JMIR Med Educmededu20JMIR Medical EducationJMIR Med Educ2369-3762JMIR PublicationsToronto, Canadav11i1e7172110.2196/71721Letter to the EditorAuthors’ Reply: Enhancing AI-Driven Medical Translations: Considerations for Language ConcordanceTengJoyceMD, PhD1NovoaRoberto AndresMD12*AleshinMaria AlexandrovnaMD1*LesterJennaMD3*SeigerKiraMD, MBA4*DzualiFiatsogbeMD3*DaneshjouRoxanaMD, PhD15Department of Dermatology, Stanford University700 Welch RdStanfordUnited StatesDepartment of Pathology, Stanford UniversityRedwood CityCAUnited StatesDepartment of Dermatology, University of CaliforniaSan FranciscoCAUnited StatesDepartment of Dermatology, University of WashingtonSeattleWAUnited StatesDepartment of Biomedical Data Science, Stanford UniversityStanfordCAUnited StatesLeungTiffanyCorrespondence to Joyce Teng, MD, PhD, Department of Dermatology, Stanford University, 700 Welch Rd, Stanford, 94305, United States, 1 6507236493; jteng3@stanford.edu
This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Education, is properly cited. The complete bibliographic information, a link to the original publication on https://mededu.jmir.org/, as well as this copyright and license information must be included.
https://mededu.jmir.org/2024/1/e51435https://mededu.jmir.org/2025/1/e70420ChatGPTartificial intelligencelanguagetranslationhealth care disparitynatural language modelsurveypatient educationaccessibilitypreferencehuman languagecommunicationlanguage-concordant care
We appreciate the thoughtful insights shared by Quon and Zhou [1] regarding our study on the application of ChatGPT in translating patient education materials [2]. We wholly agree that the linguistically distinct languages, such as Mandarin, can present challenges in capturing all the nuances and achieving precise translations.
In response to the comment regarding the use of multiple prompts, we acknowledge the complexity and variability in artificial intelligence (AI)-generated translations. However, it is important to consider the practical limitations within a clinical setting. Asking providers to use various prompts in real time may not be feasible due to time constraints and the need for efficiency in patient care. We believe that focusing on a single, effective prompt can streamline the translation process while we explore avenues for improvement in the AI’s capabilities. This could be a productive avenue for future research.
Addressing the concern regarding the reliance on board-certified dermatologists for post-translation review, we want to clarify that, in addition to being board-certified dermatologists, all reviewers were native speakers in the language they reviewed, including fluency in Mandarin at a college level. This proficiency allows for a confluence of both clinical and linguistic insights when evaluating translations, reinforcing the validity of our findings. We appreciate the importance of rigor in translation review and remain committed to enhancing the integrity of our translated materials.
Overall, while we recognize the areas where ChatGPT can improve, we also see its current utility as a valuable tool for expanding access to language-concordant care in clinical settings. Our study serves as a helpful step toward identifying and addressing the limitations of AI translations, and we welcome continued dialogue to refine these practices.
None declared.
AbbreviationsAI
artificial intelligence
ReferencesQuonSZhouSEnhancing AI-driven medical translations: considerations for language concordanceJMIR Med Educ20251110.2196/70420DzualiFSeigerKNovoaRChatGPT may improve access to language-concordant care for patients with non-English language preferencesJMIR Med Educ2024121010e5143510.2196/5143539657144