Disparate language and model effects on AI-based translation and recognition of genetic conditions
Journal of the American Medical Informatics Association · 01.07.2026 · 33 (7) · 1284-1292
DOI: 10.1093/jamia/ocag067 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 06.05.2026. Verfasst von Dat Duong und 5 weiteren Autor:innen. Beteiligte Einrichtung: Medical Genetics Branch, National Human Genome Research Institute, Bethesda, Maryland, United States. Hauptthemen laut MEDLINE: Artificial Intelligence, Translating, Neural Networks, Computer, Language. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Intramural Research Program of the National Human Genome Research Institute of the National Institutes of Health, National Human Genome Research Institute of the National Institutes of Health.
Abstract (Originalsprache)
Introduction
Artificial intelligence (AI) is increasingly prevalent. Patients and clinicians may use AI-based tools in many different languages.
Objective
To investigate AI translation tools for descriptions of genetic conditions and how AI identification of genetic conditions is affected by translations. Materials and Methods We used Neural machine translation (NMT) and large language-model (LLM) translation to translate descriptions of 40 genetic conditions into 191 and 93 languages, respectively. Excluding translations retaining English medical terms verbatim, we respectively focused on 139 and 70 languages. After assessing translations, we assessed the ability of 3 proprietary and 3 open-weight general LLMs to identify conditions in the translations. We analyzed how accuracy was affected by the conditions’ prevalence in the literature, and attributes of the languages (the script, language family, and prevalence of the language in training sources). We also investigated adaptive translation for select languages.
Results
We found significant differences in condition identification based on the translation method, condition, language, and prediction model. The accuracy of some models was more affected than others by factors like the conditions’ literature prevalence, language script, family, and language prevalence. Adaptive translation for select languages did not improve translations or diagnostic accuracy with the 3 tested LLMs. However, further analysis with 1 language showed that this approach was more effective with smaller LLMs.
Conclusions
AI-based translation has variable performance, which can affect the ability of AI models to recognize genetic conditions. These findings should inform safe medical AI use to support consistent performance in different languages.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Medical Genetics Branch, National Human Genome Research Institute, Bethesda, Maryland, United States.
- Metabolic Medicine Branch, National Human Genome Research Institute, Bethesda, Maryland, United States.
- Medical Genetics, Jupiter Hospital, Baner, Pune, India.
- Medical Genetics, Bharati Vidyapeeth Medical College, Pune, India.
- Division of Genetics and Metabolism, Brown University, Providence, Rhode Island, United States.
ORCID-Profile: Chanika Phornphutkul
Förderung
- Intramural Research Program of the National Human Genome Research Institute of the National Institutes of Health
- National Human Genome Research Institute of the National Institutes of Health
Zitieren
APA
Duong, D., Manoli, I., Phadke, S. R., Phornphutkul, C., Raymond, J. D., & Solomon, B. D. (2026). Disparate language and model effects on AI-based translation and recognition of genetic conditions. Journal of the American Medical Informatics Association, 33(7), 1284-1292. https://doi.org/10.1093/jamia/ocag067
Vancouver
Duong D, Manoli I, Phadke SR, Phornphutkul C, Raymond JD, Solomon BD. Disparate language and model effects on AI-based translation and recognition of genetic conditions. Journal of the American Medical Informatics Association. 2026;33(7):1284-1292. doi:10.1093/jamia/ocag067
BibTeX
@article{Duong2026,
author = {Duong, Dat and Manoli, Irini and Phadke, Shubha R and Phornphutkul, Chanika and Raymond, Jonathan D and Solomon, Benjamin D},
title = {Disparate language and model effects on AI-based translation and recognition of genetic conditions},
journal = {Journal of the American Medical Informatics Association},
year = {2026},
volume = {33},
number = {7},
pages = {1284--1292},
doi = {10.1093/jamia/ocag067}
}
EUVIMED