New Report: Views on the Creation of an NHS Donated Free Text Databank for Research

Information stored within electronic health records (EHR) that is recorded as unstructured text is difficult to use for research because special computerised tools are needed to process the text and complex governance arrangements make such data in the NHS hard to access. The creation of a donated databank of clinical free text could provide an important opportunity for researchers to develop natural language processing (NLP) methods and create, train and evaluate computer programs to aid research.  

Funded by Healtex and Health Data Research UK, and led by Natalie Fitzpatrick and Richard Dobson at the UCL Institute of Health Informatics, researchers from King’s College London, University of Manchester, University of Sussex and Swansea University are working on a project to ascertain the views of four key stakeholder groups around the creation of a donated free text databank and inform potential next steps for adopting a partner led approach to establish a national, funded databank of free text for use by the research community.

In March 2022, stakeholders including patients and members of the public, clinicians, NHS information governance leads, research ethics committee members and researchers with expertise in NLP took part in a series of focus groups to share their views around the acceptability of establishing a free text databank for research.  A report on the findings of the focus groups highlights significant support and a pressing need for a free text databank to develop and train NLP tools.  Despite this, participants raised significant challenges in creating, communicating and managing a databank, including access and types of data that should be included, and ensuring the databank is secure and trusted.  

Findings will now be used to develop a larger national survey in collaboration with stakeholders, which will inform next steps for the databank. 

View the full report

For more information about this project, or to get involved in the development of the survey, contact Natalie Fitzpatrick (n.fitzpatrick@ucl.ac.uk). 

Authored by: Natalie Fitzpatrick

June 2022