Evidence map›Paper›PMID 41349528›Full record

ArticleCell reports. Medicine2025

An integrated language-vision foundation model for conversational diagnostics and triaging in primary eye care.

Zhi Da Soh, Yang Bai, Kai Yu, Yang Zhou, Xiaofeng Lei, Sahil Thakur, Zann Lee, Lee Ching Linette Phang, Qingsheng Peng, Can Can Xue and 21 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in Cell reports. Medicine, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 3 papers, 1 of them a synthesis that pooled it.

0numbers the graph read from it
0cells of the map it votes in
3citing papers in PubMed, 1 pooled it
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

3 citing papers in PubMed, 1 synthesis or guideline pooled it.

  1. Pooled it
  2. Current Trends in AI and Eye Disease Diagnostics.Ophthalmic & physiological optics : the journal of the British College of Ophthalmic Opticians (Optometrists) · 2026
    Review
  3. Article
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

31 authors.

Zhi Da SohSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore.
Yang BaiInstitute of High Performance Computing, Agency of Science, Technology and Research, 1 Fusionopolis Way, Singapore 138632, Singapore.
Kai YuDepartment of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA.
Yang ZhouInstitute of High Performance Computing, Agency of Science, Technology and Research, 1 Fusionopolis Way, Singapore 138632, Singapore.
Xiaofeng LeiInstitute of High Performance Computing, Agency of Science, Technology and Research, 1 Fusionopolis Way, Singapore 138632, Singapore.
Sahil ThakurSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore.
Zann LeeSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore.
Lee Ching Linette PhangSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore.
Qingsheng PengSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore.
Can Can XueSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore.
Rachel Shujuan ChongSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore; Ophthalmology & Visual Sciences Academic Clinical Program, Duke-NUS Medical School, 8 College Road, Singapore 169857, Singapore.
Quan V HoangSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore; Ophthalmology & Visual Sciences Academic Clinical Program, Duke-NUS Medical School, 8 College Road, Singapore 169857, Singapore; Department of Ophthalmology, Columbia University, New York, 622 W 168(th) Street, 3(rd) Floor, New York, NY 10032, USA; Department of Ophthalmology, National University of Singapore, 1E Kent Ridge Road, NUHS Tower Block, Level 7, Singapore 119228, Singapore.
Lavanya RaghavanSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore.
Yih Chung ThamSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore; Centre for Innovation and Precision Eye Health, National University of Singapore, 1E Kent Ridge Road, NUHS Tower Block, Level 7, Singapore 119228, Singapore.
Charumathi SabanayagamSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore; Ophthalmology & Visual Sciences Academic Clinical Program, Duke-NUS Medical School, 8 College Road, Singapore 169857, Singapore.
Wei-Chi WuDepartment of Ophthalmology, Chang Gung Memorial Hospital, Linkou Medical Centre, Taoyuan, No. 123, Dapi Rd., Niaosong District, Kaohsiung City 83301, Taiwan; College of Medicine, Chang Gung University, Taoyuan, No 259, Wenhua 1(st) Road, Guishan District, 333, Taoyuan, Taiwan.
Ming-Chih HoDepartment of Ophthalmology, Chang Gung Memorial Hospital, Linkou Medical Centre, Taoyuan, No. 123, Dapi Rd., Niaosong District, Kaohsiung City 83301, Taiwan; College of Medicine, Chang Gung University, Taoyuan, No 259, Wenhua 1(st) Road, Guishan District, 333, Taoyuan, Taiwan.
Jiangnan HeShanghai Eye Disease Prevention & Treatment Center, Shanghai Eye Hospital, No. 1440, Hongqiao Road, Changning District, Shanghai, China.
Preeti GuptaSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore.
Ecosse LamoureuxSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore; Duke-NUS Medical School, National University of Singapore, 8 College Road, Singapore 169857, Singapore.
Seang Mei SawSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore.
Vinay NangiaSuraj Eye Institute, Plot No. 559, New Colony, Nagpur, Maharashtra 440001, India.
Songhomitra Panda-JonasPrivatpraxis Prof Jonas and Dr. Panda-Jonas, Adenauerplatz 2, 69115 Heidelberg, Germany; Department of Ophthalmology, Medical Faculty Heidelberg, Heidelberg University, Grabengasse 1, 69117 Heidelberg, Germany.
Jie XuBeijing Institute of Ophthalmology, Beijing Tongren Hospital, Capital Medical University, Fengtai District, Beijing 100054, China.
Ya Xing WangBeijing Visual Science and Translational Eye Research Institute, Beijing Tsinghua Changgung Hospital, Tsinghua Medicine, Tsinghua University, 30 Shuangqing Road, Haidian District, Beijing 100190, China; Beijing Institute of Ophthalmology, Beijing Tongren Hospital, Capital Medical University, Fengtai District, Beijing 100054, China.
Xinxing XuInstitute of High Performance Computing, Agency of Science, Technology and Research, 1 Fusionopolis Way, Singapore 138632, Singapore.
Jost B JonasSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore; Rothschild Foundation Hospital, Institut Français de Myopie, 25-29 Rue Manin, 75019 Paris, France; Privatpraxis Prof Jonas and Dr. Panda-Jonas, Adenauerplatz 2, 69115 Heidelberg, Germany; Beijing Visual Science and Translational Eye Research Institute, Beijing Tsinghua Changgung Hospital, Tsinghua Medicine, Tsinghua University, 30 Shuangqing Road, Haidian District, Beijing 100190, China; New York Eye and Ear Infirmary of Mount Sinai, Icahn School of Medicine at Mount Sinai, 1 Gustave L. Levy PI, New York, NY 10029, USA.
Tien Yin WongSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore; Beijing Visual Science and Translational Eye Research Institute, Beijing Tsinghua Changgung Hospital, Tsinghua Medicine, Tsinghua University, 30 Shuangqing Road, Haidian District, Beijing 100190, China.
Rick Siow Mong GohInstitute of High Performance Computing, Agency of Science, Technology and Research, 1 Fusionopolis Way, Singapore 138632, Singapore.
Yong LiuInstitute of High Performance Computing, Agency of Science, Technology and Research, 1 Fusionopolis Way, Singapore 138632, Singapore.
Ching-Yu ChengSingapore Eye Research Institute, Singapore National Eye Centre, 20 College Road, Singapore 169856, Singapore; Ophthalmology & Visual Sciences Academic Clinical Program, Duke-NUS Medical School, 8 College Road, Singapore 169857, Singapore; Centre for Innovation and Precision Eye Health, National University of Singapore, 1E Kent Ridge Road, NUHS Tower Block, Level 7, Singapore 119228, Singapore; Department of Ophthalmology, National University of Singapore, 1E Kent Ridge Road, NUHS Tower Block, Level 7, Singapore 119228, Singapore. Electronic address: chingyu.cheng@nus.edu.sg.

