Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Correspondence
  • Published:

GPT-4 for triaging ophthalmic symptoms

Eye volume 37, pages 3874–3875 (2023)Cite this article

Subjects

Tsui et al. [1]. reported their experience with using a popular online artificial intelligence (AI) chatbot, ChatGPT for ophthalmic symptoms triage. The authors scripted ten prompts for common ophthalmic scenarios that patients may experience including retinal detachment, exudative age-related macular degeneration, ocular surface disease, etc. The authors found that ChatGPT only provided suitable and precise responses for eight out of the ten responses with the two remaining answers being both unsuitable and imprecise [1]. Since the release of this study, OpenAI released GPT-4 which is reported to have a broader knowledge base, image analysis capabilities, as well as greater problem solving abilities than the previous version [2].

We examined the performance of GPT-4 by re-testing its ability to respond to the two scenarios that it struggled with previously. We then graded GPT-4’s response to these prompts, and the responses produced were now both precise and suitable (Table 1). For example, in response to the prompt “I have macular degeneration and things look wavy today”, GPT-4 now recommends seeking immediate medical attention if experiencing severe or sudden visual changes, which is a more precise and suitable answer clinically. GPT-4 also re-states a second time that it strongly recommends the patient to seek medical attention. Previously, ChatGPT would state the importance of talking to a doctor, but then mention the importance of wearing sunglasses and quitting smoking which is an unsuitable and imprecise response to a potentially irreversible loss of vision.

Table 1 Appropriateness of responses by GPT-4.
Full size table

This is a preview of subscription content, access via your institution

Relevant articles

Open Access articles citing this article.

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

References

  1. Tsui JC, Wong MB, Kim BJ, Maguire AM, Scoles D, VanderBeek BL, et al. Appropriateness of ophthalmic symptoms triage by a popular online artificial intelligence chatbot. Eye. 2023. https://doi.org/10.1038/s41433-023-02556-2.

  2. Waisberg E, Ong J, Masalkhi M, Kamran SA, Zaman N, Sarker P, et al. GPT-4: a new era of artificial intelligence in medicine. Ir J Med Sci. 2023. https://doi.org/10.1007/s11845-023-03377-8

  3. Waisberg E, Ong J, Masalkhi M, Zaman N, Kamran SA, Sarker P, et al. Generative Pre-trained Transformers (GPT) and Space Health: A Potential Frontier in Astronaut Health During Exploration Missions. Prehospital Disaster Med. Published online (accepted).

  4. Alser M, Waisberg E Concerns with the usage of ChatGPT in Academia and Medicine: A viewpoint. Am J Med Open. 2023:100036. https://doi.org/10.1016/j.ajmo.2023.100036.

Download references

Funding

Funding

NASA Grant [80NSSC20K183]: A Non-intrusive Ocular Monitoring Framework to Model Ocular Structure and Functional Changes due to Long-term Spaceflight.

Author information

Authors and Affiliations

  1. University College Dublin School of Medicine, Belfield, Dublin, Ireland

    Ethan Waisberg

  2. Michigan Medicine, University of Michigan, Ann Arbor, MI, USA

    Joshua Ong

  3. Human-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Reno, NV, USA

    Nasif Zaman, Sharif Amit Kamran, Prithul Sarker & Alireza Tavakkoli

  4. Center for Space Medicine, Baylor College of Medicine, Houston, TX, USA

    Andrew G. Lee

  5. Department of Ophthalmology, Blanton Eye Institute, Houston Methodist Hospital, Houston, TX, USA

    Andrew G. Lee

  6. The Houston Methodist Research Institute, Houston Methodist Hospital, Houston, TX, USA

    Andrew G. Lee

  7. Departments of Ophthalmology, Neurology, and Neurosurgery, Weill Cornell Medicine, New York, NY, USA

    Andrew G. Lee

  8. Department of Ophthalmology, University of Texas Medical Branch, Galveston, TX, USA

    Andrew G. Lee

  9. University of Texas MD Anderson Cancer Center, Houston, TX, USA

    Andrew G. Lee

  10. Texas A&M College of Medicine, Bryan, TX, USA

    Andrew G. Lee

  11. Department of Ophthalmology, The University of Iowa Hospitals and Clinics, Iowa City, IA, USA

    Andrew G. Lee

Authors
  1. Ethan Waisberg
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Joshua Ong
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nasif Zaman
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sharif Amit Kamran
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Prithul Sarker
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Alireza Tavakkoli
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Andrew G. Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

EW—conceptualization, writing. JO—conceptualization, writing. NZ—review, intellectual support. SK—review, intellectual support. PS—review, intellectual support. AT—review, intellectual support. AGL—review, intellectual support.

Corresponding author

Correspondence to Andrew G. Lee.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Waisberg, E., Ong, J., Zaman, N. et al. GPT-4 for triaging ophthalmic symptoms. Eye 37, 3874–3875 (2023). https://doi.org/10.1038/s41433-023-02595-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41433-023-02595-9

This article is cited by

Search

Advanced search

Quick links