{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T12:20:21Z","timestamp":1794572421125,"version":"4.9.1"},"reference-count":45,"publisher":"Elsevier BV","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82201195"],"award-info":[{"award-number":["82201195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["cell.com","clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Cell Reports Medicine"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.xcrm.2026.102969","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T15:20:23Z","timestamp":1785943223000},"page":"102969","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"title":["An autonomous multimodal AI agent for evidence-grounded ophthalmic diagnosis"],"prefix":"10.1016","volume":"7","author":[{"given":"Kaikai","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qixuan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daohuan","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzheng","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rupesh","family":"Agrawal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gui-shuang","family":"Ying","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrzej","family":"Grzybowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4369-2417","authenticated-orcid":false,"given":"Kai","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.xcrm.2026.102969_bib1","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA"},{"key":"10.1016\/j.xcrm.2026.102969_bib2","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1007\/s40123-024-00981-4","article-title":"Retina fundus photograph-based artificial intelligence algorithms in medicine: a systematic review","volume":"13","author":"Grzybowski","year":"2024","journal-title":"Ophthalmol. Ther."},{"key":"10.1016\/j.xcrm.2026.102969_bib3","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1038\/s44172-024-00173-9","article-title":"Deep learning-based optical coherence tomography angiography image construction using spatial vascular connectivity network","volume":"3","author":"Le","year":"2024","journal-title":"Commun. Eng."},{"key":"10.1016\/j.xcrm.2026.102969_bib4","doi-asserted-by":"crossref","first-page":"903","DOI":"10.1055\/a-2227-3742","article-title":"Deep learning-based retinal layer segmentation in optical coherence tomography scans of patients with inherited retinal diseases","volume":"242","author":"Eckardt","year":"2025","journal-title":"Klin. Monbl. Augenheilkd."},{"key":"10.1016\/j.xcrm.2026.102969_bib5","doi-asserted-by":"crossref","first-page":"1139","DOI":"10.3390\/bioengineering11111139","article-title":"Performance of a deep learning system and performance of optometrists for the detection of glaucomatous optic neuropathy using colour retinal photographs","volume":"11","author":"Jan","year":"2024","journal-title":"Bioengineering"},{"key":"10.1016\/j.xcrm.2026.102969_bib6","doi-asserted-by":"crossref","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":"10.1016\/j.xcrm.2026.102969_bib7","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","article-title":"Multimodal biomedical AI","volume":"28","author":"Acosta","year":"2022","journal-title":"Nat. Med."},{"key":"10.1016\/j.xcrm.2026.102969_bib8","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.survophthal.2025.07.003","article-title":"Multimodal artificial intelligence in ophthalmology: Applications, challenges, and future directions","volume":"71","author":"Jin","year":"2026","journal-title":"Surv. Ophthalmol."},{"key":"10.1016\/j.xcrm.2026.102969_bib9","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"Preprint at. arXiv"},{"key":"10.1016\/j.xcrm.2026.102969_bib10","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.xcrm.2026.102969_bib11","doi-asserted-by":"crossref","first-page":"57","DOI":"10.3390\/informatics11030057","article-title":"Large language models in healthcare and medical domain: a review","volume":"11","author":"Nazi","year":"2024","journal-title":"Informatics"},{"key":"10.1016\/j.xcrm.2026.102969_bib12","doi-asserted-by":"crossref","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":"10.1016\/j.xcrm.2026.102969_bib13","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102969_bib14","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1097\/JCMA.0000000000001273","article-title":"Evaluating GPT-4\u2019s visual interpretation and clinical reasoning on emergency settings: A 5-year analysis","volume":"88","author":"Wang","year":"2025","journal-title":"J. Chin. Med. Assoc."},{"key":"10.1016\/j.xcrm.2026.102969_bib15","article-title":"Capabilities of GPT-4 on medical challenge problems","author":"Nori","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102969_bib16","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1038\/s41586-024-07618-3","article-title":"A multimodal generative AI copilot for human pathology","volume":"634","author":"Lu","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.xcrm.2026.102969_bib17","doi-asserted-by":"crossref","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":"10.1016\/j.xcrm.2026.102969_bib18","doi-asserted-by":"crossref","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":"10.1016\/j.xcrm.2026.102969_bib19","doi-asserted-by":"crossref","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":"10.1016\/j.xcrm.2026.102969_bib20","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1016\/j.ccell.2022.09.012","article-title":"Artificial intelligence for multimodal data integration in oncology","volume":"40","author":"Lipkova","year":"2022","journal-title":"Cancer Cell"},{"key":"10.1016\/j.xcrm.2026.102969_bib21","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","author":"Lewis","year":"2020","journal-title":"Proc. Adv. NeurIPS"},{"key":"10.1016\/j.xcrm.2026.102969_bib22","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1038\/s41746-025-01802-z","article-title":"Retrieval-augmented generation elevates local LLM quality in radiology contrast media consultation","volume":"8","author":"Wada","year":"2025","journal-title":"npj Digit. Med."