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:

Clinical large language models with misplaced focus

Nature Machine Intelligence volume 6, pages 1411–1412 (2024)Cite this article

Subjects

Access through your institution
Buy or subscribe

On 12 September 2024, OpenAI released two new large language models (LLMs) — o1-preview and o1-mini — marking an important shift in the competitive landscape of commercial LLMs, particularly concerning their reasoning capabilities. Since the introduction of GPT-3.5, OpenAI has launched 31 LLMs in two years. Researchers are rapidly applying these evolving commercial models in clinical medicine, achieving results that sometimes exceed human performance in specific tasks. Although such success is encouraging, the development of the models used for these tasks may not align with the characteristics and needs of clinical practice.

LLMs can be categorized as either open-source or closed-source. Open-source models, such as Meta’s Llama, allow developers to access source code, training data and documentation freely. By contrast, closed-source models are accessed only through official channels or application programming interfaces (APIs). Initially, open-source models dominated the LLM landscape, until the release of OpenAI’s GPT-3 in 20201, which attracted considerable commercial interest and shifted focus towards closed-source approaches2.

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

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

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

References

  1. Brown, T. B. et al. Preprint at https://doi.org/10.48550/arXiv.2005.14165 (2020).

  2. Hoyos, D. Medium; https://go.nature.com/3NSdY5n (2024).

  3. Xu, M. https://github.com/shibing624/MedicalGPT (2024).

  4. Luo, Z. et al. https://github.com/Ruosining/clinical_llm_evaluation (2024).

  5. Suchman, K., Garg, S. & Trindade, A. J. Am. J. Gastroenterol. 118, 2280–2282 (2023).

    Article  Google Scholar 

  6. Lim, Z. W. et al. eBioMedicine 95, 104770 (2023).

    Article  Google Scholar 

Download references

Acknowledgements

The authors express their gratitude to Guangzhi Luo, who contributed significantly to the overall design of this research in its early stages, provided guidance as a mentor, and died due to illness in September 2024.

Author information

Authors and Affiliations

  1. North Sichuan Medical College, Nanchong, China

    Zining Luo, Aimin Hu, Jiang Yu, Yang Qiao, Junxian Gu, Hongying Li, Xuxi Peng, Ying Liu, Zhenglong Liu, Jiebin Xie & Zhen Jiang

  2. Henan Provincial People’s Hospital, Zhengzhou, China

    Zining Luo & Gang Tian

  3. Case Western Reserve University, Cleveland, OH, USA

    Haowei Ma

  4. Beijing Institute of Petrochemical Technology, Beijing, China

    Zhiwu Li

  5. School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia

    Yuquan Chen

  6. Department of Hepatobiliary and Pancreatic Surgery, Peking University First Hospital, Beijing, China

    Yixin Sun

  7. University of Glasgow, Glasgow, UK

    Dunrui Wang

  8. University of Electronic Science and Technology of China, Chengdu, China

    Dunrui Wang

Authors
  1. Zining Luo
    View author publications

    Search author on:PubMed Google Scholar

  2. Haowei Ma
    View author publications

    Search author on:PubMed Google Scholar

  3. Zhiwu Li
    View author publications

    Search author on:PubMed Google Scholar

  4. Yuquan Chen
    View author publications

    Search author on:PubMed Google Scholar

  5. Yixin Sun
    View author publications

    Search author on:PubMed Google Scholar

  6. Aimin Hu
    View author publications

    Search author on:PubMed Google Scholar

  7. Jiang Yu
    View author publications

    Search author on:PubMed Google Scholar

  8. Yang Qiao
    View author publications

    Search author on:PubMed Google Scholar

  9. Junxian Gu
    View author publications

    Search author on:PubMed Google Scholar

  10. Hongying Li
    View author publications

    Search author on:PubMed Google Scholar

  11. Xuxi Peng
    View author publications

    Search author on:PubMed Google Scholar

  12. Dunrui Wang
    View author publications

    Search author on:PubMed Google Scholar

  13. Ying Liu
    View author publications

    Search author on:PubMed Google Scholar

  14. Zhenglong Liu
    View author publications

    Search author on:PubMed Google Scholar

  15. Jiebin Xie
    View author publications

    Search author on:PubMed Google Scholar

  16. Zhen Jiang
    View author publications

    Search author on:PubMed Google Scholar

  17. Gang Tian
    View author publications

    Search author on:PubMed Google Scholar

Corresponding authors

Correspondence to Jiebin Xie, Zhen Jiang or Gang Tian.

Ethics declarations

Competing interests

All authors confirm that they have no conflicts or competing interests in contributing to this article.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Luo, Z., Ma, H., Li, Z. et al. Clinical large language models with misplaced focus. Nat Mach Intell 6, 1411–1412 (2024). https://doi.org/10.1038/s42256-024-00929-0

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-024-00929-0

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing