Use of Natural Language Processing to identify Obsessive Compulsive Symptoms in patients with schizophrenia, schizoaffective disorder or bipolar disorder

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.

Natural Language Processing Systems for Diagnosing and Determining Level of Lung Cancer: A Systematic Review

“…In this review, we have only included application of NLP methods for lung cancer radiology report, but NLP techniques have been adapted in other kinds of radiology reports [41][42][43]. There are many other NLP medical applications such as EHR information extraction, and identification of diseases [44][45][46]. The Use of NLP in radiology report applications may benefit from NLP applications that operate on EHR data from other fields.…”

Genomics of Obsessive-Compulsive Disorder—Toward Personalized Medicine in the Era of Big Data

“…Finally, the rapid development of bioinformatics and its application to medicine will also render new possibilities. In particular, artificial intelligence and one of its varieties, machine learning, are already used to diagnose ( 80 ), predict severity and outcome ( 81 , 82 ), and trajectories of treatment response ( 83 – 85 ) in OCD. The advancements promised by Big Data catapulted in the field and provided new insights over the past 10 years.…”

Medical Specialty Recommendations by an Artificial Intelligence Chatbot on a Smartphone: Development and Deployment

“…To develop AI chatbots, electronic medical records (EMRs) have generally been used as input data pipelines for NLP-related medical studies. Using EMRs for NLP facilitates the identification of patients with digestive disorders [ 8 , 9 ] and the prediction of the risk of psychiatric problems, such as actual self-harm, harm to others or victimization, and the risk of health care–associated infections such as surgical site infections [ 10 , 11 ]. Furthermore, EMRs have been used to develop an excellent medical specialty classifier built using deep learning–based NLP, which reportedly had area under receiver operating characteristic curve (AUC) scores of 0.975 and 0.991 and F 1 -scores of 0.845 and 0.870 in 2 different EMR data sets [ 12 ].…”