Mood 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).

To extract mood instability data from EHRs and investigate its impact on people with mental health disorders.

Data 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.

Mood 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).

Using 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.

The authors have not supplied their declaration of competing interest.

Remote monitoring of mood disorders may be an effective and low resource option for patient follow-up, but relevant evidence remains very limited. This study explores real-life compliance and health services impacts of mood monitoring among patients with bipolar disorder in the UK.

Patients with a diagnosis of bipolar disorder who were registered users of the True Colours monitoring system for at least 12 months at study assessment were included in this retrospective cohort study (n = 79). Compliance was measured as the proportion of valid depression and mania scale messages received in comparison to their expected numbers over the first 12 months of monitoring. Mental health service use data were extracted from case notes, costed using national unit costs, and compared 12 months before (pre-TC period) and 12 months after (TC period) patients’ engagement with monitoring. Associations with relevant patient factors were investigated in a multiple regression model.

Average compliance with monitoring was 82%. Significant increases in the annual use and costs of psychiatrist contacts and total mental health services were shown for patients newly referred to the clinic during the pre-TC period but not for long-term patients of the clinic. Psychiatric medication costs increased significantly between the pre-TC and TC periods (£ 235, P = 0.005) unrelated to patients’ referral status.

Remote mood monitoring has good compliance among consenting patients with bipolar disorder. We found no associations between observed changes in mental health service costs and the introduction of monitoring except for the increase in psychiatric medication costs.

Mobile technology enables high frequency mood monitoring and automated passive collection of data (e.g. actigraphy) from patients more efficiently and less intrusively than has previously been possible. Such techniques are increasingly being deployed in research and clinical settings however little is known about how such approaches are experienced by patients. Here, we explored the experiences of individuals with bipolar disorder engaging in a study involving mood and activity monitoring with a range of portable and wearable technologies.

Patients were recruited from a wider sample of 50 individuals with Bipolar Disorder taking part in the Automated Monitoring of Symptom Severity (AMoSS) study in Oxford. A sub-set of 21 patients participated in a qualitative interview that followed a semi-structured approach.

Monitoring was associated with benefits including increased illness insight, behavioural change. Concerns were raised about the potential preoccupation with, and paranoia about, monitoring. Patients emphasized the need for personalization, flexibility, and the importance of context, when monitoring mood.

Mobile and electronic health approaches have potential to lend new insights into mental health and transform healthcare. Capitalizing on the perceived utility of these approaches from the patients’ perspective, while addressing their concerns, will be essential for the promise of new technologies to be realised.