Redefining Bias Audits for Generative AI in Health Care
NEJM AI · 2025
DOI: 10.1056/aip2500015 ↗Kurz gefasst
Editorial in der Zeitschrift NEJM AI, 2025. Verfasst von Irene Y Chen und 1 weiteren Autor:innen. Beteiligte Einrichtung: Computational Precision Health, University of California, Berkeley and University of California, San Francisco, Berkeley. Hauptthemen laut MEDLINE: Delivery of Health Care. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 87 Literaturangaben.
Abstract (Originalsprache)
AbstractLarge language models (LLMs) are transforming health care by supporting a range of administrative and clinical tasks; however, recent studies have raised concerns about their potential to exacerbate existing health care inequities. Traditional algorithmic auditing approaches fall short in addressing the unique challenges posed by LLMs, which process complex text-based inputs and generate human-like outputs. In this perspective, we examine current approaches for evaluating LLM bias in clinical settings, identifying key gaps in existing audit methodologies. We propose comprehensive guidelines for categorizing and detecting biases in LLM applications and illustrate their application through two real-world deployed systems - in-basket patient response drafting and mental health chatbots. Finally, we offer concrete recommendations for advancing LLM bias evaluation in a rapidly evolving technological landscape.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Computational Precision Health, University of California, Berkeley and University of California, San Francisco, Berkeley.
- Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley.
- Biomedical Data Science, Stanford University, Stanford, CA.
ORCID-Profile: Irene Y Chen, Emily Alsentzer
Zitieren
APA
Chen, I. Y., & Alsentzer, E. (2025). Redefining Bias Audits for Generative AI in Health Care. NEJM AI. https://doi.org/10.1056/aip2500015
Vancouver
Chen IY, Alsentzer E. Redefining Bias Audits for Generative AI in Health Care. NEJM AI. 2025. doi:10.1056/aip2500015
BibTeX
@article{Chen2025,
author = {Chen, Irene Y and Alsentzer, Emily},
title = {Redefining Bias Audits for Generative AI in Health Care},
journal = {NEJM AI},
year = {2025},
doi = {10.1056/aip2500015}
}
EUVIMED