{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T02:11:39Z","timestamp":1773195099228,"version":"3.50.1"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"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>This study aims to develop and evaluate a multimodal large language model (LLM) for predicting refractive error (diopter) in adolescents by integrating fundus images with clinical and demographic data. The goal is to demonstrate how such a model can serve as a digital health tool for early screening and personalized management of refractive conditions in clinical and remote health settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A dataset of 16,226 annotated records from adolescents aged 2 to 18 years was used. A vision-language foundation model based on Qwen2.5-VL was fine-tuned using supervised learning, incorporating both imaging and clinical data to predict spherical equivalent (SE). The model was trained on a randomly split dataset, and performance was evaluated using mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (\n                      <jats:italic>R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      ) and the Pearson correlation coefficient.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The model achieved a mean absolute error of 0.647 diopters and showed strong predictive performance across most refractive subgroups. The incorporation of multimodal data significantly outperformed single-modality models. Visualization analyses confirmed that the model's predictions are clinically interpretable and reliable.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This multimodal LLM demonstrates the potential of digital health technologies to enhance refractive error prediction in adolescents. Its integration into digital health platforms can provide a non-invasive, scalable solution for early myopia screening, making it an invaluable tool for clinicians in both remote and urban settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1770007","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:31:02Z","timestamp":1773120662000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Prediction of refractive error in adolescents using a multimodal large language model"],"prefix":"10.3389","volume":"13","author":[{"given":"Chaojun","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Ophthalmology and Optometry, Lixiang Eye Hospital of Soochow University","place":["Suzhou, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Optometry, Lixiang Eye Hospital of Soochow University","place":["Suzhou, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Optometry, Lixiang Eye Hospital of Soochow University","place":["Suzhou, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahong","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Optometry, Lixiang Eye Hospital of Soochow University","place":["Suzhou, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pinghui","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Optometry, Lixiang Eye Hospital of Soochow University","place":["Suzhou, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianjun","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Optometry, Lixiang Eye Hospital of Soochow University","place":["Suzhou, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leilei","family":"Cao","sequence":"additional","affiliation":[{"name":"Innovation Center of Yangtze River Delta, Zhejiang University","place":["Jiaxing, Zhejiang, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1167\/tvst.13.8.16","article-title":"Machine learning models for predicting cycloplegic refractive error and myopia status based on non-cycloplegic data in Chinese students","volume":"13","author":"Ying","year":"2024","journal-title":"Transl Vision Sci Technol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1298","DOI":"10.1136\/bmjophth-2023-001298","article-title":"Prediction of refractive error and its progression: a machine learning-based algorithm","volume":"8","author":"Barraza-Bernal","year":"2023","journal-title":"BMJ Open Ophthalmol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"e2553543","DOI":"10.1001\/jamanetworkopen.2025.53543","article-title":"Deep learning prediction of childhood myopia progression using fundus image and refraction data","volume":"9","author":"Kang","year":"2026","journal-title":"JAMA Network Open"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e16225","DOI":"10.2196\/16225","article-title":"Deep learning-based prediction of refractive error using photorefraction images captured by a smartphone: model development and validation study","volume":"8","author":"Chun","year":"2020","journal-title":"JMIR Med Inform"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2861","DOI":"10.1167\/iovs.18-23887","article-title":"Deep learning for predicting refractive error from retinal fundus images","volume":"59","author":"Varadarajan","year":"2018","journal-title":"Investigat Ophthalmol Visual Sci"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1016\/j.jcrs.2018.06.017","article-title":"Predicting pseudophakic refractive error: interplay of biometry prediction error, anterior chamber depth, and changes in corneal curvature","volume":"44","author":"Wallace","year":"2018","journal-title":"J Cataract Refract Surg"},{"key":"B7","doi-asserted-by":"publisher","first-page":"e0248494","DOI":"10.1371\/journal.pone.0248494","article-title":"Prediction of cycloplegic refraction for noninvasive screening of children for refractive error","volume":"16","author":"Magome","year":"2021","journal-title":"PLoS ONE"},{"key":"B8","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1186\/s12938-022-01025-3","article-title":"Deep learning for predicting refractive error from multiple photorefraction images","volume":"21","author":"Xu","year":"2022","journal-title":"Biomed Eng Online"},{"key":"B9","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.aopr.2024.06.005","article-title":"Ocular image-based deep learning for predicting refractive error: a systematic review","volume":"4","author":"Yew","year":"2024","journal-title":"Adv Ophthalmol Pract Res"},{"key":"B10","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1038\/s41746-025-01772-2","article-title":"A multimodal visual-language