Governance, tools and approaches for using text analytics and natural language processing for research

Information stored within electronic health records (EHR) that is recorded in written form – sometimes referred to as unstructured text – is difficult to use in research because special computerised tools are needed to process written text and complex governance arrangements make such data in the NHS hard to access. Better use of unstructured text contained within EHR would have a number of benefits for patients including more streamlined matching of patients to clinical trials, better understanding of risk and outcome for diseases, and identification of drug-repurposing opportunities.

The HDR UK National Text Analytics Project, funded by HDR UK, is helping to build the UK’s natural language processing community for healthcare by making available shared tools, methods and datasets across the NHS, creating richer, more useful clinical information to improve healthcare.

The HDR UK National Text Analytics team is hosting a special 1-day workshop where you will hear from experts from across the UK working in academia, the NHS and other organisations including data custodians and regulators on key issues in the text analytics field, including:

• Opportunities and challenges for text analytics in research
• Issues around accessing unstructured text for research and governance requirements
• Demonstrations of existing text analytics and natural language processing data extraction tools and methods including MedCAT, CogStack, CRIS, KOMENTI and EdiER
• How text analytics is being used in practice in the NHS

The workshop is aimed at the clinical and research community, including those working in HDR UK Hubs and Alliances, who are interested in using text analytics and natural language processing to unlock the rich data contained within EHR to deliver improvements in healthcare.

Registration and further details through Eventbrite.