Journal article · 2026 · Open access

Large language models provide unsafe answers to patient-posed medical questions

Rachel Lea Draelos, Samina Afreen, Barbara J. Blasko, Tiffany L. Brazile, Natasha Chase, Dimple Patel Desai, Jessica Evert, Heather Gardner, Lauren Herrmann, Aswathy Vaikom House, Stephanie L. Kass, Marianne Kavan and 5 more

npj Digital Medicine, 9(1) · Published 13 February 2026 · DOI 10.1038/s41746-026-02428-5

Open PDFView at the publisherCite this paper

In brief

“Large language models provide unsafe answers to patient-posed medical questions” is a 2026 journal article by Rachel Lea Draelos and 16 co-authors, published in npj Digital Medicine. OpenAlex counts 115 citations as of 17 November 2026, which puts it in the top 7% of works published in 2026 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at npj Digital Medicine.

Citations
115
Most cited in
2026 (113)
Field-weighted impact
115.32
References
19
Authors
17

Abstract

Millions of patients are regularly using large language model (LLM) chatbots for medical advice, raising patient safety concerns. This physician-led red-teaming study compares the safety of four publicly available chatbots-Claude by Anthropic, Gemini by Google, GPT-4o by OpenAI, and Llama-3.0/3.1-70B by Meta-on a new dataset, HealthAdvice, using an evaluation framework that enables quantitative and qualitative analysis. In total, 888 chatbot responses are evaluated for 222 patient-posed advice-seeking medical questions on primary care topics spanning internal medicine, women's health, and pediatrics. We find statistically significant differences between chatbots. The rate of problematic responses varies from 21.6% (Claude) to 43.2% (Llama), with unsafe responses varying from 5% (Claude) to 13% (GPT-4o, Llama). Qualitative results reveal chatbot responses with the potential to lead to serious patient harm. This study suggests that millions of patients could be receiving unsafe medical advice from publicly available chatbots, and further work is needed to improve the clinical safety of these powerful tools.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Draelos, R. L., Afreen, S., Blasko, B. J., Brazile, T. L., Chase, N., Desai, D. P., Evert, J., Gardner, H., Herrmann, L., House, A. V., Kass, S. L., Kavan, M., Khemani, K., Koire, A. M., McDonald, L. E., Rabeeah, Z., & Shah, A. (2026). Large language models provide unsafe answers to patient-posed medical questions. npj Digital Medicine, 9(1). https://doi.org/10.1038/s41746-026-02428-5

MLA 9

Draelos, Rachel Lea, et al. “Large language models provide unsafe answers to patient-posed medical questions.” npj Digital Medicine, vol. 9, no. 1, 2026. https://doi.org/10.1038/s41746-026-02428-5.

Chicago

Draelos, Rachel Lea, Samina Afreen, Barbara J. Blasko, Tiffany L. Brazile, Natasha Chase, Dimple Patel Desai, Jessica Evert, et al. 2026. “Large language models provide unsafe answers to patient-posed medical questions.” npj Digital Medicine 9 (1). https://doi.org/10.1038/s41746-026-02428-5.

Harvard

Draelos, R. L. et al. (2026) ‘Large language models provide unsafe answers to patient-posed medical questions’, npj Digital Medicine, 9(1). doi:10.1038/s41746-026-02428-5.

IEEE

R. L. Draelos et al., “Large language models provide unsafe answers to patient-posed medical questions,” npj Digital Medicine, vol. 9, no. 1, 2026, doi: 10.1038/s41746-026-02428-5.

BibTeX

@article{draelos2026large,
  title     = {{Large language models provide unsafe answers to patient-posed medical questions}},
  author    = {Draelos, Rachel Lea and Afreen, Samina and Blasko, Barbara J. and Brazile, Tiffany L. and Chase, Natasha and Desai, Dimple Patel and Evert, Jessica and Gardner, Heather and Herrmann, Lauren and House, Aswathy Vaikom and Kass, Stephanie L. and Kavan, Marianne and Khemani, Kirshma and Koire, Amanda M. and McDonald, Lauren E. and Rabeeah, Zahraa and Shah, Amy},
  journal   = {npj Digital Medicine},
  year      = {2026},
  volume    = {9},
  number    = {1},
  doi       = {10.1038/s41746-026-02428-5},
  url       = {https://doi.org/10.1038/s41746-026-02428-5}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education

  • large language models
  • healthcare chatbots
  • patient safety
  • red teaming
  • primary care
  • Claude
  • Gemini
  • GPT-4o

Work with this paper

Most-cited papers in Medicine

All highly cited Medicine papers

Questions about this paper

How do I cite this paper in APA style?

Draelos, R. L., Afreen, S., Blasko, B. J., Brazile, T. L., Chase, N., Desai, D. P., Evert, J., Gardner, H., Herrmann, L., House, A. V., Kass, S. L., Kavan, M., Khemani, K., Koire, A. M., McDonald, L. E., Rabeeah, Z., & Shah, A. (2026). Large language models provide unsafe answers to patient-posed medical questions. npj Digital Medicine, 9(1). https://doi.org/10.1038/s41746-026-02428-5

How many times has this paper been cited?

115 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at npj Digital Medicine: sign in and open the PDF from this page.

Who wrote this paper?

Rachel Lea Draelos, Samina Afreen, Barbara J. Blasko, Tiffany L. Brazile, Natasha Chase, Dimple Patel Desai, Jessica Evert, Heather Gardner, Lauren Herrmann, Aswathy Vaikom House, Stephanie L. Kass, Marianne Kavan and 5 more.

What is the DOI of this paper?

10.1038/s41746-026-02428-5, permanently at https://doi.org/10.1038/s41746-026-02428-5. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.