Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.

Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study

Open access
Zack, Travis, Lehman, Eric, Suzgun, Mirac, Rodriguez, Jorge A, Celi, Leo Anthony, Gichoya, Judy, Jurafsky, Dan, Szolovits, Peter, Bates, David W, Abdulnour, Raja-Elie E, Butte, Atul J, Alsentzer, Emily · 2024 · The Lancet Digital Health

Abstract

BACKGROUND: Large language models (LLMs) such as GPT-4 hold great promise as transformative tools in health care, ranging from automating administrative tasks to augmenting clinical decision making. However, these models also pose a danger of perpetuating biases and delivering incorrect medical diagnoses, which can have a direct, harmful impact on medical care. We aimed to assess whether GPT-4 encodes racial and gender biases that impact its use in health care. METHODS: Using the Azure OpenAI application interface, this model evaluation study tested whether GPT-4 encodes racial and gender biases and examined the impact of such biases on four potential applications of LLMs in the clinical domain-namely, medical education, diagnostic reasoning, clinical plan generation, and subjective patient assessment. We conducted experiments with prompts designed to resemble typical use of GPT-4 within clinical and medical education applications. We used clinical vignettes from NEJM Healer and from published research on implicit bias in health care. GPT-4 estimates of the demographic distribution of medical conditions were compared with true US prevalence estimates. Differential diagnosis and treatment planning were evaluated across demographic groups using standard statistical tests for significance between groups. FINDINGS: We found that GPT-4 did not appropriately model the demographic diversity of medical conditions, consistently producing clinical vignettes that stereotype demographic presentations. The differential diagnoses created by GPT-4 for standardised clinical vignettes were more likely to include diagnoses that stereotype certain races, ethnicities, and genders. Assessment and plans created by the model showed significant association between demographic attributes and recommendations for more expensive procedures as well as differences in patient perception. INTERPRETATION: Our findings highlight the urgent need for comprehensive and transparent bias assessments of LLM tools such as GPT-4 for intended use cases before they are integrated into clinical care. We discuss the potential sources of these biases and potential mitigation strategies before clinical implementation. FUNDING: Priscilla Chan and Mark Zuckerberg.

Overview

Integrity signals

Registry

Crossref · 10.1016/s2589-7500(23)00225-x

Cites

47 of 47 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

2 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Citations

Cites

Show all 44 references

Research works printed but not linked: 2

  1. OpenAI. GPT-4 technical report. arXiv 2023; published online March 15. https://doi.org/10/48550/arXiv.2303.08774 (preprint).
  2. Fleming, 2023, Assessing the potential of USMLE-like exam questions generated by GPT-4, medRxiv

Cited by

See all 613

Metadata

Authors
Zack, T., Lehman, E., Suzgun, M., Rodriguez, J. A., Celi, L. A., Gichoya, J., Jurafsky, D., Szolovits, P., Bates, D. W., Abdulnour, R.-E. E., Butte, A. J., & Alsentzer, E.
Affiliations
  • University of California, San Francisco (US)
  • MIT Computer Science and Artificial Intelligence Laboratory (US)
  • Brigham and Women's Hospital (US)
  • Beth Israel Deaconess Medical Center (US)
  • Emory University (US)
  • Stanford University (US)
Corresponding author
Alsentzer, Emily
Venue
The Lancet Digital Health
Publisher
Elsevier BV
Published
2024-01
Volume
6
Issue
1
Pages
e12-e22
ISSN
2589-7500 (ISSN-L)
OpenAlex
W4389917881
Cited by
510
References
44
Citations by year
2026: 161 · 2025: 203 · 2024: 145
FWCI
20.37
Type
journal article
Language
en
Update notices
erratum (2024-07-01)
Open access
Licence
Locations
  • The Lancet Digital Health (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
  • National Cancer Institute
  • National Science Foundation (IIS-2128145)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
  • Social Sciences › Gender Studies › Diversity and Career in Medicine
Keywords
GPT-4, large language models, algorithmic bias, racial bias, gender bias, health care, medical education, differential diagnosis, clinical decision support, bias mitigation, patient perspectives
MeSH terms
Clinical Decision-Making, Delivery of Health Care, Diagnosis, Differential, Education, Medical, Female, Health Facilities, Humans, Male

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study. https://app.cochat.ai/papers/10.1016/s2589-7500(23)00225-x
The paper
Zack, T., Lehman, E., Suzgun, M., Rodriguez, J. A., Celi, L. A., Gichoya, J., Jurafsky, D., Szolovits, P., Bates, D. W., Abdulnour, R.-E. E., Butte, A. J., & Alsentzer, E. (2024). Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study. The Lancet Digital Health. https://doi.org/10.1016/s2589-7500(23)00225-x

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.