foundation model for computational ophthalmology","volume":"8","author":"Shi","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1608988","DOI":"10.3389\/fcell.2025.1608988","article-title":"Large language models in the management of chronic ocular diseases: a scoping review","volume":"13","author":"Zhang","year":"2025","journal-title":"Front Cell Dev Biol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1732","DOI":"10.1097\/IAE.0000000000004204","article-title":"Applications of multimodal generative artificial intelligence in a real-world retina clinic setting","volume":"44","author":"Ghalibafan","year":"2024","journal-title":"Retina"},{"key":"B14","doi-asserted-by":"publisher","first-page":"255","DOI":"10.51329\/mehdiophthal1517","article-title":"Artificial intelligence in ophthalmology: opportunities, challenges, and ethical considerations","volume":"14","author":"Kazemzadeh","year":"2025","journal-title":"Med Hypoth Discov Innovat Ophthalmol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1576465","DOI":"10.3389\/fcell.2025.1576465","article-title":"Artificial intelligence technology in ophthalmology public health: current applications and future directions","volume":"13","author":"Chen","year":"2025","journal-title":"Front Cell Dev Biol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"834281","DOI":"10.3389\/fmed.2022.834281","article-title":"Prediction of refractive error based on ultrawide field images with deep learning models in myopia patients","volume":"9","author":"Yang","year":"2022","journal-title":"Front Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"100659","DOI":"10.1016\/j.xops.2024.100659","article-title":"Deep imbalanced regression model for predicting refractive error from retinal photos","volume":"5","author":"Yew","year":"2025","journal-title":"Ophthalmol Sci"},{"key":"B18","doi-asserted-by":"publisher","first-page":"20406223231209895","DOI":"10.1177\/20406223231209895","article-title":"Deep learning-based fundus image analysis for cardiovascular disease: a review","volume":"14","author":"Chikumba","year":"2023","journal-title":"Ther Adv Chronic Dis"},{"key":"B19","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1007\/s40123-025-01105-2","article-title":"Evaluating the efficacy of Large Language Models in guiding treatment decisions for pediatric refractive error","volume":"14","author":"Kang","year":"2025","journal-title":"Ophthalmol Ther"},{"key":"B20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18240\/ijo.2025.01.01","article-title":"Assessing the possibility of using large language models in ocular surface diseases","volume":"18","author":"Ling","year":"2025","journal-title":"Int J Ophthalmol"},{"key":"B21","doi-asserted-by":"crossref","DOI":"10.1145\/3744746","article-title":"A comprehensive overview of large language models","volume-title":"ACM Transactions on Intelligent Systems and Technology.","author":"Naveed","year":"2025"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641289","article-title":"A survey on evaluation of large language models","volume":"15","author":"Chang","year":"2024","journal-title":"ACM Trans Intellig Syst Technol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1038\/s41746-025-01487-4","article-title":"Application of multimodal large language models for safety indicator calculation and contraindication prediction in laser vision correction","volume":"8","author":"Choi","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B24","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1038\/s41746-025-01461-0","article-title":"Multimodal machine learning enables AI chatbot to diagnose ophthalmic diseases and provide high-quality medical responses","volume":"8","author":"Ma","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B25","doi-asserted-by":"publisher","first-page":"nwae403","DOI":"10.1093\/nsr\/nwae403","article-title":"A survey on multimodal large language models","volume":"11","author":"Yin","year":"2024","journal-title":"Nat Sci Rev"},{"key":"B26","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1111\/opo.13284","article-title":"Utility of artificial intelligence-based large language models in ophthalmic care","volume":"44","author":"Biswas","year":"2024","journal-title":"Ophthalmic Physiol Optics"},{"key":"B27","doi-asserted-by":"publisher","first-page":"895","DOI":"10.2147\/OPTH.S455178","article-title":"Comparison of refractive prediction error by axial length in flanged intrascleral intraocular lens fixation","volume":"18","author":"Kabata","year":"2024","journal-title":"Clini Ophthalmol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1186\/s12886-021-01950-2","article-title":"Gender differences in refraction prediction error of five formulas for cataract surgery","volume":"21","author":"Zhang","year":"2021","journal-title":"BMC Ophthalmol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1186\/s40662-023-00338-1","article-title":"Artificial intelligence-based refractive error prediction and EVO-implantable collamer lens power calculation for myopia correction","volume":"10","author":"Jiang","year":"2023","journal-title":"Eye Vision"},{"key":"B30","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1111\/opo.13444","article-title":"Refractive error maps: a predictive tool for refractive error progression","volume":"45","author":"Debowy","year":"2025","journal-title":"Ophthalmic Physiolog Optics"},{"key":"B31","doi-asserted-by":"publisher","first-page":"11206721251318384","DOI":"10.1177\/11206721251318384","article-title":"Artificial intelligence in the diagnosis and management of refractive errors","volume":"35","author":"Nguyen","year":"2025","journal-title":"Eur J Ophthalmol"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.13923","article-title":"Qwen2","author":"Bai","year":"2025","journal-title":"arXiv"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1770007\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:31:03Z","timestamp":1773120663000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1770007\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":32,"alternative-id":["10.3389\/fmed.2026.1770007"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1770007","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"article-number":"1770007"}}