Abstract Sumithra Velupillai 4 December 2019

From IMC wiki
Jump to: navigation, search

Title: NLP for mental health research - examples from the South London and Maudsley Biomedical Research Centre


Routine healthcare data such as electronic health records (EHRs) are an incredibly rich resource for secondary data analysis, and appropriate utilization of these could have a dramatic impact on healthcare research and delivery. A large proportion of the documentation in EHRs is in written text form. In mental health care, this proportion is larger than in other clinical domains, as the most important features of mental health care do not lend themselves to structured fields (e.g. mental health symptoms, determining treatment initiation, outcome evaluation). To enable large-scale analysis of this information, Natural Language Processing (NLP) applications are needed. In this talk, I will describe past and ongoing projects where NLP methods have been applied on mental health records from a large secondary mental health care provider in South London, UK. I will give some examples of use-cases and approaches, and discuss opportunities and challenges.


Dr. Velupillai is a Lecturer in Applied Health Informatics, at the NIHR South London and Maudsley Biomedical Research Centre (SLaM BRC), Institute of Psychiatry, Psychology and Neuroscience, King's College London, UK. Dr. Velupillai has worked on clinical NLP since 2007 and on mental health-related research since 2016, particularly on information extraction techniques.