When medical AI fails outside English
Large language models (LLMs) are increasingly positioned as general-purpose medical systems, with demonstrated potential in diagnosis and management reasoning for patient care tasks.
Authors
- Hardy Kagimoto
- Irene Li (ORCID: https://orcid.org/0000-0002-1851-5390)
- Yutaka Matsuo
- Yusuke Iwasawa
- Ethan Goh (ORCID: https://orcid.org/0000-0003-1965-025X)
Institutions
- Tokyo University of Information Sciences (JP)
- Stanford University (US)
Publication Details
- Journal
- BMJ Digital Health & AI
- Published
- 2026-05-01
- DOI
- https://doi.org/10.1136/bmjdh-2026-000038
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00