Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Aug 28.
doi: 10.1038/s41591-025-03900-7. Online ahead of print.

An eyecare foundation model for clinical assistance: a randomized controlled trial

Yilan Wu #  1   2 Bo Qian #  3   4   5 Tingyao Li #  3   4 Yiming Qin #  1   2   3   4 Zhouyu Guan #  3 Tingli Chen #  6 Yali Jia #  7   8 Ping Zhang #  9   10 Dian Zeng #  1   2 Sayoko Moroi  11 Rajiv Raman  12 Benjamin Sommer Thinggaard  13   14 Frederik Pedersen  13 José Alogo Obiang Ñehe  15 Tengku Ain Kamalden  16   17 Yukun Zhou  18   19 Yixiao Jin  1 Huating Li  3 An Ran Ran  20 Dawei Yang  20 Ziyao Meng  3   4 Qingsheng Peng  21   22 Ying Feng Zheng  23 Dingqiao Wang  24 Hongwei Ji  1   2 Pengxiao Zang  7   8 Changchang Yin  9   10 Jie Shen  25 Youxin Chen  26   27   28 Weihong Yu  26   27   28 Rongping Dai  27   28 Chenxi Zhang  21   26   27   28 Xinyu Zhao  26   27   28 Xiangning Wang  29 Yan Chen  29 Qiang Wu  29 Hongbin Xie  30 Simon K H Szeto  20 Julia Y Y Chan  20 Victor T T Chan  20 Hua-Tao Xie  31 Ruili Wei  32 Jin Li  33 Weizhi Ma  34 Lei Zhu  35   36 Hongqiu Wang  35 Huazhu Fu  37 Wenxiao Wang  38 Shan Lin  39 Zejun Xu  39 Nian Guan  39 Xiao Zhang  40 Andrzej Grzybowski  41   42 Monika Gołębiowska-Bogaj  43 Maciej Gawęcki  43 Adrian Smedowski  44   45   46 Wojciech Szaraniec  47   48 You Wu  49   50 Yang Wen  51 Xiang Chen  3   4 Yuanqi Yao  3   4 EyeFM Global Reader Study TeamLee-Ling Lim  52   53   54 Carol Y Cheung  21 Gavin Siew Wei Tan  22 Jakob Grauslund  14 Paisan Ruamviboonsuk  55 Sobha Sivaprasad  19   20 Pearse A Keane  19   20 Ya Xing Wang  1 Yih-Chung Tham  21   22   56 Ching-Yu Cheng  21   22 Tien Yin Wong  57   58   59   60 Bin Sheng  61   62
Collaborators, Affiliations

An eyecare foundation model for clinical assistance: a randomized controlled trial

Yilan Wu et al. Nat Med. .

Abstract

In the context of an increasing need for clinical assessments of foundation models, we developed EyeFM, a multimodal vision-language eyecare copilot, and conducted a multifaceted evaluation, including retrospective validations, multicountry efficacy validation as a clinical copilot and a double-masked randomized controlled trial (RCT). EyeFM was pretrained on 14.5 million ocular images from five imaging modalities paired with clinical texts from global, multiethnic datasets. Efficacy validation invited 44 ophthalmologists across North America, Europe, Asia and Africa in primary and specialty care settings, highlighting its utility as a clinical copilot. The RCT-a parallel, single-center, double-masked study-assessed EyeFM as a clinical copilot in retinal disease screening among a high-risk population in China. A total of 668 participants (mean age 57.5 years, 79.5% male) were randomized to 16 ophthalmologists, equally allocated into intervention (with EyeFM copilot) and control (standard care) groups. The primary endpoint indicated that ophthalmologists with EyeFM copilot achieved higher correct diagnostic rate (92.2% versus 75.4%, P < 0.001) and referral rate (92.2% versus 80.5%, P < 0.001). Secondary outcome indicated improved standardization score of clinical reports (median 33 versus 37, P < 0.001). Participant satisfaction with the screening was similar between groups, whereas the intervention group demonstrated higher compliance with self-management (70.1% versus 49.1%, P < 0.001) and referral suggestions (33.7% versus 20.2%, P < 0.001) at follow-up. Post-deployment evaluations indicated strong user acceptance. Our study provided evidence that implementing EyeFM copilot can improve the performance of ophthalmologists and the outcome of patients. Chinese Clinical Trial Registry registration: ChiCTR2500095518 .

PubMed Disclaimer

Conflict of interest statement

Competing interests: Y.J. is a patent holder of Optovue/Visionix, Inc., Optos plc and Genentech, Inc. She receives financial support from Genentech, Inc., and she receives financial compensation from Optovue/Visionix, Inc. and Genentech, Inc. P.A.K. is a co-founder of Cascader Ltd., has acted as a consultant for Retina Consultants of America, Roche, Boehringer Ingleheim and Bitfount and is an equity owner in Big Picture Medical. He has received speaker fees from Zeiss, Thea, Apellis and Roche. He has received travel support from Bayer and Roche. He has attended advisory boards for Topcon, Bayer, Boehringer Ingleheim and Roche. T.Y.W. is a consultant for AbbVie Pte Ltd., Aldropika Therapeutics, Bayer, Boehringer Ingelheim, Zeiss, Genentech, Iveric Bio, Novartis, Opthea Limited, Plano, Quaerite Biopharm Research Ltd., Roche, Sanofi and Shanghai Henlius. He is an inventor, holds patents and is a co-founder of start-up companies EyRiS and Visre, which have interests in, and develop digital solutions for, eye diseases. All potential conflicts of interests for consultancy, advisory boards and positions in the start-up companies and financial renumeration, if any, are managed by institutional policies under SingHealth and Tsinghua University. The other authors declare no competing interests.

References

    1. Zhou, Y. et al. A foundation model for generalizable disease detection from retinal images. Nature 622, 156–163 (2023). - PubMed - PMC
    1. Chen, R. J. et al. Towards a general-purpose foundation model for computational pathology. Nat. Med. 30, 850–862 (2024). - PubMed - PMC
    1. Lu, M. Y. et al. A visual-language foundation model for computational pathology. Nat. Med. 30, 863–874 (2024). - PubMed - PMC
    1. Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44–56 (2019). - PubMed
    1. Tanno, R. et al. Collaboration between clinicians and vision–language models in radiology report generation. Nat. Med. 31, 599–608 (2025). - PubMed

LinkOut - more resources