Investigating symptom dimensions to predict outcomes in first episode psychosis - a natural language processing study

  • Applicant: Rashmi Patel
  • Project ID: 16-051

Psychotic disorders may result in a substantial burden of illness upon affected individuals, carers and healthcare services. At present, it is not possible to predict illness course at an individual level. This may be due to the fact that the representation of psychotic disorders in current diagnostic classification systems (e.g. ICD-10/DSM-5) does not reflect the wide range of symptoms an individual may experience. These may include positive, negative, manic, depressive and disorganized symptoms. I aim to identify the frequency and pattern of presenting symptoms in people with first episode psychosis (FEP) in free text electronic mental health records using natural language processing. I will also investigate how symptoms at first presentation may predict future clinical outcomes with the aim of supporting future research to improve clinical assessment and management of people with psychosis.

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