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 Research

Comment on “Credibility of ChatGPT in the assessment of obesity in type 2 diabetes according to the guidelines”

International Journal of Obesity volume 48, page 288 (2024)Cite this article

Subjects

We would like to respond to a comment on the published article entitled “Credibility of ChatGPT in the assessment of obesity in type 2 diabetes according to the guidelines [1]”. The study assessed ChatGPT’s ability to answer questions about obesity treatment in accordance with established guidelines. The responses were divided into four groups based on their conformity to the guidelines. ChatGPT demonstrated a methodical approach and recommended seeking personalized advice from a healthcare provider. While it had 100% compatibility in assessing obesity in type 2 diabetes, it had a lower compatibility in the treatment sections. Additional prompts were required for responses that were compatible but did not provide all of the guideline information.

The study’s weaknesses include its reliance on non-human subjects and the narrow scope of the questions posed. More testing with human subjects and a broader range of questions could yield more robust results. Furthermore, the study did not investigate the reasons for ChatGPT’s lower compatibility in treatment sections, which necessitates further investigation. To improve compatibility with the guidelines, it is critical to refine ChatGPT’s responses in the therapy sections in the future. This could entail expanding its knowledge base and understanding of the guidelines, thereby reducing the need for additional prompts. Furthermore, studies with human subjects and assessing real-world applicability would be beneficial. Collaborations with healthcare professionals in the future, as well as continuous fine-tuning of ChatGPT’s capabilities, could ensure its effectiveness in providing accurate and comprehensive obesity treatment recommendations in accordance with the guidelines. Any set guideline should cover the code of conduct for appropriate use of AI since human is the user and responsible for any AI process [2].

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

References

  1. Barlas T, Altinova AE, Akturk M, Toruner FB. Credibility of ChatGPT in the assessment of obesity in type 2 diabetes according to the guidelines. Int J Obes. 2023. https://doi.org/10.1038/s41366-023-01410-5.

  2. Kleebayoon A, Wiwanitkit V. ChatGPT, critical thing and ethical practice. Clin Chem Lab Med. 2023;61:e221.

    Article  PubMed  CAS  Google Scholar 

Download references

Funding

The authors have no fund and ask for waiving for any charge from the journal.

Author information

Authors and Affiliations

  1. Private Academic Consultant, Phonhong, Lao People’s Democratic Republic

    Hinpetch Daungsupawong

  2. Chandigarh University, Mohali, India

    Viroj Wiwanitkit

Authors
  1. Hinpetch Daungsupawong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Viroj Wiwanitkit
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

HD 50% ideas, writing, analyzing, approval. VW 50% ideas, supervision, approval.

Corresponding author

Correspondence to Hinpetch Daungsupawong.

Ethics declarations

Competing interests

The authors declare no competing interests.

Consent for publication

Agree.

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

Daungsupawong, H., Wiwanitkit, V. Comment on “Credibility of ChatGPT in the assessment of obesity in type 2 diabetes according to the guidelines”. Int J Obes 48, 288 (2024). https://doi.org/10.1038/s41366-023-01437-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41366-023-01437-8

Search

Advanced search

Quick links