The Word Lab
Keeping industry professionals up-to-date with the latest news affecting life science translations
All Posts

machine translationI found a really interesting article this week, that I thought was worth bringing up. It is based on a study of phrases utilized in clinical settings, and the effectiveness of a free machine translation to bridge communication gaps between patient and caregiver. Interpreters in Healthcare settings often play a vital role, as clear communication is critical. Interpreters and translators are able to ensure that a caregiver can fully understand patient concerns and allow them to confidently relay information such as treatment instructions.

The challenge comes when these services are needed but unavailable. Remote locations, budget, and time constraints are all factors that play into when a caregiver needs to access programs for translation.

Machine Translation Results from Study

What they found was not unexpected. Given the precise nature of the life science sector, even a slight mistranslation can completely change meanings.

Ten medical phrases were evaluated in 26 languages (8 Western European, 5 Eastern European, 11 Asian, and 2 African), giving 260 translated phrases. Of the total translations, 150 (57.7%) were correct while 110 (42.3%) were wrong. African languages scored lowest (45% correct), followed by Asian languages (46%), Eastern European next with 62%, and Western European languages were most accurate at 74%. The medical phrase that was best translated across all languages was “Your husband has the opportunity to donate his organs” (88.5%), while “Your child has been fitting” was translated accurately in only 7.7% (table?). Swahili scored lowest with only 10% correct, while Portuguese scored highest at 90%. There were some serious errors. For instance, “Your child is fitting” translated in Swahili to “Your child is dead.” In Polish “Your husband has the opportunity to donate his organs” translated to “Your husband can donate his tools.” In Marathi “Your husband had a cardiac arrest” translated to “Your husband had an imprisonment of heart.” “Your wife needs to be ventilated” in Bengali translated to “Your wife wind movement needed.”

Source. Patil, Sumant & Davies, Patrick. Use of Google Translate in medical communication: evaluation of accuracy. 2014. Retrieved from

Machine Translation in Practice

What I found most helpful in this article is actually in the comments section which I encourage you to take a look at. The comments provide a unique insight into real life situations where this type of language solution has been the only option available. Some pitfalls to the process are highlighted.

To be most effective, having the patient actively help to read and write responses is helpful. However, due to varying literacy levels this is not always an option. Regardless, the process of using a machine translation often requires the use of additional gestures. It is extremely important to limit overly technical jargon and use precise straightforward sentence structure. Pay careful attention to wording such a homophones and compound words, because they often do not translate.

While there is value to utilizing these types of free services when nothing else is available, it comes with a big responsibility. One has to take extra care which may require altering their normal method of communication. However even given that, there is no way to ensure that it will be effective in any given situation and certainly not in those such as informed consent.

Previously, we discussed the Stepes App. The value that it could add to these types of scenarios is immense. When on-site interpretation is unattainable, or a simple quick translation in required in a conversation, Stepes provides a number of solutions with the ease of machine translation yet the specialization of medical translators.