Propagation of Interpreter Errors by Ambient AI Scribes: Study Using Simulated Clinical Encounters
Alexandra Rabotin, Efren Aguilar, Saitiel Sandoval Gonzalez, Alonso Iniguez, Christina Jung, Eric Lee, Douglas S Bell, Jeffrey Arroyo, Andrew Coristine · 2026
Read Propagation of Interpreter Errors by Ambient AI Scribes: Study Using Simulated Clinical Encounters by Alexandra Rabotin, Efren Aguilar, Saitiel Sandoval Gonzalez, Alonso Iniguez, Christina Jung, Eric Lee, Douglas S Bell, Jeffrey Arroyo, Andrew Coristine (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13412140.txt.
Description
Alexandra Rabotin and co-authors report in 2026 on a weakness of ambient AI scribes, programs that listen to medical visits and draft the clinical note. In clinics that work through interpreters, a spoken mistake can quietly enter the record. The study used simulated clinical encounters in English and Spanish to see whether scribes pass interpreter errors along into written notes.
The scribes did carry interpreter errors into the notes they produced. How often this happened varied with who was speaking, clinician or patient, and with the kind of error made. The authors conclude that scribe performance in multilingual, interpreter-mediated care needs dedicated evaluation before health systems lean on these tools for documentation.
Catalog record
| CREATOR | Alexandra Rabotin, Efren Aguilar, Saitiel Sandoval Gonzalez, Alonso Iniguez, Christina Jung, Eric Lee, Douglas S Bell, Jeffrey Arroyo, Andrew Coristine |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 14 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |