{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:49:36Z","timestamp":1790790576614,"version":"4.1.0"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>There are significant differences in the diagnosis and treatment of chronic non-bacterial osteitis (CNO), and there is an urgent need for health education efforts to enhance awareness of this condition. Deepseek V3, Doubao, and Kimi1.5 are highly popular language models in China that can provide knowledge related to diseases. This article aims to investigate the accuracy and reproducibility of the responses provided by these three artificial intelligence (AI) language models in answering questions about CNO.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>According to the latest expert consensus, 16 questions related to CNO were collected. The three AI language models were separately asked these questions at three different times. The answers were independently evaluated by two orthopedic experts.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Among the responses of the three AI models to 16 CNO-related questions across three rounds of testing, only Doubao received \u201cCompletely incorrect\u201d ratings (accounting for 6.25%) in the third round of scoring by Reviewer 2. During the answering process, Doubao had the shortest response time and provided the most words in its answers. In the first and third rounds of scoring by the first expert, Kimi scored the highest (3.938\u202f\u00b1\u202f0.342, 3.875\u202f\u00b1\u202f0.873), while in the second round, Doubao scored the highest (3.875\u202f\u00b1\u202f0.5). In the second round of scoring by the second expert, Doubao received the highest score (3.812\u202f\u00b1\u202f0.403). In the first and third rounds, Kimi1.5 received the highest score (3.812\u202f\u00b1\u202f0.602, 3.812\u202f\u00b1\u202f0.704).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Deepseek V3, Doubao, and Kimi1.5 are capable of answering most questions related to CNO with good accuracy and reproducibility, showing no significant differences.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2025.1629149","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T05:27:04Z","timestamp":1759123624000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Evaluation of the accuracy and repeatability of Deepseek V3, Doubao, and Kimi1.5 in answering knowledge-related queries about chronic non-bacterial osteitis"],"prefix":"10.3389","volume":"8","author":[{"given":"Zhenxing","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longxin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoran","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1001\/jama.2020.0370","article-title":"Artificial intelligence improves breast cancer screening in study","volume":"323","author":"Abbasi","year":"2020","journal-title":"JAMA"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"152365","DOI":"10.1016\/j.anndiagpath.2024.152365","article-title":"ChatGPT for histopathologic diagnosis","volume":"73","author":"Apornvirat","year":"2024","journal-title":"Ann. Diagn. Pathol."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1016\/j.annemergmed.2023.01.022","article-title":"The ChatGPT era: artificial intelligence in emergency medicine","volume":"81","author":"Bradshaw","year":"2023","journal-title":"Ann. Emerg. Med."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1038\/s41575-022-00701-y","article-title":"Artificial intelligence and automation in endoscopy and surgery","volume":"20","author":"Chadebecq","year":"2023","journal-title":"Nat. Rev. Gastroenterol. Hepatol."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2414","DOI":"10.1038\/s41591-023-02573-4","article-title":"AI-supported insulin dosing for type 2 diabetes","volume":"29","author":"Davis","year":"2023","journal-title":"Nat. Med."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e768","DOI":"10.1097\/01.JU.0001008880.11564.10.13","article-title":"MP47-13 ChatGPT explains testosterone therapy: accurate answers with questionable references","volume":"211","author":"Hartman-Kenzler","year":"2024","journal-title":"J. Urol."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"109344","DOI":"10.1016\/j.clim.2023.109344","article-title":"Gathering expert consensus to inform a proposed trial in chronic nonbacterial osteomyelitis (CNO)","volume":"251","author":"Hedrich","year":"2023","journal-title":"Clin. Immunol."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"S770","DOI":"10.1016\/j.annonc.2024.08.1254","article-title":"1194P development of a novel artificial intelligence (AI) algorithm to detect pulmonary nodules on chest radiography","volume":"35","author":"Higuchi","year":"2024","journal-title":"Ann. Oncol."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e13116","DOI":"10.1111\/hel.13116","article-title":"Assessing accuracy of ChatGPT on addressing Helicobacter pylori infection-related questions: a national survey and comparative study","volume":"29","author":"Hu","year":"2024","journal-title":"Helicobacter"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1111\/j.1651-2227.2011.02205.x","article-title":"Nonbacterial osteitis in children: data of a German incidence surveillance study","volume":"100","author":"Jansson","year":"2011","journal-title":"Acta Paediatr."