ChatGPT May Improve Access to Language-Concordant Care for Patients With Non-English Language Preferences

Fiatsogbe Dzuali; Kira Seiger; Roberto Novoa; Maria Aleshin; Joyce Teng; Jenna Lester; Roxana Daneshjou

doi:10.2196/51435

ChatGPT May Improve Access to Language-Concordant Care for Patients With Non-English Language Preferences

JMIR Med Educ. 2024 Dec 10:10:e51435. doi: 10.2196/51435.

Authors

Fiatsogbe Dzuali¹, Kira Seiger², Roberto Novoa^{3

4}, Maria Aleshin³, Joyce Teng³, Jenna Lester¹, Roxana Daneshjou^{3

5}

Affiliations

¹ Department of Dermatology, University of California, San Francisco, 1701 Divisadero Street, San Francisco, CA, 94115, United States, 1 415-353-7800.
² Department of Dermatology, University of Washington, Seattle, WA, United States.
³ Department of Dermatology, Stanford University, Redwood City, CA, United States.
⁴ Department of Pathology, Stanford University, Redwood City, CA, United States.
⁵ Department of Biomedical Data Science, Stanford University, Stanford, CA, United States.

PMID: 39657144
PMCID: PMC11651640
DOI: 10.2196/51435

Abstract

This study evaluated the accuracy of ChatGPT in translating English patient education materials into Spanish, Mandarin, and Russian. While ChatGPT shows promise for translating Spanish and Russian medical information, Mandarin translations require further refinement, highlighting the need for careful review of AI-generated translations before clinical use.

Keywords: ChatGPT; artificial intelligence; health care disparity; human language; language; language-concordant care; natural language model; patient education; preference; survey; translation.

MeSH terms

Communication Barriers
Health Services Accessibility
Humans
Language
Patient Education as Topic
Translating*