{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T18:17:53Z","timestamp":1791915473586,"version":"4.3.4"},"reference-count":43,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004377","name":"The Hong Kong Polytechnic University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Advances in Ophthalmology Practice and Research"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.aopr.2025.10.006","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T01:41:16Z","timestamp":1761788476000},"page":"33-41","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"title":["Benchmarking large multimodal models for ophthalmic visual question answering with OphthalWeChat"],"prefix":"10.1016","volume":"6","author":[{"given":"Pusheng","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiyi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiancheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingjie","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yalin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingguang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6094-137X","authenticated-orcid":false,"given":"Danli","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.aopr.2025.10.006_bib1","doi-asserted-by":"crossref","DOI":"10.1038\/s41591-025-03727-2","article-title":"Benchmark evaluation of DeepSeek large language models in clinical decision-making","author":"Sandmann","year":"2025","journal-title":"Nat Med"},{"key":"10.1016\/j.aopr.2025.10.006_bib2","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.aopr.2025.05.001","article-title":"DeepSeek-R1 outperforms Gemini 2.0 Pro, OpenAI o1, and o3-mini in bilingual complex ophthalmology reasoning","volume":"5","author":"Xu","year":"2025","journal-title":"Adv Ophthalmol Pract Res"},{"key":"10.1016\/j.aopr.2025.10.006_bib3","article-title":"Vision-Language Models in medical image analysis: from simple fusion to general large models","author":"Li","year":"2025","journal-title":"Inf Fusion"},{"key":"10.1016\/j.aopr.2025.10.006_bib4","doi-asserted-by":"crossref","DOI":"10.2196\/59505","article-title":"Multimodal large Language models in health care: applications, challenges, and future outlook","volume":"26","author":"AlSaad","year":"2024","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.aopr.2025.10.006_bib5","doi-asserted-by":"crossref","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":"10.1016\/j.aopr.2025.10.006_bib6","doi-asserted-by":"crossref","unstructured":"Khare, Y. et al. Mmbert: multimodal bert pretraining for improved medical vqa. 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI). 1033\u20131036 (IEEE). https:\/\/doi.org\/10.1109\/ISBI48211.2021.9434063.","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"10.1016\/j.aopr.2025.10.006_bib7","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2023.102611","article-title":"Medical visual question answering: a survey","volume":"143","author":"Lin","year":"2023","journal-title":"Artif Intell Med"},{"key":"10.1016\/j.aopr.2025.10.006_bib8","article-title":"ChatFFA: an ophthalmic chat system for unified vision-language understanding and question answering for fundus fluorescein angiography","volume":"27","author":"Chen","year":"2024","journal-title":"iScience"},{"key":"10.1016\/j.aopr.2025.10.006_bib9","doi-asserted-by":"crossref","DOI":"10.2196\/54047","article-title":"Slit lamp report generation and question answering: development and validation of a multimodal transformer model with large Language model integration","volume":"26","author":"Zhao","year":"2024","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.aopr.2025.10.006_bib10","doi-asserted-by":"crossref","DOI":"10.1136\/bjo-2023-324446","article-title":"ICGA-GPT: report generation and question answering for indocyanine green angiography images","author":"Chen","year":"2024","journal-title":"Br J Ophthalmol"},{"key":"10.1016\/j.aopr.2025.10.006_bib11","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1038\/s41746-024-01101-z","article-title":"FFA-GPT: an automated pipeline for fundus fluorescein angiography interpretation and question-answer","volume":"7","author":"Chen","year":"2024","journal-title":"npj Digit Med"},{"key":"10.1016\/j.aopr.2025.10.006_bib12","article-title":"From visual question answering to intelligent AI agents in ophthalmology","author":"Chen","year":"2025","journal-title":"The British journal of ophthalmology"},{"key":"10.1016\/j.aopr.2025.10.006_bib13","doi-asserted-by":"crossref","DOI":"10.1016\/j.imed.2025.03.002","article-title":"Evaluating large language models and agents in healthcare: key challenges in clinical