Skip links

AI language recognition during awake brain surgery

Client :
Liquid Themes

AI language recognition during awake brain surgery

Project summary

Currently, patients who have to undergo awake brain surgery are given language tests before, after and during the operation to monitor their language level as much as possible. Spontaneous language (language in a conversation that is as natural as possible) is also transcribed and scored, for example, on the number of incomplete sentences or the number of unique words.

“That takes a lot of time, but it is very important,” says Elke. Spontaneous language is much more sensitive and shows mild language problems that do not always emerge from standardized language tests. Djaina: ‘If we do not analyze spontaneous language properly, we may miss language errors, while patients do have complaints at home and at work. These patients are then sent home while they actually still needed to be followed up with more specific tests and speech therapy.’


The researchers will continue to do their own scoring of errors to identify a language problem. But with this pilot they hope to collect enough data to eventually submit a new application to also automatically classify language errors. “If the model can also score in addition to transcribing, perhaps even during an awake brain operation, we will not only be faster, but also more objective,” says Elke.

More detailed information

Principal Investigator:

Elke de Witte, Djaina Satoer, Arnaud Vincent

Role Erasmus MC:




Project website:

Funding Agency:

Stichting Stop Hersentumoren