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:

LLM-based agentic systems in medicine and healthcare

Nature Machine Intelligence volume 6, pages 1418–1420 (2024)Cite this article

Subjects

Large language model-based agentic systems can process input information, plan and decide, recall and reflect, interact and collaborate, leverage various tools and act. This opens up a wealth of opportunities within medicine and healthcare, ranging from clinical workflow automation to multi-agent-aided diagnosis.

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 SpringerLink
  • Instant access to the full article PDF.

USD 39.95

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

Fig. 1: Characteristics of LLMs, traditional agents and LLM-based agents.

References

  1. Patel, S. B. & Lam, K. Lancet Digit. Health 5, e107–e108 (2023).

    Article  Google Scholar 

  2. Vaid, A., Landi, I., Nadkarni, G. & Nabeel, I. Lancet Digit. Health. 5, e855–e858 (2023).

    Article  Google Scholar 

  3. Touvron, H. et al. Preprint at https://doi.org/10.48550/arXiv.2302.13971 (2023).

  4. Russell, S.J. & Norvig, P. Artificial Intelligence: A Modern Approach (Pearson; 2016).

  5. Wei, J. et al. Adv. Neural Inf. Process. Syst. 35, 24824–24837 (2022).

    Google Scholar 

  6. Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K. & Yao, S. Advances in Neural Information Processing Systems 36 (NeurIPS 2023) https://go.nature.com/3CK7BPb (2023).

  7. Yao, S. et al. International Conference on Learning Representations https://openreview.net/pdf?id=WE_vluYUL-X (2023).

  8. Li, G., Hammoud, H. A. A. K., Itani, H., Khizbullin, D. & Ghanem, B. Adv. Neural Inf. Process. Syst. 36, 51991–52008 (2023).

    Google Scholar 

  9. Eloundou, T., Manning, S., Mishkin, P. & Rock, D. Science 384, 1306–1308 (2024).

    Article  Google Scholar 

  10. Hong, S. et al. International Conference on Learning Representations https://openreview.net/forum?id=VtmBAGCN7o (2024).

  11. Lewis, P. et al. Adv. Neural Inf. Process. Syst. 33, 9459–9474 (2020).

    Google Scholar 

  12. Zakka, C. et al. NEJM AI https://doi.org/10.1056/AIoa2300068 (2024).

  13. Gou, Z. et al. International Conference on Learning Representations https://openreview.net/forum?id=Sx038qxjek (2024)

  14. Tian, Y., Yang, X., Zhang, J., Dong, Y. & Su, H. Preprint at https://doi.org/10.48550/arXiv.2311.11855 (2024).

  15. Tu, T. et al. Preprint at https://doi.org/10.48550/arXiv.2401.05654 (2024).

Download references

Acknowledgements

This work is supported by the Research Grants Council of Hong Kong SAR (ECS24211020, GRF14203821, GRF14216222 and GRF14201824) and the Innovation and Technology Fund (ITF) of Hong Kong SAR (ITS/252/23). K.L. is supported by a UK National Institute for Health and Care Research Academic Clinical Fellowship. The authors thank L. Li (King’s College London) for helpful discussions.

Author information

Author notes

  1. These authors contributed equally: Jianing Qiu, Kyle Lam.

Authors and Affiliations

  1. Department of Biomedical Engineering, The Chinese University of Hong Kong, New Territories, Hong Kong SAR, China

    Jianing Qiu

  2. Department of Surgery and Cancer, Imperial College London, London, UK

    Kyle Lam

  3. Department of Engineering Science, University of Oxford, Oxford, UK

    Guohao Li

  4. Institute of Global Health Innovation, Imperial College London, London, UK

    Amish Acharya & Ara Darzi

  5. Tsinghua Medicine, Tsinghua University, Beijing, China

    Tien Yin Wong

  6. Beijing Tsinghua Changgang Hospital, Beijing, China

    Tien Yin Wong

  7. Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore

    Tien Yin Wong & Wu Yuan

  8. Scripps Research Translational Institute, La Jolla, CA, USA

    Eric J. Topol

Authors
  1. Jianing Qiu
    View author publications

    Search author on:PubMed Google Scholar

  2. Kyle Lam
    View author publications

    Search author on:PubMed Google Scholar

  3. Guohao Li
    View author publications

    Search author on:PubMed Google Scholar

  4. Amish Acharya
    View author publications

    Search author on:PubMed Google Scholar

  5. Tien Yin Wong
    View author publications

    Search author on:PubMed Google Scholar

  6. Ara Darzi
    View author publications

    Search author on:PubMed Google Scholar

  7. Wu Yuan
    View author publications

    Search author on:PubMed Google Scholar

  8. Eric J. Topol
    View author publications

    Search author on:PubMed Google Scholar

Corresponding author

Correspondence to Wu Yuan.

Ethics declarations

Competing interests

The authors declare no competing interests.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Qiu, J., Lam, K., Li, G. et al. LLM-based agentic systems in medicine and healthcare. Nat Mach Intell 6, 1418–1420 (2024). https://doi.org/10.1038/s42256-024-00944-1

Download citation

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s42256-024-00944-1

This article is cited by

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