Free-text clinical data is a vast, untapped source of rich information to guide research and clinical care, that would clarify and supplement information coded in structured data fields, if it were more accessible.
Generally, clinical data needs to be de-identified or anonymised before being used for secondary purposes such as audit and research, but there are major challenges in finding effective methods that do not also damage free-text data utility.
In short, we need to make free-text data more accessible but ensure this is done safely and securely.
Although there is a wealth of research on free-text de-identification methods, there is a need for focused work on the development of data governance models.
Our main aim in the TexGov project is to work towards creating data governance standards to enable free-text data to be used safely for research for the benefit of patients and the public.