},{"key":"10.1016\/j.xcrm.2026.102969_bib23","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1038\/s41746-025-01519-z","article-title":"Retrieval augmented generation for 10 large language models and its generalizability in assessing medical fitness","volume":"8","author":"Ke","year":"2025","journal-title":"npj Digit. Med."},{"key":"10.1016\/j.xcrm.2026.102969_bib24","article-title":"Almanac\u2014retrieval-augmented language models for clinical medicine","volume":"1","author":"Zakka","year":"2024","journal-title":"NEJM"},{"key":"10.1016\/j.xcrm.2026.102969_bib25","article-title":"ReAct: Synergizing reasoning and acting in language models","author":"Yao","year":"2022","journal-title":"arXiv."},{"key":"10.1016\/j.xcrm.2026.102969_bib26","doi-asserted-by":"crossref","first-page":"1603","DOI":"10.1038\/s41467-024-45879-8","article-title":"Large language models streamline automated machine learning for clinical studies","volume":"15","author":"Tayebi Arasteh","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.xcrm.2026.102969_bib27","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1038\/s43018-025-00991-6","article-title":"Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology","volume":"6","author":"Ferber","year":"2025","journal-title":"Nat. Cancer"},{"key":"10.1016\/j.xcrm.2026.102969_bib28","doi-asserted-by":"crossref","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":"10.1016\/j.xcrm.2026.102969_bib29","doi-asserted-by":"crossref","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":"10.1016\/j.xcrm.2026.102969_bib30","doi-asserted-by":"crossref","DOI":"10.3389\/fcell.2025.1642539","article-title":"Multimodal reasoning agent for enhanced ophthalmic decision-making: a preliminary real-world clinical validation","volume":"13","author":"Zhuang","year":"2025","journal-title":"Front. Cell Dev. Biol."},{"key":"10.1016\/j.xcrm.2026.102969_bib31","first-page":"4641","article-title":"EyeAgent: A Large Language Model-Based AI Agent for Multimodal Multitask Ophthalmology Analyses","volume":"66","author":"Chen","year":"2025","journal-title":"Investigative Ophthalmology & Visual Science"},{"key":"10.1016\/j.xcrm.2026.102969_bib32","article-title":"PathVQA: 30000+ questions for medical visual question answering","author":"He","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102969_bib33","article-title":"Proposal for a regulation of the european parliament and of the council laying down harmonised rules on artificial intelligence (artificial intelligence act) and amending certain union legislative acts","year":"2021","journal-title":"Technical Report"},{"key":"10.1016\/j.xcrm.2026.102969_bib34","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1038\/s41698-024-00517-w","article-title":"New regulatory thinking is needed for AI-based personalised drug and cell therapies in precision oncology","volume":"8","author":"Derraz","year":"2024","journal-title":"npj Precis. Oncol."},{"key":"10.1016\/j.xcrm.2026.102969_bib35","doi-asserted-by":"crossref","first-page":"2757","DOI":"10.18653\/v1\/2025.emnlp-main.138","article-title":"From generation to judgment: Opportunities and challenges of llm-as-a-judge","author":"Li","year":"2025","journal-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing"},{"key":"10.1016\/j.xcrm.2026.102969_bib36","article-title":"Human Evaluators vs. LLM-as-a-Judge: Toward Scalable, Real-Time Evaluation of GenAI in Global Health","author":"Williams","year":"2025","journal-title":"medRxiv"},{"key":"10.1016\/j.xcrm.2026.102969_bib37","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"Proc. Adv. NeurIPS"},{"key":"10.1016\/j.xcrm.2026.102969_bib38","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102969_bib39","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.xcrm.2026.102969_bib40","article-title":"Qwen3 technical report","author":"Yang","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102969_bib41","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-025-02300-y","article-title":"Grounded report generation for enhancing ophthalmic ultrasound interpretation using Vision-Language Segmentation models","volume":"9","author":"Jin","year":"2026","journal-title":"npj Digit. Med."},{"key":"10.1016\/j.xcrm.2026.102969_bib42","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"10.1016\/j.xcrm.2026.102969_bib44","article-title":"Glm-4.5: Agentic, reasoning, and coding (arc) foundation models","author":"Zeng","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102969_bib45","article-title":"Gemini: a family of highly capable multimodal models","author":"Anil","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102969_bib47","doi-asserted-by":"crossref","first-page":"276","DOI":"10.11613\/BM.2012.031","article-title":"Interrater reliability: the kappa statistic","volume":"22","author":"McHugh","year":"2012","journal-title":"Biochem. Med."}],"container-title":["Cell Reports Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666379126003861?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666379126003861?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T00:27:10Z","timestamp":1793060830000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666379126003861"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":45,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["S2666379126003861"],"URL":"https:\/\/doi.org\/10.1016\/j.xcrm.2026.102969","relation":{},"ISSN":["2666-3791"],"issn-type":[{"value":"2666-3791","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An autonomous multimodal AI agent for evidence-grounded ophthalmic diagnosis","name":"articletitle","label":"Article Title"},{"value":"Cell Reports Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.xcrm.2026.102969","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"102969"}}