{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T11:58:11Z","timestamp":1785499091672,"version":"3.56.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"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>Distinguishing glaucomatous damage from structural and functional changes related to high myopia remains a persistent clinical challenge.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To evaluate multimodal large language models (LLMs) for the differential diagnosis of high myopia alone versus high myopia with glaucoma under direct-answer and chain-of-thought (CoT) prompting, and to compare physician-rated response quality across models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analyzed a fixed retrospective archive of 100 patients, including 50 patients with high myopia without glaucoma and 50 patients with high myopia and primary open-angle glaucoma (POAG). High myopia was defined according to the source clinical archive as spherical equivalent of \u22126.0 diopters or less and\/or axial length of 26.0\u202fmm or greater. Four multimodal LLMs were assessed in Direct and CoT modes. Two ophthalmologists, each with more than 10\u202fyears of clinical experience, independently rated each output on clinical logic, medical knowledge\/conclusion accuracy, and evidence use\/multimodal consistency; one rater was a chief physician and the other was an attending physician. Diagnostic correctness was compared using Cochran\u2019s Q and McNemar tests; physician ratings were compared using Friedman and Wilcoxon signed-rank tests; weighted Cohen\u2019s kappa and intraclass correlation coefficients (ICCs) were used to assess inter-rater agreement.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      In Direct mode, case-level accuracies were 83.0% for Gemini 3 Flash Preview, 75.0% for Kimi-k2.5, 65.0% for GPT-5.4, and 49.0% for Qwen3.5-Plus. In CoT mode, case-level accuracies were 78.0% for Gemini 3 Flash Preview, 75.0% for Qwen3.5-Plus, 73.0% for GPT-5.4, and 69.0% for Kimi-k2.5. Cross-model differences were significant in Direct mode (Cochran\u2019s Q\u202f=\u202f31.16,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.001) but not in CoT mode (Q\u202f=\u202f3.23,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f0.357). Inter-rater agreement was strong, with weighted Cohen\u2019s kappa values of 0.80, 0.84, and 0.83 across the three physician-rated domains and ICC(3, k)\u202f=\u202f0.92 for the combined total score.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Multimodal LLMs showed variable performance on this retrospective benchmark for differentiating high myopia from high myopia with glaucoma, but CoT prompting did not consistently improve diagnostic accuracy. Physician ratings provided complementary evidence on clinical coherence and multimodal evidence use, supporting a broader benchmark-oriented evaluation framework for ophthalmic LLM applications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1864498","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T11:10:22Z","timestamp":1785496222000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating multimodal large language models for differential diagnosis of high myopia versus high myopia with Glaucoma"],"prefix":"10.3389","volume":"13","author":[{"given":"Houfa","family":"Yin","sequence":"first","affiliation":[{"name":"Eye Center of Second Affiliated Hospital, School of Medicine, Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang Provincial Key Laboratory of Ophthalmology, Zhejiang Provincial Clinical Research Center for Eye Diseases, Zhejiang Provincial Engineering Institute on Eye Diseases","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Yu","sequence":"additional","affiliation":[{"name":"Eye Center of Second Affiliated Hospital, School of Medicine, Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang Provincial Key Laboratory of Ophthalmology, Zhejiang Provincial Clinical Research Center for Eye Diseases, Zhejiang Provincial Engineering Institute on Eye Diseases","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[{"name":"Eye Center of Second Affiliated Hospital, School of Medicine, Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang Provincial Key Laboratory of Ophthalmology, Zhejiang Provincial Clinical Research Center for Eye Diseases, Zhejiang Provincial Engineering Institute on Eye Diseases","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixia","family":"Shen","sequence":"additional","affiliation":[{"name":"Eye Center of Second Affiliated Hospital, School of Medicine, Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang Provincial Key Laboratory of Ophthalmology, Zhejiang Provincial Clinical Research Center for Eye Diseases, Zhejiang Provincial Engineering Institute on Eye Diseases","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongmei","family":"Shi","sequence":"additional","affiliation":[{"name":"Eye Center of Second Affiliated Hospital, School of Medicine, Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang Provincial Key Laboratory of Ophthalmology, Zhejiang Provincial Clinical Research Center for Eye Diseases, Zhejiang Provincial Engineering Institute on Eye Diseases","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Clinical Medicine, Hangzhou Medical College","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaikai","family":"Zhao","sequence":"additional","affiliation":[{"name":"Eye Center of Second Affiliated Hospital, School of Medicine, Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang Provincial Key Laboratory of Ophthalmology, Zhejiang Provincial Clinical Research Center for Eye Diseases, Zhejiang Provincial