Development of a Natural Language Processing pipeline to support the differential diagnosis of epilepsy based on the descriptions of the semiology of the seizures

  • Applicant: Angus Roberts
  • Project ID: 21-081

According to World Health Organization (WHO), epilepsy is one of the most common serious neurological disorder. It affects 50 million individuals worldwide and up to 10% of people have one seizure during their lifetime. So, based on the information available in the Electronic Health Records (EHRs) from the CRIS database the main aim of this project is to build a support tool for epilepsy diagnosis considering seizures as symptoms. Once a document is classified with a good degree of reliability, the description of the specific signs of each seizure will be used to distinguish between different epilepsy classes.

The Clinical Record Interactive Search (CRIS) system is a computer system that allows researchers at the NIHR Maudsley Biomedical Research Centre (BRC) to carry out research using information from South London and Maudsley NHS Foundation Trust clinical records.

About

The Clinical Record Interactive Search has been developed in collaboration with:

South London and Maudsley NHS Foundation Trust
NIHR Maudsley BRC