author":"M Zhou","year":"2025","unstructured":"Zhou, M., Pan, Y., Zhang, Y., Song, X. & Zhou, Y. Evaluating AI-generated patient education materials for spinal surgeries: Comparative analysis of readability and DISCERN quality across ChatGPT and deepseek models. Int. J. Med. Inform. 198, 105871. https:\/\/doi.org\/10.1016\/j.ijmedinf.2025.105871 (2025).","journal-title":"Int. J. Med. Inform."},{"key":"62671_CR24","doi-asserted-by":"publisher","DOI":"10.1097\/md.0000000000035543","volume":"102","author":"S Yilmaz Hanci","year":"2023","unstructured":"Yilmaz Hanci, S. How readable and quality are online patient education materials about Helicobacter pylori?: Assessment of the readability, quality and reliability. Medicine (Baltimore) 102, e35543. https:\/\/doi.org\/10.1097\/md.0000000000035543 (2023).","journal-title":"Medicine (Baltimore)"},{"key":"62671_CR25","doi-asserted-by":"publisher","DOI":"10.2196\/41518","volume":"25","author":"Z He","year":"2023","unstructured":"He, Z. et al. The reliability and quality of short videos as a source of dietary guidance for inflammatory bowel disease: Cross-sectional study. J. Med. Internet Res. 25, e41518. https:\/\/doi.org\/10.2196\/41518 (2023).","journal-title":"J. Med. Internet Res."},{"key":"62671_CR26","doi-asserted-by":"publisher","DOI":"10.1111\/hel.13078","volume":"29","author":"Y Lai","year":"2024","unstructured":"Lai, Y. et al. Exploring the capacities of ChatGPT: A comprehensive evaluation of its accuracy and repeatability in addressing Helicobacter pylori-related queries. Helicobacter 29, e13078. https:\/\/doi.org\/10.1111\/hel.13078 (2024).","journal-title":"Helicobacter"},{"key":"62671_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjoto.2025.104667","volume":"46","author":"S Prasad","year":"2025","unstructured":"Prasad, S., Langlie, J., Pasick, L., Chen, R. & Franzmann, E. Evaluating advanced AI reasoning models: ChatGPT-4.0 and DeepSeek-R1 diagnostic performance in otolaryngology: A comparative analysis. Am. J. Otolaryngol. 46, 104667. https:\/\/doi.org\/10.1016\/j.amjoto.2025.104667 (2025).","journal-title":"Am. J. Otolaryngol."},{"key":"62671_CR28","doi-asserted-by":"publisher","DOI":"10.1590\/s1677-5538.Ibju.2025.0325","author":"VBP Pinto","year":"2025","unstructured":"Pinto, V. B. P. et al. Performance of ChatGPT and DeepSeek in the management of postprostatectomy uri-nary incontinence. Int. Braz. J. Urol. https:\/\/doi.org\/10.1590\/s1677-5538.Ibju.2025.0325 (2025).","journal-title":"Int. Braz. J. Urol."},{"key":"62671_CR29","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1111\/coa.14273","volume":"50","author":"\u00c7 Becerik","year":"2025","unstructured":"Becerik, \u00c7., Y\u0131ld\u0131z, S., Tepe Karaca, \u00c7. & Toros, S. Z. Evaluation of the usability of ChatGPT-4 and Google Gemini in patient education about rhinosinusitis. Clin. Otolaryngol. 50, 456\u2013461. https:\/\/doi.org\/10.1111\/coa.14273 (2025).","journal-title":"Clin. Otolaryngol."},{"key":"62671_CR30","doi-asserted-by":"publisher","DOI":"10.2196\/82885","volume":"12","author":"SS Thiru","year":"2026","unstructured":"Thiru, S. S. et al. ChatGPT versus UpToDate in preclinical medical education: Cross-sectional analysis using term frequency-inverse document frequency cosine similarity. JMIR Med. Educ. 12, e82885. https:\/\/doi.org\/10.2196\/82885 (2026).","journal-title":"JMIR Med. Educ."},{"key":"62671_CR31","doi-asserted-by":"publisher","first-page":"Itc33","DOI":"10.7326\/aitc202203150","volume":"175","author":"FZ Syed","year":"2022","unstructured":"Syed, F. Z. Type 1 diabetes mellitus. Ann. Intern. Med. 175, Itc33-itc48. https:\/\/doi.org\/10.7326\/aitc202203150 (2022).","journal-title":"Ann. Intern. Med."},{"key":"62671_CR32","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1038\/s41574-023-00816-5","volume":"19","author":"D Tatovic","year":"2023","unstructured":"Tatovic, D., Narendran, P. & Dayan, C. M. A perspective on treating type 1 diabetes mellitus before insulin is needed. Nat. Rev. Endocrinol. 19, 361\u2013370. https:\/\/doi.org\/10.1038\/s41574-023-00816-5 (2023).","journal-title":"Nat. Rev. Endocrinol."},{"key":"62671_CR33","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2022-067899","volume":"13","author":"O Cisuelo","year":"2023","unstructured":"Cisuelo, O. et al. Development of an artificial intelligence system to identify hypoglycaemia via ECG in adults with type 1 diabetes: Protocol for data collection under controlled and free-living conditions. BMJ Open 13, e067899. https:\/\/doi.org\/10.1136\/bmjopen-2022-067899 (2023).","journal-title":"BMJ Open"},{"key":"62671_CR34","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1055\/a-2118-2011","volume":"131","author":"JS Schmelzer","year":"2023","unstructured":"Schmelzer, J. S., Kahle-Stephan, M., Meier, J. J. & Nauck, M. A. Prospective external validation of an algorithm predicting hourly basal insulin infusion rates from characteristics of patients with type 1 diabetes treated with insulin pumps. Exp. Clin. Endocrinol. Diabetes 131, 539\u2013547. https:\/\/doi.org\/10.1055\/a-2118-2011 (2023).","journal-title":"Exp. Clin. Endocrinol. Diabetes"},{"key":"62671_CR35","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1016\/j.knee.2025.06.007","volume":"56","author":"H Wu","year":"2025","unstructured":"Wu, H. et al. ChatGPT-4.0 and DeepSeek-R1 does not yet provide clinically supported answers for knee osteoarthritis. Knee 56, 386\u2013396. https:\/\/doi.org\/10.1016\/j.knee.2025.06.007 (2025).","journal-title":"Knee"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62671-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62671-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62671-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T23:06:58Z","timestamp":1792537618000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62671-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["62671"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-62671-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]},"assertion":[{"value":"9 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study involved expert evaluators assessing AI-generated responses. Informed consent was obtained from all participating experts.","order":2,"name":"Ethics","label":"Ethical approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"33094"}}