Feasibility of Real-time Artificial Intelligence–based Language Translation for Bilingual Informed Consent in Interventional Radiology:An Australian Proof-of-concept
Goran Mitreski, Philip Chan, Cephas Tamburayi Kamba, Nathan Ng, David Duong, Rose Thomas, Jyothirmayi Velaga, Miranda Siemienowicz, Hong Kuan Kok · 2026
Read Feasibility of Real-time Artificial Intelligence–based Language Translation for Bilingual Informed Consent in Interventional Radiology:An Australian Proof-of-concept by Goran Mitreski, Philip Chan, Cephas Tamburayi Kamba, Nathan Ng, David Duong, Rose Thomas, Jyothirmayi Velaga, Miranda Siemienowicz, Hong Kuan Kok (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/pmc-13572924.txt.
Description
Mitreski and a team including Chan and Kamba tested in twenty twenty-six if a smart chat tool can translate live talks on consent for scans and treatments. Tongue gaps can lead to mix-ups and poor care, and trained speakers are often not at hand. They ran fake consent talks in nine tongues with the tool GPT-4o.
Thirty-six talks were scored on a long list of points for clear and true word swaps. Most talks passed the set bar, with a mean near nine-tenths of the top score. Seven tongues passed each time, while two tongues lagged well behind. Speed was high in all tongues, but the lagging two still need a human speaker in charge.
Catalog record
| CREATOR | Goran Mitreski, Philip Chan, Cephas Tamburayi Kamba, Nathan Ng, David Duong, Rose Thomas, Jyothirmayi Velaga, Miranda Siemienowicz, Hong Kuan Kok |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 21 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |