Abstract
Obsessive and Compulsive Symptoms (OCS) or Obsessive Compulsive Disorder (OCD) in the context of schizophrenia or related disorders are of clinical importance as these are associated with a range of adverse outcomes. Natural Language Processing (NLP) applied to Electronic Health Records (EHRs) presents an opportunity to create large datasets to facilitate research in this area. This is a challenging endeavour however, because of the wide range of ways in which these symptoms are recorded, and the overlap of terms used to describe OCS with those used to describe other conditions. We developed an NLP algorithm to extract OCS information from a large mental healthcare EHR data resource at the South London and Maudsley NHS Foundation Trust using its Clinical Record Interactive Search (CRIS) facility. We extracted documents from individuals who had received a diagnosis of schizophrenia, schizoaffective disorder, or bipolar disorder. These text documents, annotated by human coders, were used for developing and refining the NLP algorithm (600 documents) with an additional set reserved for final validation (300 documents). The developed NLP algorithm utilized a rules-based approach to identify each of symptoms associated with OCS, and then combined them to determine the overall number of instances of OCS. After its implementation, the algorithm was shown to identify OCS with a precision and recall (with 95% confidence intervals) of 0.77 (0.65–0.86) and 0.67 (0.55–0.77) respectively. The development of this application demonstrated the potential to extract complex symptomatic data from mental healthcare EHRs using NLP to facilitate further analyses of these clinical symptoms and their relevance for prognosis and intervention response.
Highlights
The increasing use of electronic health records (EHRs) across health services provides opportunities for research using real world data[1]
We describe the development of an Natural Language Processing (NLP) application for extracting data on obsessive compulsive symptoms (OCS) and obsessive compulsive disorder (OCD) from free text in EHRs in patients with schizophrenia, schizoaffective or bipolar disorders, using a rules-based approach
A machine learning approach was trialed to develop an OCS NLP application because this could be developed and deployed more rapidly. This application was developed using TextHunter which is a bespoke piece of software developed at the SLaM Biomedical Research Centre (BRC) that allows for the fast creation and deployment of Machine Learning applications based on an annotated training set and gold standard
Summary
The increasing use of electronic health records (EHRs) across health services provides opportunities for research using real world data[1]. NLP applications can be developed using machine learning and rules based approaches, each with its own advantages and drawbacks in relation to specific problems. Machine learning in the context of NLP refers to an automated method of creating an NLP application[4] It involves an annotated set of training data being utilized by various algorithms to create models to classify future documents[5]. Rule based approaches involve a human coder manually analyzing training data and creating rules based on their observations of the data[6], these rules are implemented programmatically This can be a challenging task, as the rules created need to be broad enough to ensure that they are applied to all the required instances, but not excessively broad as might lead to the rules being incorrectly applied. As EHRs continue to be exploited for research, NLP is being applied to increasingly subtle and complex tasks[10]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
