Developing natural language processing tools to investigate alcohol and illicit substance misuse in people with serious mental illness

  • Applicant: Rashmi Patel
  • Project ID: 16-053

A number of studies have highlighted the risks associated with alcohol and illicit substances in relation to serious mental illness. The role of cannabis has been investigated in a previous study using CRIS but less is known about alcohol and other illicit substances such as opiates, cocaine, amphetamines, ketamine and novel psychoactive substances. In this study, I aim to develop natural language processing (NLP) tools to identify alcohol and illicit substance use from free text electronic health records and apply these tools to investigate the association of alcohol/illicit substance use with clinical outcomes in people with serious mental illness.

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