{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T15:14:07Z","timestamp":1786115647674,"version":"build-2736575974"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T00:00:00Z","timestamp":1785974400000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Myopia is a major global public health concern, and the growing use of LLMs for health consultation makes the accuracy of their myopia-related responses increasingly important. Existing ophthalmic LLM studies have largely focused on image-based applications and mixed ocular diseases, with limited evaluation of myopia-specific reasoning. Yet myopia-related inquiries span both breadth and depth, from specialized differential considerations to common issues in prevention, control, and public education. This study aimed to assess mainstream LLMs across multiple levels of myopia-related knowledge and clinical reasoning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This comparative evaluation study assessed six large language models: GPT-5.3 Instant, DeepSeek-V3.2, Gemini 3.1 Pro Preview, Claude Opus 4.7, Qwen3.6-Plus, and Doubao-Seed-2.0-Pro. The assessment covered four clinically relevant domains of myopia care and included hierarchical case-based scenarios spanning core judgment, preferred management, and follow-up. Objective items were submitted in independent new chat sessions, repeated three times, and tested without additional medically enhancing prompts. For the open-ended case tasks, responses from the six models and eight junior physicians were independently scored by two senior ophthalmology experts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>ChatGPT showed the highest accuracy in standardized judgment tasks, case-based clinical tasks, and external validation multiple-choice questions, achieving 92.33% \u00b1 1.15%, 85.00% \u00b1 1.67%, and 88.00% \u00b1 1.00%, respectively, with DeepSeek ranking second. In case-based scenarios, model performance was strongest for core judgment but declined notably for preferred management decisions. In the open-ended case assessment, ChatGPT, DeepSeek, Claude, and Gemini achieved higher expert-rated scores than junior clinicians, whereas Doubao and Qwen showed lower overall performance. Across the four clinical domains, performance differences widened in tasks requiring applied management and referral reasoning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Current LLMs demonstrated substantial capability in myopia-related knowledge assessment and text-based clinical reasoning. For patients and the public, these models may provide convenient access to relatively professional responses to common myopia-related questions. Although several models achieved higher expert-rated scores than junior clinicians in standardized written cases, this advantage was limited to text-based assessment and should not be extrapolated to real-world clinical performance. Given the complexity of specialist judgment and individual variation, model-generated responses should serve as informative references for consultation, health education, and preliminary decision support, not substitutes for formal clinical advice or physician-led individualized management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1886498","type":"journal-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T04:25:24Z","timestamp":1785990324000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating large language models in specialized myopia knowledge and clinical reasoning"],"prefix":"10.3389","volume":"13","author":[{"given":"Zhilin","family":"Li","sequence":"first","affiliation":[{"name":"Guangzhou Medical University","place":["Guangzhou, China"]},{"name":"The Third Affiliated Hospital (The Affiliated Luohu Hospital) of Shenzhen University, Shenzhen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Xin","sequence":"additional","affiliation":[{"name":"Shenzhen Eye Hospital, Shenzhen Eye Medical Center, Southern Medical University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tai","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, The Second People's Hospital of Chengdu Pidu District","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Li","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Guizhou University of Traditional Chinese Medicine","place":["Guiyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiyu","family":"Jia","sequence":"additional","affiliation":[{"name":"Shenzhen Eye Hospital, Shenzhen Eye Medical Center, Southern Medical University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1167\/iovs.62.5.2","article-title":"IMI Impact of myopia","volume":"62","author":"Sankaridurg","year":"2021","journal-title":"Invest Ophth Vis Sci."},{"key":"B2","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1038\/s41572-020-00231-4","article-title":"Myopia","volume":"6","author":"Baird","year":"2020","journal-title":"Nat Rev Dis Primers."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1016\/j.ophtha.2016.01.006","article-title":"Global prevalence of myopia and high myopia and temporal trends from 2000 through 2050","volume":"123","author":"Holden","year":"2016","journal-title":"Ophthalmology."},{"key":"B4","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1167\/iovs.61.4.49","article-title":"The complications of myopia: a review and meta-analysis","volume":"61","author":"Haarman","year":"2020","journal-title":"Invest Ophth Vis Sci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1016\/j.ophtha.2015.03.018","article-title":"Increasing prevalence of myopia in Europe and the impact of education","volume":"122","author":"Williams","year":"2015","journal-title":"Ophthalmology."