Review

. 2023 Dec;5(12):e917-e924.

doi: 10.1016/S2589-7500(23)00201-7.

Large language models and their impact in ophthalmology

Bjorn Kaijun Betzler¹, Haichao Chen², Ching-Yu Cheng³, Cecilia S Lee⁴, Guochen Ning⁵, Su Jeong Song⁶, Aaron Y Lee⁴, Ryo Kawasaki⁷, Peter van Wijngaarden⁸, Andrzej Grzybowski⁹, Mingguang He¹⁰, Dawei Li¹¹, An Ran Ran¹², Daniel Shu Wei Ting¹³, Kelvin Teo¹³, Paisan Ruamviboonsuk¹⁴, Sobha Sivaprasad¹⁵, Varun Chaudhary¹⁶, Ramin Tadayoni¹⁷, Xiaofei Wang¹⁸, Carol Y Cheung¹², Yingfeng Zheng¹⁹, Ya Xing Wang²⁰, Yih Chung Tham²¹, Tien Yin Wong²²

Affiliations

¹ Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
² Tsinghua Medicine, Tsinghua University, Beijing, China.
³ Centre for Innovation and Precision Eye Health, National University of Singapore, Singapore; Department of Ophthalmology, National University of Singapore, Singapore; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore; Ophthalmology and Visual Science Academic Clinical Program, Duke-NUS Medical School, Singapore.
⁴ University of Washington School of Medicine, Department of Ophthalmology, Seattle, WA, USA.
⁵ Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China.
⁶ Department of Ophthalmology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, South Korea.
⁷ Division of Public Health, Department of Social Medicine, Graduate School of Medicine, Osaka University, Osaka, Japan; Artificial Intelligence Center for Medical Research and Application, Osaka University Hospital, Osaka, Japan.
⁸ Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Melbourne, VA, Australia; Ophthalmology, University of Melbourne Department of Surgery, East Melbourne, Melbourne, VA, Australia.
⁹ Institute for Research in Ophthalmology, Foundation for Ophthalmology Development, Poznan, Poland.
¹⁰ Hong Kong Polytechnic University, Hong Kong Special Administrative Region, China.
¹¹ College of Future Technology, Peking University, Beijing, China.
¹² Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong Special Administrative Region, China.
¹³ Singapore Eye Research Institute, Singapore National Eye Centre, Singapore; Ophthalmology and Visual Science Academic Clinical Program, Duke-NUS Medical School, Singapore.
¹⁴ Department of Ophthalmology, Rajavithi Hospital, Bangkok, Thailand.
¹⁵ NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital, London, UK.
¹⁶ Department of Surgery, McMaster University, Hamilton, ON, Canada.
¹⁷ Université Paris Cité, AP-HP, Lariboisière, Saint Louis, and Rothschild Foundation Hospitals, Paris, France.
¹⁸ Key Laboratory for Biomechanics and Mechanobiology of Ministry of Education, Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China.
¹⁹ State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China; Guangzhou Regenerative Medicine and Health Guangdong Laboratory, Guangzhou, China.
²⁰ Beijing Institute of Ophthalmology, Beijing Ophthalmology and Visual Science Key Lab, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
²¹ Centre for Innovation and Precision Eye Health, National University of Singapore, Singapore; Department of Ophthalmology, National University of Singapore, Singapore; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore; Ophthalmology and Visual Science Academic Clinical Program, Duke-NUS Medical School, Singapore. Electronic address: thamyc@nus.edu.sg.
²² Tsinghua Medicine, Tsinghua University, Beijing, China; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.

PMID: 38000875
PMCID: PMC11003328
DOI: 10.1016/S2589-7500(23)00201-7

Review

Large language models and their impact in ophthalmology

Bjorn Kaijun Betzler et al. Lancet Digit Health. 2023 Dec.

. 2023 Dec;5(12):e917-e924.

doi: 10.1016/S2589-7500(23)00201-7.

Authors

Affiliations

¹ Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
² Tsinghua Medicine, Tsinghua University, Beijing, China.
³ Centre for Innovation and Precision Eye Health, National University of Singapore, Singapore; Department of Ophthalmology, National University of Singapore, Singapore; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore; Ophthalmology and Visual Science Academic Clinical Program, Duke-NUS Medical School, Singapore.
⁴ University of Washington School of Medicine, Department of Ophthalmology, Seattle, WA, USA.
⁵ Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China.
⁶ Department of Ophthalmology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, South Korea.
⁷ Division of Public Health, Department of Social Medicine, Graduate School of Medicine, Osaka University, Osaka, Japan; Artificial Intelligence Center for Medical Research and Application, Osaka University Hospital, Osaka, Japan.
⁸ Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Melbourne, VA, Australia; Ophthalmology, University of Melbourne Department of Surgery, East Melbourne, Melbourne, VA, Australia.
⁹ Institute for Research in Ophthalmology, Foundation for Ophthalmology Development, Poznan, Poland.
¹⁰ Hong Kong Polytechnic University, Hong Kong Special Administrative Region, China.
¹¹ College of Future Technology, Peking University, Beijing, China.
¹² Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong Special Administrative Region, China.
¹³ Singapore Eye Research Institute, Singapore National Eye Centre, Singapore; Ophthalmology and Visual Science Academic Clinical Program, Duke-NUS Medical School, Singapore.
¹⁴ Department of Ophthalmology, Rajavithi Hospital, Bangkok, Thailand.
¹⁵ NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital, London, UK.
¹⁶ Department of Surgery, McMaster University, Hamilton, ON, Canada.
¹⁷ Université Paris Cité, AP-HP, Lariboisière, Saint Louis, and Rothschild Foundation Hospitals, Paris, France.
¹⁸ Key Laboratory for Biomechanics and Mechanobiology of Ministry of Education, Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China.
¹⁹ State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China; Guangzhou Regenerative Medicine and Health Guangdong Laboratory, Guangzhou, China.
²⁰ Beijing Institute of Ophthalmology, Beijing Ophthalmology and Visual Science Key Lab, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
²¹ Centre for Innovation and Precision Eye Health, National University of Singapore, Singapore; Department of Ophthalmology, National University of Singapore, Singapore; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore; Ophthalmology and Visual Science Academic Clinical Program, Duke-NUS Medical School, Singapore. Electronic address: thamyc@nus.edu.sg.
²² Tsinghua Medicine, Tsinghua University, Beijing, China; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.

