Mood instability and clinical outcomes in mental health disorders: A natural language processing (NLP) study

Abstract

IntroductionMood instability is an important problem but has received relatively little research attention. Natural language processing (NLP) is a novel method, which can used to automatically extract clinical data from electronic health records (EHRs).AimsTo extract mood instability data from EHRs and investigate its impact on people with mental health disorders.MethodsData on mood instability were extracted using NLP from 27,704 adults receiving care from the South London and Maudsley NHS Foundation Trust (SLaM) for affective, personality or psychotic disorders. These data were used to investigate the association of mood instability with different mental disorders and with hospitalisation and treatment outcomes.ResultsMood instability was documented in 12.1% of people included in the study. It was most frequently documented in people with bipolar disorder (22.6%), but was also common in personality disorder (17.8%) and schizophrenia (15.5%). It was associated with a greater number of days spent in hospital (B coefficient 18.5, 95% CI 12.1–24.8), greater frequency of hospitalisation (incidence rate ratio 1.95, 1.75–2.17), and an increased likelihood of prescription of antipsychotics (2.03, 1.75–2.35).ConclusionsUsing NLP, it was possible to identify mood instability in a large number of people, which would otherwise not have been possible by manually reading clinical records. Mood instability occurs in a wide range of mental disorders. It is generally associated with poor clinical outcomes. These findings suggest that clinicians should screen for mood instability across all common mental health disorders. The data also highlight the utility of NLP for clinical research.Disclosure of interestThe authors have not supplied their declaration of competing interest.