Propagation of Interpreter Errors by Ambient AI Scribes: Study Using Simulated Clinical Encounters
Abstract In simulated English and Spanish clinical encounters, ambient AI scribes propagated interpreter errors into clinical notes, with patterns varying by speaker role and error type. These findings highlight the need for further evaluation of AI-scribe performance in multilingual and interpreter-mediated clinical care.
Authors
- S. Sandoval-Gonzalez (ORCID: https://orcid.org/0000-0002-7917-6097)
- Efren Aguilar (ORCID: https://orcid.org/0000-0003-2701-0412)
- Douglas S. Bell (ORCID: https://orcid.org/0000-0002-5063-8294)
- Alonso J. Iñiguez (ORCID: https://orcid.org/0000-0002-4869-3278)
- Alexandra Rabotin (ORCID: https://orcid.org/0000-0002-2832-1792)
- Jeffrey Arroyo (ORCID: https://orcid.org/0009-0001-2022-6360)
- Eric Lee (ORCID: https://orcid.org/0009-0006-9304-9357)
- Christina Jung (ORCID: https://orcid.org/0009-0003-4364-4762)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2026-07-28
- DOI
- https://doi.org/10.2196/88734
- Primary Topic
- Interpreting and Communication in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00