Medical, multilingual and privacy-preserving natural language processing in the clinical domain
For this project, funded by the Swiss National Science Foundation, we are developing advanced tools using artificial intelligence (AI) and natural language processing (NLP) to enable the safe and more informative use of clinical notes in medical research.
We are working on machine learning methods to automatically identify and remove personal health information, while assessing the residual risk of re-identification. This will allow researchers to use the data without compromising patient confidentiality.
The development of a multilingual de-identification algorithm will make it possible to securely share this data on a centralized, high-performance IT infrastructure and to create new multilingual NLP tools for two targeted clinical applications.
By developing secure, multilingual tools, this project will enable better use of clinical notes to support research and patient communication, while ensuring the protection of their data.
- (opens in a new window)
- Next
- Previous