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1001\/jamaophthalmol.2021.3303","article-title":"Continued increase of axial length and its risk factors in adults with high myopia","volume":"139","author":"Du","year":"2021","journal-title":"JAMA Ophthalmol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1001\/jamaophthalmol.2025.2918","article-title":"DeepSeek-R1 vs OpenAI o1 for ophthalmic diagnoses and management plans","volume":"143","author":"Mikhail","year":"2025","journal-title":"JAMA Ophthalmol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1001\/jamaophthalmol.2024.2513","article-title":"Development and evaluation of a retrieval-augmented large language model framework for ophthalmology","volume":"142","author":"Luo","year":"2024","journal-title":"JAMA Ophthalmol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"3887","DOI":"10.1245\/s10434-024-15107-0","article-title":"Enhanced artificial intelligence strategies in renal oncology: iterative optimization and comparative analysis of GPT 35 versus 40","volume":"31","author":"Liang","year":"2024","journal-title":"Ann Surg Oncol."},{"key":"B10","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1038\/s41591-024-03445-1","article-title":"Medical large language models are vulnerable to data-poisoning attacks","volume":"31","author":"Alber","year":"2025","journal-title":"Nat Med."},{"key":"B11","doi-asserted-by":"publisher","first-page":"100082","DOI":"10.70389\/PJS.100082","article-title":"Transparency in the reporting of artificial intelligence \u2013 the TITAN guideline","volume":"10","author":"Agha","year":"2025","journal-title":"Premier J Sci."},{"key":"B12","doi-asserted-by":"publisher","first-page":"6501","DOI":"10.1097\/JS9.0000000000001775","article-title":"Amplifying Chinese physicians' emphasis on patients' psychological states beyond urologic diagnoses with ChatGPT - a multicenter cross-sectional study","volume":"110","author":"Peng","year":"2024","journal-title":"Int J Surg."},{"key":"B13","doi-asserted-by":"publisher","first-page":"104770","DOI":"10.1016\/j.ebiom.2023.104770","article-title":"Benchmarking large language models' performances for myopia care: a comparative analysis of ChatGPT-35, ChatGPT-40, and Google Bard","volume":"95","author":"Lim","year":"2023","journal-title":"EBioMedicine."},{"key":"B14","doi-asserted-by":"publisher","first-page":"102384","DOI":"10.1016\/j.clae.2025.102384","article-title":"Evaluation of large language models for providing educational information in orthokeratology care","volume":"48","author":"Huang","year":"2025","journal-title":"Cont Lens Anterior Eye."},{"key":"B15","doi-asserted-by":"publisher","first-page":"P1","DOI":"10.1016\/j.ophtha.2022.10.031","article-title":"Refractive errors preferred practice pattern\u00ae","volume":"130","author":"Jacobs","year":"2023","journal-title":"Ophthalmology."},{"key":"B16","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1167\/iovs.66.12.39","article-title":"IMI-interventions for controlling myopia onset and progression 2025","volume":"66","author":"Bullimore","year":"2025","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3390\/app11146421","article-title":"What disease does this patient have? A large-scale open domain question answering dataset from medical exams","author":"Jin","year":"2021","journal-title":"Appl Sci."},{"key":"B18","volume-title":"Myopia: Causes, Prevention, and Treatment of an Increasingly Common Disease","year":"2024"},{"key":"B19","doi-asserted-by":"publisher","first-page":"M161","DOI":"10.1167\/iovs.18-25963","article-title":"IMI - industry guidelines and ethical considerations for myopia control report","volume":"60","author":"Jones","year":"2019","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1111\/opo.13207","article-title":"Assessing the utility of ChatGPT as an artificial intelligence-based large language model for information to answer questions on myopia","volume":"43","author":"Biswas","year":"2023","journal-title":"Ophthalmic Physiol Opt."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1007\/s40123-025-01142-x","article-title":"Large language models: pioneering new educational frontiers in childhood myopia","volume":"14","author":"Delsoz","year":"2025","journal-title":"Ophthalmol Ther."},{"key":"B22","doi-asserted-by":"publisher","first-page":"113768","DOI":"10.1016\/j.isci.2025.113768","article-title":"ChatMyopia: an AI agent for myopia-related consultation in primary eye care settings","volume":"28","author":"Wu","year":"2025","journal-title":"iScience."},{"key":"B23","doi-asserted-by":"publisher","first-page":"21059","DOI":"10.1038\/s41598-026-51205-7","article-title":"Evaluation of large language models and retrieval-augmented generation for clinical reasoning in pediatric myopia: a 50-case real-world study","volume":"16","author":"Kang","year":"2026","journal-title":"Sci Rep."},{"key":"B24","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","year":"2023","journal-title":"Nature."},{"key":"B25","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1038\/s41746-026-02627-0","article-title":"Clinical setting-dependent diagnostic accuracy of artificial intelligence and store-and-forward diabetic retinopathy screening: a systematic review and meta-analysis","volume":"9","author":"Chen","year":"2026","journal-title":"NPJ Digit Med."},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2026.1744389","article-title":"Comparative performance of GPT-4, GPT-o3, GPT-5, Gemini-3-Flash, and DeepSeek-R1 in ophthalmology question answering","author":"Zhang","year":"","journal-title":"Front Cell Dev Biol."},{"key":"B27","article-title":"Boosting medical visual understanding from multi-granular language learning","author":"Li","year":"2025","journal-title":"arXiv"},{"key":"B28","doi-asserted-by":"publisher","first-page":"11848","DOI":"10.1109\/TPAMI.2025.3598734","article-title":"Visionunite: a vision-language foundation model for ophthalmology enhanced with clinical knowledge","volume":"47","author":"Li","year":"2025","journal-title":"IEEE Trans Pattern Anal Mach Intell."}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1886498\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T04:25:25Z","timestamp":1785990325000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1886498\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,6]]},"references-count":28,"alternative-id":["10.3389\/fmed.2026.1886498"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1886498","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,6]]},"article-number":"1886498"}}