applications","author":"Chen","year":"2025","journal-title":"Intelligent Medicine"},{"key":"10.1016\/j.aopr.2025.10.006_bib14","doi-asserted-by":"crossref","first-page":"e51","DOI":"10.1016\/S2589-7500(20)30240-5","article-title":"A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisability","volume":"3","author":"Khan","year":"2021","journal-title":"Lancet Digit Health"},{"key":"10.1016\/j.aopr.2025.10.006_bib15","article-title":"Predicting diabetic macular edema treatment responses using OCT: dataset and methods of APTOS competition","author":"Zhang","year":"2025","journal-title":"arXiv preprint arXiv250505768"},{"key":"10.1016\/j.aopr.2025.10.006_bib16","doi-asserted-by":"crossref","DOI":"10.1136\/bjo-2024-327006","article-title":"AngioReport: dataset and baseline methods for fundus angiography report generation","author":"Xu","year":"2025","journal-title":"The British journal of ophthalmology"},{"key":"10.1016\/j.aopr.2025.10.006_bib17","doi-asserted-by":"crossref","first-page":"2307","DOI":"10.1038\/s41591-023-02504-3","article-title":"A visual-language foundation model for pathology image analysis using medical Twitter","volume":"29","author":"Huang","year":"2023","journal-title":"Nat Med"},{"key":"10.1016\/j.aopr.2025.10.006_bib18","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2018.251","article-title":"A dataset of clinically generated visual questions and answers about radiology images","volume":"5","author":"Lau","year":"2018","journal-title":"Sci Data"},{"key":"10.1016\/j.aopr.2025.10.006_bib19","article-title":"30000+ questions for medical visual question answering","author":"He","year":"2020","journal-title":"arXiv preprint arXiv200310286"},{"key":"10.1016\/j.aopr.2025.10.006_bib20","doi-asserted-by":"crossref","unstructured":"Yim, W.-w. et al. Dermavqa: a multilingual visual question answering dataset for dermatology. International Conference on Medical Image Computing and Computer-Assisted Intervention. 209\u2013219 (Springer). https:\/\/doi.org\/10.1007\/978-3-031-72086-4_20.","DOI":"10.1007\/978-3-031-72086-4_20"},{"key":"10.1016\/j.aopr.2025.10.006_bib21","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1038\/s43856-024-00709-2","article-title":"Development of a large-scale medical visual question-answering dataset","volume":"4","author":"Zhang","year":"2024","journal-title":"Communications Medicine"},{"key":"10.1016\/j.aopr.2025.10.006_bib22","doi-asserted-by":"crossref","first-page":"8384","DOI":"10.1038\/s41467-024-52417-z","article-title":"Towards building multilingual language model for medicine","volume":"15","author":"Qiu","year":"2024","journal-title":"Nat Commun"},{"key":"10.1016\/j.aopr.2025.10.006_bib23","doi-asserted-by":"crossref","unstructured":"Zha, Y., Yang, Y., Li, R. & Hu, Z. AlignScore: evaluating factual consistency with A unified alignment function. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 11328\u201311348. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.634.","DOI":"10.18653\/v1\/2023.acl-long.634"},{"key":"10.1016\/j.aopr.2025.10.006_bib24","first-page":"27263","article-title":"Bartscore: evaluating generated text as text generation","volume":"34","author":"Yuan","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.aopr.2025.10.006_bib25","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q. & Artzi, Y. BERTScore: evaluating text generation with BERT. International Conference on Learning Representations."},{"key":"10.1016\/j.aopr.2025.10.006_bib26","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T. & Zhu, W.-J. Bleu: a method for automatic evaluation of machine translation. Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 311\u2013318. https:\/\/doi.org\/10.3115\/1073083.1073135.","DOI":"10.3115\/1073083.1073135"},{"key":"10.1016\/j.aopr.2025.10.006_bib27","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C. & Parikh, D. Cider: Consensus-based image description evaluation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4566\u20134575.","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"10.1016\/j.aopr.2025.10.006_bib28","unstructured":"Banerjee, S. & Lavie, A. METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. Proceedings of the Acl Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. 65\u201372."},{"key":"10.1016\/j.aopr.2025.10.006_bib29","unstructured":"Lin, C.-Y. Rouge: a package for automatic evaluation of summaries. Text Summarization Branches out. 74\u201381."},{"key":"10.1016\/j.aopr.2025.10.006_bib30","unstructured":"The most spoken languages worldwide in 2025, Access Date: 25 July, 2025. URL: https:\/\/www.statista.com\/statistics\/266808\/the-most-spoken-languages-worldwide\/."