PMID: 38000875
PMCID: PMC11003328
DOI: 10.1016/S2589-7500(23)00201-7

Abstract

The advent of generative artificial intelligence and large language models has ushered in transformative applications within medicine. Specifically in ophthalmology, large language models offer unique opportunities to revolutionise digital eye care, address clinical workflow inefficiencies, and enhance patient experiences across diverse global eye care landscapes. Yet alongside these prospects lie tangible and ethical challenges, encompassing data privacy, security, and the intricacies of embedding large language models into clinical routines. This Viewpoint highlights the promising applications of large language models in ophthalmology, while weighing up the practical and ethical barriers towards their real-world implementation. This Viewpoint seeks to stimulate broader discourse on the potential of large language models in ophthalmology and to galvanise both clinicians and researchers into tackling the prevailing challenges and optimising the benefits of large language models while curtailing the associated risks.

PubMed Disclaimer

Conflict of interest statement

Declaration of interests PvW declares financial interests as a cofounder of Enlighten Imaging, an early-stage medical technology start-up company devoted to hyperspectral retinal imaging and image analysis, including the development of artificial intelligence systems; research grant support from Roche and Bayer; and honoraria from Roche, Bayer, Novartis, and Mylan. RT declares consulting fees from Novartis, AbbVie, Allergan, Bayer, Alcon, Roche Genentech, Thea, Apellis, Iveric Bio, and Oculis; honoraria from Optic 2000; support for attending meetings from Novartis, AbbVie, Allergan, and Bayer; participation on advisory boards for Novartis, AbbVie, Allergan, Bayer, Apellis, Iveric Bio, Oculis, and Roche Genentech; a leadership role as the President Elect of Euretina; stock in Oculis; and equipment and materials from Zeiss. SS declares grants from Bayer and Boehringer Ingleheim; consulting fees from Roche, AbbVie, Apellis, Bayer, Biogen, Boehringer Ingelheim, Novartis, Janssen Pharmaceuticals, Optos, Ocular Therapeutix, and OcuTerra; support for attending meetings and travel from Bayer and Roche; participation on data safety monitoring boards or advisory boards for Novo Nordisk and Bayer; leadership in RCOphth, Macular Society, and Editor of EYE; stock in Eyebiotech; and equipment and materials from Boehringer Ingleheim. AYL reports grants to their affiliated institutions from Santen, Novartis, Carl Zeiss Meditec, Microsoft, NVIDIA, the National Institutes of Health (NIH; grant numbers NIH/NEI K23EY029246 and NIH OT2OD032644), Research to Prevent Blindness, and the Latham Vision Innovation Award. AYL reports consulting fees from USDA, Genentech, Verana Health, Johnson & Johnson, Gyroscope, Janssen Research and Development, and Regeneron; payment for lectures from Topcon; and payment from Alcon Research for various educational events and activities. ARR declares a grant from the Health and Medical Research Fund (grant number 19201991). CSL reports grants to their institution from the NIH (grant numbers NIH/NIA R01AG060942, NIH/NIA U19AG066567, and NIH OT2OD032644), Research to Prevent Blindness, and the Latham Vision Innovation Award; and consulting fees from Boehringer Ingelheim. TYW declares consulting fees from Aldropika Therapeutics, Bayer, Boehringer Ingelheim, Genentech, Iveric Bio, Novartis, Plano, Oxurion, Roche, Sanofi, and Shanghai Henlius; funding from the National Key R&D Program, China (grant number 2022YFC2502800); and being an inventor, patent holder, and cofounder of the start-up companies EyRiS and Visre. All other authors declare no competing interests.

Figures

**Figure 1.**
Outline of the current clinical workflow in tertiary eye centres

**Figure 2**
Use of ChatGPT to enhance delivery of patient-centric health services.

**Figure 3**
Use of ChatGPT to enhance efficiency in medical record documentation.

**Figure 4.**
Use of ChatGPT to facilitate medical education and learning.

See this image and copyright information in PMC

References

1. OpenAI. GPT-4 Technical Report2023 March 01, 2023:[arXiv:2303.08774 p.]. Available from: https://ui.adsabs.harvard.edu/abs/2023arXiv230308774O.
1. Touvron H, Lavril T, Izacard G, Martinet X, Lachaux M-A, Lacroix T, et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:230213971. 2023.
1. Chowdhery A, Narang S, Devlin J, Bosma M, Mishra G, Roberts A, et al. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:220402311. 2022.
1. Scao TL, Fan A, Akiki C, Pavlick E, Ilić S, Hesslow D, et al. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:221105100. 2022.
1. Hoffmann J, Borgeaud S, Mensch A, Buchatskaya E, Cai T, Rutherford E, et al. Training compute-optimal large language models. arXiv preprint arXiv:220315556. 2022.

Publication types

Actions
Actions
Actions

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions

Grants and funding

LinkOut - more resources

Full Text Sources

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Large language models and their impact in ophthalmology

Affiliations

Large language models and their impact in ophthalmology

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

References

Publication types

MeSH terms

Grants and funding

LinkOut - more resources

Full Text Sources