Language translation apps

Language translation apps

yellow unaunahi tile
Print this page

Language translation apps in health care settings

Communication between health professionals and patients can be challenging if they have different language backgrounds. In such situations it is best to use an interpreter service, which is available in most areas of New Zealand for hospital and primary care visits. But sometimes getting an interpreter may not be possible and increasingly people are using language translation apps.  

We have not been able to review all the available language translation apps that may be helpful in the healthcare setting, but here are a few for consideration. 

A study evaluating iPad-compatible language translation apps to determine their suitability for enabling everyday conversations in health care settings found the following apps to be most suitable:1

  • CALD Assist (not available in New Zealand)

The authors noted that apps allowing free input of information to be translated were less suitable as there were no limits to the way they could be used, whereas apps that only enabled translation of pre-set phrases were more suitable. Read more(external link)

What about Google Translate?

Google Translate is a free, web-based and app-based translation software that allows users to write free text in one language and have it converted to written or spoken text in another language. Google Translate uses a statistics-based translation (statistical machine translation) method that produces translations based on their probability of being correct. Currently, Google Translate can translate more than 100 languages.

A study in the United Kingdom found limited usefulness for medical phrases used in communications between patients and doctor. The authors found that Google Translate has about 57.7% accuracy when used for medical phrase translations and should not be trusted for important medical communications. The researchers found many translations that were completely wrong. Because Google Translate uses statistical matching to translate, rather than a dictionary/grammar rules approach, this leaves it open to nonsensical results. The authors suggest that for health-related questions Google Translate should be used with caution. Google Translate should not be used for taking consent for surgery, procedures or research from patients or relatives unless all avenues to find a human translator have been exhausted and the procedure is clinically urgent.

Likewise, a study in the United States comparing a pilot translation tool with Google Translate among emergency medical service personnel found numerous challenges with using Google Translate. Some of the problems encountered by participants included that guessing was necessary to understand the translation, the translation was difficult to understand and it was difficult to ask questions, there were culturally inappropriate words and it was inconsistent.3 


  1. Panayiotou A, Wiliams S, Zucchi E, et al. Language translation apps in health care settings: expert opinion.(external link) JMIR Mhealth Uhealth. 2019 7(4):e11316
  2. Patil S, Davies P. Use of Google Translate in medical communication: evaluation of accuracy.(external link) BMJ. 2014 349:g7392.
  3. Turner AM, Choi YK, Dew K, et al.  Evaluating the usefulness of translation technologies for emergency response communication: a scenario-based study.(external link) JMIR Public Health Surveill. 2019 Jan-Mar;5(1): e11171.
App developer: If you are the developer and would like to provide updated information about this app, please email the app library manager at

Disclaimer: Healthify’s app library is a free consumer service to help you decide whether a health app would be suitable for you. Our review process is independent. We have no relationship with the app developers or companies and no responsibility for the service they provide. This means that if you have an issue with one of the apps we have reviewed, you will need to contact the app developer or company directly.

Last reviewed:

Page last updated: