EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Implicit bias in digital health: systematic biases in large language models’ representation of global public health attitudes and challenges to health equity

Yuan Gao, Yican Feng, Surng Gahb Jahng

Frontiers in Public Health · 28.11.2025 · 13

DOI: 10.3389/fpubh.2025.1705082 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Public Health, online erschienen am 28.11.2025. Verfasst von Yuan Gao und 2 weiteren Autor:innen. Beteiligte Einrichtung: Advanced Graduate School of Imaging, Chung-Ang University, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Health Equity, Public Health, Language, Global Health. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

As emerging instruments in digital health, large language models (LLMs) assimilate values and attitudes from human-generated data, thereby possessing the latent capacity to reflect public health perspectives. This study investigates into the representational biases of LLMs through the lens of health equity. We propose and empirically validate a three-dimensional explanatory framework encompassing Data Resources, Opinion Distribution, and Prompt Language, positing that prompts are not just communicative media but critical conduits that embed cultural context.

Methods

Utilizing a selection of prominent LLMs from the United States and China-namely Gemini 2.5 Pro, GPT-5, DeepSeek-V3, and Qwen 3. We conduct a systematic empirical analysis of their performance in representing health attitudes across diverse nations and demographic strata.

Results

Our findings demonstrate that: first, the accessibility of data resources is a primary determinant of an LLM’s representational fidelity for internet users and nations with high internet penetration. Second, a greater consensus in public health opinion correlates with an increased propensity for the models to replicate the dominant viewpoint. Third, a significant “native language association” is observed, wherein Gemini 2.5 Pro and DeepSeek-V3 exhibit superior performance when prompted in their respective native languages. Conversely, models with enhanced multilingual proficiencies, such as GPT-5.0 and Qwen 3, display greater cross-lingual consistency.

Discussion

This paper not only quantifies the degree to which these leading LLMs reflect public health attitudes but also furnishes a robust analytical pathway for dissecting the underlying mechanisms of their representational biases. These findings bear profound implications for the advancement of health equity in the artificial intelligence era.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Health EquityPublic HealthLanguageGlobal HealthHumansChinaUnited StatesLarge Language ModelsDigital Health

Stichwörter der Autor:innen

algorithmic auditdigital healthhealth equitylarge language modelsrepresentational bias

Autor:innen und Institutionen

  • Advanced Graduate School of Imaging, Chung-Ang University, Seoul, Republic of Korea.
  • Fashion Design Institute, Zhejiang Fashion Institute of Technology, Ningbo, China.

Zitieren

APA

Gao, Y., Feng, Y., & Jahng, S. G. (2025). Implicit bias in digital health: systematic biases in large language models’ representation of global public health attitudes and challenges to health equity. Frontiers in Public Health, 13. https://doi.org/10.3389/fpubh.2025.1705082

Vancouver

Gao Y, Feng Y, Jahng SG. Implicit bias in digital health: systematic biases in large language models’ representation of global public health attitudes and challenges to health equity. Frontiers in Public Health. 2025;13. doi:10.3389/fpubh.2025.1705082

BibTeX
@article{Gao2025,
  author = {Gao, Yuan and Feng, Yican and Jahng, Surng Gahb},
  title = {Implicit bias in digital health: systematic biases in large language models’ representation of global public health attitudes and challenges to health equity},
  journal = {Frontiers in Public Health},
  year = {2025},
  volume = {13},
  doi = {10.3389/fpubh.2025.1705082}
}
Kostenlos starten →