Investigating online activity in UK adolescent mental health patients: a feasibility study using a natural language processing approach for electronic health records.

OBJECTIVES: To assess the feasibility of using a natural language processing (NLP) application for extraction of free-text online activity mentions in adolescent mental health patient electronic health records (EHRs). SETTING: The Clinical Records Interactive Search system allows detailed research based on deidentified EHRs from the South London and Maudsley NHS Foundation Trust, a large south London Mental Health Trust providing secondary and tertiary mental healthcare. PARTICIPANTS AND METHODS: We developed a gazetteer of online activity terms and annotation guidelines, from 5480 clinical notes (200 adolescents, aged 11-17 years) receiving specialist mental healthcare. The preprocessing and manual curation steps of this real-world data set allowed development of a rule-based NLP application to automate identification of online activity (internet, social media, online gaming) mentions in EHRs. The context of each mention was also recorded manually as: supportive, detrimental or neutral in a subset of data for additional analysis. RESULTS: The NLP application performed with good precision (0.97) and recall (0.94) for identification of online activity mentions. Preliminary analyses found 34% of online activity mentions were considered to have been documented within a supportive context for the young person, 38% detrimental and 28% neutral. CONCLUSION: Our results provide an important example of a rule-based NLP methodology to accurately identify online activity recording in EHRs, enabling researchers to now investigate associations with a range of adolescent mental health outcomes.

Risk and protective factors for self-harm and suicide in children and adolescents: a systematic review and meta-analysis protocol.

INTRODUCTION: Self-harm and suicide are major public health concerns among children and adolescents. Many risk and protective factors for suicide and self-harm have been identified and reported in the literature. However, the capacity of these identified risk and protective factors to guide assessment and management is limited due to their great number. This protocol describes an ongoing systematic review and meta-analysis which aims to examine longitudinal studies of risk factors for self-harm and suicide in children and adolescents, to provide a comparison of the strengths of association of the various risk factors for self-harm and suicide and to shed light on those that require further investigation. METHODS AND ANALYSIS: We perform a systematic search of the literature using the databases EMBASE, PsycINFO, Medline, CINAHL and HMIC from inception up to 28 October 2020, and the search will be updated before the systematic review publication. Additionally, we will contact experts in the field, including principal investigators whose peer-reviewed publications are included in our systematic review as well as investigators from our extensive research network, and we will search the reference lists of relevant reviews to retrieve any articles that were not identified in our search. We will extract relevant data and present a narrative synthesis and combine the results in meta-analyses where there are sufficient data. We will assess the risk of bias for each study using the Newcastle-Ottawa Scale and present a summary of the quantity and the quality of the evidence for each risk or protective factor. ETHICS AND DISSEMINATION: Ethical approval will not be sought as this is a systematic review of the literature. Results will be published in mental health journals and presented at conferences focused on suicide prevention. PROSPERO REGISTRATION NUMBER: CRD42021228212.

Harm minimisation for the management of self-harm: a mixed-methods analysis of electronic health records in secondary mental healthcare.

BACKGROUND: Prevalence of self-harm in the UK was reported as 6.4% in 2014. Despite sparse evidence for effectiveness, guidelines recommend harm minimisation; a strategy in which people who self-harm are supported to do so safely. AIMS: To determine the prevalence, sociodemographic and clinical characteristics of those who self-harm and practise harm minimisation within a London mental health trust. METHOD: We included electronic health records for patients treated by South London and Maudsley NHS Trust. Using an iterative search strategy, we identified patients who practise harm minimisation, then classified the approaches using a content analysis. We compared the sociodemographic characteristics with that of a control group of patients who self-harm and do not use harm minimisation. RESULTS: In total 22 736 patients reported self-harm, of these 693 (3%) had records reporting the use of harm-minimisation techniques. We coded the approaches into categories: (a) 'substitution' (>50% of those using harm minimisation), such as using rubber bands or using ice; (b) 'simulation' (9%) such as using red pens; (c) 'defer or avoid' (7%) such as an alternative self-injury location; (d) 'damage limitation' (9%) such as using antiseptic techniques; the remainder were unclassifiable (24%). The majority of people using harm minimisation described it as helpful (>90%). Those practising harm minimisation were younger, female, of White ethnicity, had previous admissions and were less likely to have self-harmed with suicidal intent. CONCLUSIONS: A small minority of patients who self-harm report using harm minimisation, primarily substitution techniques, and the large majority find harm minimisation helpful. More research is required to determine the acceptability and effectiveness of harm-minimisation techniques and update national clinical guidelines.