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1001\/jama.2023.11440","article-title":"Artificial intelligence in clinical diagnosis: opportunities, challenges, and hype","volume":"330","author":"Kulkarni","year":"2023","journal-title":"JAMA"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e13078","DOI":"10.1111\/hel.13078","article-title":"Exploring the capacities of ChatGPT: a comprehensive evaluation of its accuracy and repeatability in addressing Helicobacter pylori-related queries","volume":"29","author":"Lai","year":"2024","journal-title":"Helicobacter"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1097\/BOR.0000000000000734","article-title":"Comparing children and adults with chronic nonbacterial osteomyelitis","volume":"32","author":"Lenert","year":"2020","journal-title":"Curr. Opin. Rheumatol."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"4291","DOI":"10.1093\/eurheartj\/ehae465","article-title":"Artificial intelligence in cardiovascular medicine: clinical applications","volume":"45","author":"L\u00fcscher","year":"2024","journal-title":"Eur. Heart J."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"268","DOI":"10.4103\/crst.crst_83_24","article-title":"Testosterone hallucination by artificial intelligence? ENZAMET trial, in the spring of 2023","volume":"7","author":"Natchagande","year":"2024","journal-title":"Cancer Research Statistics Treatment"},{"key":"ref16","first-page":"499","article-title":"Beyond data quantity: key factors driving performance in multilingual language models","author":"Nezhad","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"56","DOI":"10.3390\/ai6030056","article-title":"Emotion-aware embedding fusion in large language models (flan-T5, llama 2, DeepSeek-R1, and ChatGPT 4) for intelligent response generation","volume":"6","author":"Rasool","year":"2025","journal-title":"AI"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1145\/3383972.3384061","article-title":"Statistic solution for machine learning to analyze heart disease data","volume-title":"Proceedings of the 2020 12th international conference on machine learning and computing","author":"Rasool","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1737","DOI":"10.1007\/s00296-016-3572-6","article-title":"Unexpectedly high incidences of chronic non-bacterial as compared to bacterial osteomyelitis in children","volume":"36","author":"Schnabel","year":"2016","journal-title":"Rheumatol. Int."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"103679","DOI":"10.1016\/j.trc.2022.103679","article-title":"A literature review of artificial intelligence applications in railway systems","volume":"140","author":"Tang","year":"2022","journal-title":"Transport. Res. Part C"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1038\/s41591-024-02970-3","article-title":"Artificial intelligence in surgery","volume":"30","author":"Varghese","year":"2024","journal-title":"Nat. Med."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.future.2022.07.018","article-title":"Special issue on artificial intelligence-of-things (AIoT): opportunities, challenges, and solutions-part I: artificial intelligence applications in various fields","volume":"137","author":"Wei","year":"2022","journal-title":"Futur. Gener. Comput. Syst."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1136\/ard-2024-226446","article-title":"Expert consensus recommendations for the diagnosis and treatment of chronic non-bacterial osteitis (CNO) in adults","volume":"84","author":"Winter","year":"2025","journal-title":"Ann. Rheum. Dis."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"S1090","DOI":"10.1016\/j.annonc.2023.09.848","article-title":"2066P evaluation of the quality and reliability of ChatGPT and perplexity\u2019s responses about rectal cancer","volume":"34","author":"Yazici","year":"2023","journal-title":"Ann. Oncol."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"100095","DOI":"10.1016\/j.jtauto.2021.100095","article-title":"Chronic nonbacterial osteomyelitis (CNO) and chronic recurrent multifocal osteomyelitis (CRMO)","volume":"4","author":"Zhao","year":"2021","journal-title":"J. Transl. Autoimmun."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"105871","DOI":"10.1016\/j.ijmedinf.2025.105871","article-title":"Evaluating AI-generated patient education materials for spinal surgeries: comparative analysis of readability and DISCERN quality across ChatGPT and deepseek models","volume":"198","author":"Zhou","year":"2025","journal-title":"Int. J. Med. Inform."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1629149\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T05:27:04Z","timestamp":1759123624000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1629149\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":26,"alternative-id":["10.3389\/frai.2025.1629149"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1629149","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]},"article-number":"1629149"}}