},{"key":"10.1016\/j.aopr.2025.10.006_bib31","article-title":"FunBench: benchmarking fundus reading skills of MLLMs","author":"Wei","year":"2025","journal-title":"arXiv preprint arXiv:250300901"},{"key":"10.1016\/j.aopr.2025.10.006_bib32","article-title":"A novel ophthalmic benchmark for evaluating multimodal large Language models with fundus photographs and OCT images","author":"Liang","year":"2025","journal-title":"arXiv preprint arXiv:250307094"},{"key":"10.1016\/j.aopr.2025.10.006_bib33","doi-asserted-by":"crossref","DOI":"10.1136\/bjo-2023-325054","article-title":"Unveiling the clinical incapabilities: a benchmarking study of GPT-4V(ision) for ophthalmic multimodal image analysis","author":"Xu","year":"2024","journal-title":"The British journal of ophthalmology"},{"key":"10.1016\/j.aopr.2025.10.006_bib34","doi-asserted-by":"crossref","unstructured":"Tascon-Morales, S., M\u00e1rquez-Neila, P. & Sznitman, R. Consistency-preserving visual question answering in medical imaging. International Conference on Medical Image Computing and Computer-Assisted Intervention. 386\u2013395 (Springer). https:\/\/doi.org\/10.1007\/978-3-031-16452-1_37.","DOI":"10.1007\/978-3-031-16452-1_37"},{"key":"10.1016\/j.aopr.2025.10.006_bib35","first-page":"94327","article-title":"Gmai-mmbench: a comprehensive multimodal evaluation benchmark towards general medical ai","volume":"37","author":"Ye","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.aopr.2025.10.006_bib36","doi-asserted-by":"crossref","unstructured":"Hu, Y. et al. Omnimedvqa: a new large-scale comprehensive evaluation benchmark for medical lvlm. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 22170\u201322183.","DOI":"10.1109\/CVPR52733.2024.02093"},{"key":"10.1016\/j.aopr.2025.10.006_bib37","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","article-title":"DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning","volume":"645","author":"Guo","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.aopr.2025.10.006_bib38","doi-asserted-by":"crossref","unstructured":"Pan, J., Bi, Q., Yang, Y., Zhu, P. & Bian, C. Label-efficient hybrid-supervised learning for medical image segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026\u20132034. https:\/\/doi.org\/10.1609\/aaai.v36i2.20098.","DOI":"10.1609\/aaai.v36i2.20098"},{"key":"10.1016\/j.aopr.2025.10.006_bib39","doi-asserted-by":"crossref","DOI":"10.1016\/j.xops.2023.100401","article-title":"Translation of color fundus photography into fluorescein angiography using deep learning for enhanced diabetic retinopathy screening","volume":"3","author":"Shi","year":"2023","journal-title":"Ophthalmol Sci"},{"key":"10.1016\/j.aopr.2025.10.006_bib40","article-title":"Reference-Guided verdict: llms-as-judges in automatic evaluation of free-form text","author":"Badshah","year":"2024","journal-title":"arXiv preprint arXiv:240809235"},{"key":"10.1016\/j.aopr.2025.10.006_bib41","first-page":"1847","article-title":"AHP-Powered LLM reasoning for multi-criteria evaluation of open-ended responses","author":"Lu","year":"2024","journal-title":"Findings of the Association for Computational Linguistics: EMNLP"},{"key":"10.1016\/j.aopr.2025.10.006_bib42","doi-asserted-by":"crossref","DOI":"10.2196\/53164","article-title":"Hallucination rates and reference accuracy of ChatGPT and bard for systematic reviews: comparative analysis","volume":"26","author":"Chelli","year":"2024","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.aopr.2025.10.006_bib43","article-title":"Why Language models hallucinate","author":"Kalai","year":"2025","journal-title":"arXiv preprint arXiv:250904664"}],"container-title":["Advances in Ophthalmology Practice and Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2667376225000538?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2667376225000538?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T04:32:55Z","timestamp":1773981175000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2667376225000538"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["S2667376225000538"],"URL":"https:\/\/doi.org\/10.1016\/j.aopr.2025.10.006","relation":{},"ISSN":["2667-3762"],"issn-type":[{"value":"2667-3762","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Benchmarking large multimodal models for ophthalmic visual question answering with OphthalWeChat","name":"articletitle","label":"Article Title"},{"value":"Advances in Ophthalmology Practice and Research","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aopr.2025.10.006","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier Inc. on behalf of Zhejiang University Press.","name":"copyright","label":"Copyright"}]}}