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

We present Meta-EyeFM, an integrated language-vision foundation model designed for conversational diagnostics and triaging in primary eye care. By combining a large language model (LLM) with eight task-specific vision foundation models (VFMs), Meta-EyeFM dynamically routes user queries and fundus photographs to the most appropriate VFMs (accuracy 96.8%). It demonstrates high performance in detecting ocular diseases (area under the receiver operating curve [AUC] ≥91.2%), differentiating disease severity (AUC ≥82%), identifying ocular signs (AUC ≥77.9%), and predicting systemic conditions like diabetes (AUC ≥79.8%). Meta-EyeFM is 11%-43% more accurate than Gemini-1.5-flash and GPT-4o LLM and generally outperforms junior ophthalmologist and optometrist graders in detecting different eye diseases. Its conversational interface and robust generalizability support its role as a diagnostic decision support tool in community settings. Through self-supervised learning and a user-friendly platform, Meta-EyeFM addresses the scarcity of skilled eye care professionals, offering scalable, explainable AI for enhancing vision screening and disease triage globally.

Indexed as

Eye DiseasesLanguagePrimary Health CareTriageHumansROC Curveartificial intelligencedeep learningdiagnostic decision support toolfoundation modellarge language modelophthalmologyself-supervised learning modelvision language model

Identifiers

PMID41349528
PMCPMC12765825

What OpenQuestion holds

Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.