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.

  • Comment
  • Published:

GPT-4 to document ophthalmic post-operative complications

Eye volume 38, pages 414–415 (2024)Cite this article

Subjects

ChatGPT, created by OpenAI, is an advanced AI chatbot that utilizes the GPT-4 (Generative Pre-trained Transformer 4) large language model [1]. Large language models (LLMs) have been developed to produce responses that resemble human language in response to inputs in natural language [1]. Utilizing deep learning methodologies, ChatGPT has the capacity to comprehend and evaluate extensive quantities of textual information, thereby enabling it to produce responses that are contextually and logically consistent, stretching a wide variety of topics [1]. The transformer architecture utilized in ChatGPT enables the model to effectively identify patterns within words and phrases, allowing it to predict the subsequent content in a given context [1]. As part of its training, the model is presented with extensive quantities of data in order to develop its own hypotheses regarding linguistic structures, without any supervision [1]. Subsequently, in the fine-tuning stage, the model’s underlying assumptions are rectified and enhanced through the utilization of structured and labeled data that has been moderated by humans [1].

ChatGPT can aid users in retrieving information, responding to inquiries, and participating in interactive dialogs across diverse domains [2]. ChatGPT exhibits promising potential to support professionals in clinical and laboratory diagnosis, deliver timely information regarding medical advancements, and function as a virtual assistant to assist patients in effectively managing their health [3]. ChatGPT can also potentially be used to help write operating notes. While AI generated operating notes could potentially result in errors, traditional operative notes are not immune from errors and should be carefully reviewed by the operating surgeon. Future research will need to be conducted in this area for a definitive answer on error rates in AI-generated versus traditional operative notes.

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

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

Fig. 1

References

  1. GPT-4. Accessed June 29, https://openai.com/gpt-4 (2023).

  2. Alser M, Waisberg E Concerns with the usage of ChatGPT in academia and medicine: a viewpoint. Am J Med Open. Published online February 100036. https://doi.org/10.1016/j.ajmo.2023.100036 (2023).

  3. Waisberg E, Ong J, Masalkhi M, SA Kamran, N Zaman, P Sarker, et al. GPT-4: a new era of artificial intelligence in medicine. Ir J Med Sci. Published online April 19, https://doi.org/10.1007/s11845-023-03377-8 (2023).

  4. Aaronson A, Viljanen A, Kanclerz P, Grzybowski A, Tuuminen R. Cataract complications study: an analysis of adverse effects among 14,520 eyes in relation to surgical experience. Ann Transl Med. 2020;8:1541–1541.

    Article  PubMed  PubMed Central  Google Scholar 

  5. Waisberg E, Ong J, Zaman N, SA Kamran, P Sarker, A Tavakkoli, et al. GPT-4 for triaging ophthalmic symptoms. Eye. Published online May 25. https://doi.org/10.1038/s41433-023-02595-9 (2023).

  6. Waisberg E, Ong J, Masalkhi M, N Zaman, SA Kamran, P Sarker, et al. Generative pre-trained transformers (GPT) and space health: a potential frontier in astronaut health during exploration missions. Prehosp Disaster Med. Published online June 2, 1-5. https://doi.org/10.1017/S1049023X23005848 (2023).

Download references

Author information

Authors and Affiliations

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

    Ethan Waisberg & Mouayad Masalkhi

  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, 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, Texas, 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. Mouayad Masalkhi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nasif Zaman
    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. Andrew G. Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Alireza Tavakkoli
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

EW—Conceptualization, Writing, JO—Conceptualization, Writing, MM—Conceptualization, Writing, NZ—Review, Intellectual Support, PS—Review, Intellectual Support, AGL—Review, Intellectual Support, AT—Review, Intellectual Support.

Corresponding author

Correspondence to Ethan Waisberg.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval

This article does not contain any studies with human participants performed by any of the authors.

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., Masalkhi, M. et al. GPT-4 to document ophthalmic post-operative complications. Eye 38, 414–415 (2024). https://doi.org/10.1038/s41433-023-02731-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41433-023-02731-5

This article is cited by

Search

Advanced search

Quick links