Engineering Institute on Eye Diseases","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrzej","family":"Grzybowski","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, University of Warmia and Mazury","place":["Olsztyn, Poland"]},{"name":"Institute for Research in Ophthalmology, Foundation for Ophthalmology Development","place":["Poznan, Poland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Jin","sequence":"additional","affiliation":[{"name":"Eye Center of Second Affiliated Hospital, School of Medicine, Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang Provincial Key Laboratory of Ophthalmology, Zhejiang Provincial Clinical Research Center for Eye Diseases, Zhejiang Provincial Engineering Institute on Eye Diseases","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1136\/bjo.2005.081224","article-title":"The number of people with glaucoma worldwide in 2010 and 2020","volume":"90","author":"Quigley","year":"2006","journal-title":"Br J Ophthalmol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1016\/S0161-6420(99)90416-5","article-title":"The relationship between glaucoma and myopia: the Blue Mountains eye study","volume":"106","author":"Mitchell","year":"1999","journal-title":"Ophthalmology"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"6570","DOI":"10.1167\/iovs.13-12173","article-title":"Myopia and glaucoma in the south Korean population","volume":"54","author":"Chon","year":"2013","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1038\/eye.2013.223","article-title":"Histological changes of high axial myopia","volume":"28","author":"Jonas","year":"2014","journal-title":"Eye"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"562","DOI":"10.3390\/biom13030562","article-title":"Glaucoma and myopia: diagnostic challenges","volume":"13","author":"Sun","year":"2023","journal-title":"Biomolecules"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1001\/jamaophthalmol.2023.1717","article-title":"Comparison of optical coherence tomography structural parameters for diagnosis of Glaucoma in high myopia","volume":"141","author":"Jeong","year":"2023","journal-title":"JAMA Ophthalmol."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1097\/IJG.0000000000001631","article-title":"Optical coherence tomography can be used to assess glaucomatous optic nerve damage in Most eyes with high myopia","volume":"29","author":"Zemborain","year":"2020","journal-title":"J Glaucoma"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1097\/OPX.0000000000000776","article-title":"Macular diagnostic ability in OCT for assessing Glaucoma in high myopia","volume":"93","author":"Hung","year":"2016","journal-title":"Optom Vis Sci"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1260","DOI":"10.3390\/bioengineering10111260","article-title":"Addressing Glaucoma in myopic eyes: diagnostic and surgical challenges","volume":"10","author":"Vinod","year":"2023","journal-title":"Bioengineering"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1097\/ICU.0b013e32835cef31","article-title":"Myopia and glaucoma: diagnostic and therapeutic challenges","volume":"24","author":"Chang","year":"2013","journal-title":"Curr Opin Ophthalmol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1016\/j.ophtha.2018.01.023","article-title":"Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs","volume":"125","author":"Li","year":"2018","journal-title":"Ophthalmology"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1097\/IJG.0000000000000765","article-title":"Hybrid deep learning on single wide-field optical coherence tomography scans accurately classifies glaucoma suspects","volume":"26","author":"Muhammad","year":"2017","journal-title":"J Glaucoma"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1109\/TMI.2019.2927226","article-title":"A large-scale database and a CNN model for attention-based Glaucoma detection","volume":"39","author":"Li","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e172","DOI":"10.1016\/S2589-7500(19)30085-8","article-title":"Detection of glaucomatous optic neuropathy with spectral-domain optical coherence tomography: a retrospective training and validation deep-learning analysis","volume":"1","author":"Ran","year":"2019","journal-title":"Lancet Digit Health."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"e917","DOI":"10.1016\/S2589-7500(23)00201-7","article-title":"Large language models and their impact in ophthalmology","volume":"5","author":"Betzler","year":"2023","journal-title":"Lancet Digit Health"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1291404","DOI":"10.3389\/fmed.2023.1291404","article-title":"Exploring large language model for next generation of artificial intelligence in ophthalmology","volume":"10","author":"Jin","year":"2023","journal-title":"Front Med"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1001\/jamaophthalmol.2023.6917","article-title":"Assessment of a large language model's responses to questions and cases about Glaucoma and retina management","volume":"142","author":"Huang","year":"2024","journal-title":"JAMA Ophthalmol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1097\/IJG.0000000000002627","article-title":"Comparing performance of large language model-based tools on patient-driven Glaucoma inquiries","volume":"35","author":"Gupta","year":"2026","journal-title":"J Glaucoma"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.ajo.2024.05.022","article-title":"Predicting Glaucoma before onset using a large language model Chatbot","volume":"266","author":"Huang","year":"2024","journal-title":"Am J Ophthalmol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"e50842","DOI":"10.2196\/50842","article-title":"Performance of ChatGPT on ophthalmology-related questions across various examination levels: observational study","volume":"10","author":"Haddad","year":"2024","journal-title":"JMIR Med Educ"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e59843","DOI":"10.2196\/59843","article-title":"Large language models may help patients understand peer-reviewed scientific articles about ophthalmology: development and usability study","volume":"26","author":"Kianian","year":"2024","journal-title":"J Med Internet Res"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"2752","DOI":"10.1038\/s41433-025-03935-7","article-title":"Large language models in ophthalmology: a scoping review on their utility for clinicians, researchers, patients, and educators","volume":"39","author":"Artiaga","year":"2025","journal-title":"Eye (Lond)"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"e72101","DOI":"10.2196\/72101","article-title":"Performance of a small language model versus a large language model in answering Glaucoma frequently asked patient questions: development and usability study","volume":"5","author":"Faneli","year":"2026","journal-title":"JMIR AI"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"8756","DOI":"10.1038\/s41598-026-39444-0","article-title":"Benchmark evaluation of video large language models in quality assessment of science popularization videos for dry eye","volume":"16","author":"Zhou","year":"2026","journal-title":"Sci Rep"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"e76947","DOI":"10.2196\/76947","article-title":"Evaluating large language models in ophthalmology: systematic review","volume":"27","author":"Zhang","year":"2025","journal-title":"J Med Internet Res"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1097\/ICU.0000000000001062","article-title":"Vision of the future: large language models in ophthalmology","volume":"35","author":"Tailor","year":"2024","journal-title":"Curr Opin Ophthalmol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.aopr.2024.03.003","article-title":"Integration of smartphone technology and artificial intelligence for advanced ophthalmic care: a systematic review","volume":"4","author":"Jin","year":"2024","journal-title":"Adv Ophthalmol Pract Res"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.aopr.2025.10.004","article-title":"A systematic review of vision and vision-language foundation models in ophthalmology","volume":"6","author":"Jin","year":"2026","journal-title":"Adv Ophthalmol Pract Res."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"100078","DOI":"10.1016\/j.aopr.2022.100078","article-title":"Artificial intelligence and deep learning in ophthalmology: current status and future perspectives","volume":"2","author":"Jin","year":"2022","journal-title":"Adv Ophthalmol Pract Res."},{"key":"ref31","doi-asserted-by":"crossref","first-page":"24824","DOI":"10.52202\/068431-1800","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv Neural Inf Proces Syst"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"P71","DOI":"10.1016\/j.ophtha.2020.10.022","article-title":"Primary open-angle Glaucoma preferred practice pattern","volume":"128","author":"Gedde","year":"2021","journal-title":"Ophthalmology"},{"key":"ref33","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2023","journal-title":"arXiv"},{"key":"ref34","article-title":"MM-CoT: a benchmark for probing visual chain-of-thought reasoning in multimodal models","author":"Zhang","year":"2025","journal-title":"arXiv"},{"key":"ref35","article-title":"Look light, think heavy: what multimodal chain-of-thought reasoning can and cannot do","author":"Jin","year":"2026","journal-title":"arXiv"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"860574","DOI":"10.3389\/fmed.2022.860574","article-title":"Three-dimensional multi-task deep learning model to detect glaucomatous optic neuropathy and myopic features from optical coherence tomography scans: a retrospective multi-Centre study","volume":"9","author":"Ran","year":"2022","journal-title":"Front Med"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"8040","DOI":"10.1038\/s41598-023-34794-5","article-title":"Development of a deep learning system to detect glaucoma using macular vertical optical coherence tomography scans of myopic eyes","volume":"13","author":"Kim","year":"2023","journal-title":"Sci Rep"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1394","DOI":"10.3390\/biomedicines12071394","article-title":"Deep learning evaluation of Glaucoma detection using fundus photographs in highly myopic populations","volume":"12","author":"Chiang","year":"2024","journal-title":"Biomedicine"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1624015","DOI":"10.3389\/fopht.2025.1624015","article-title":"Glaucoma detection in myopic eyes using deep learning autoencoder-based regions of interest","volume":"5","author":"Bowd","year":"2025","journal-title":"Front Ophthalmol"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"100681","DOI":"10.1016\/j.xops.2024.100681","article-title":"Large language models in ophthalmology: a review of publications from top ophthalmology journals","volume":"5","author":"Agnihotri","year":"2025","journal-title":"Ophthalmol Sci"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1864498\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T11:10:24Z","timestamp":1785496224000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1864498\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":40,"alternative-id":["10.3389\/fmed.2026.1864498"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1864498","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]},"article-number":"1864498"}}