Reviewing a Decade of Research Into Suicide and Related Behaviour Using the South London and Maudsley NHS Foundation Trust Clinical Record Interactive Search (CRIS) System.

Suicide is a serious public health issue worldwide, yet current clinical methods for assessing a person's risk of taking their own life remain unreliable and new methods for assessing suicide risk are being explored. The widespread adoption of electronic health records (EHRs) has opened up new possibilities for epidemiological studies of suicide and related behaviour amongst those receiving healthcare. These types of records capture valuable information entered by healthcare practitioners at the point of care. However, much recent work has relied heavily on the structured data of EHRs, whilst much of the important information about a patient's care pathway is recorded in the unstructured text of clinical notes. Accessing and structuring text data for use in clinical research, and particularly for suicide and self-harm research, is a significant challenge that is increasingly being addressed using methods from the fields of natural language processing (NLP) and machine learning (ML). In this review, we provide an overview of the range of suicide-related studies that have been carried out using the Clinical Records Interactive Search (CRIS): a database for epidemiological and clinical research that contains de-identified EHRs from the South London and Maudsley NHS Foundation Trust. We highlight the variety of clinical research questions, cohorts and techniques that have been explored for suicide and related behaviour research using CRIS, including the development of NLP and ML approaches. We demonstrate how EHR data provides comprehensive material to study prevalence of suicide and self-harm in clinical populations. Structured data alone is insufficient and NLP methods are needed to more accurately identify relevant information from EHR data. We also show how the text in clinical notes provide signals for ML approaches to suicide risk assessment. We envision increased progress in the decades to come, particularly in externally validating findings across multiple sites and countries, both in terms of clinical evidence and in terms of NLP and machine learning method transferability.

School absenteeism as a risk factor for self-harm and suicidal ideation in children and adolescents: a systematic review and meta-analysis.

Self-harm and suicidal ideation in children and adolescents are common and are risk factors for completed suicide. Social exclusion, which can take many forms, increases the risk of self-harm and suicidal ideation. One important marker of social exclusion in young people is school absenteeism. Whether school absenteeism is associated with these adverse outcomes, and if so to what extent, remains unclear. To determine the association between school absenteeism and both self-harm (including completed suicide) and suicidal ideation in children and adolescents, we conducted a systematic review of observational studies. We conducted meta-analysis and report a narrative synthesis where this was not possible. Meta-analysis of cross-sectional studies showed that school absenteeism was associated with an increased risk of self-harm [pooled adjusted odds ratio (aOR) 1.37, 95% confidence interval 1.20-1.57, P = 0.01] and of suicidal ideation (pooled aOR 1.20, 95% CI 1.02-1.42, P = 0.03). A small number of studies showed that school absenteeism had a longitudinal association with both adverse outcomes. Heterogeneity in the exposure and outcome variables, study design and reporting was prominent and limited the extent to which it was appropriate to pool results. School absenteeism was associated with both self-harm and suicidal ideation in young people, but this evidence was derived from a small number of cross-sectional studies. Further research into the mechanisms of this association could help to inform self-harm and suicide prevention strategies at clinical, school and population levels.

Social media, internet use and suicide attempts in adolescents.

PURPOSE OF REVIEW: Suicide is the second leading cause of death in youth aged 10-24 years old globally, but detecting those at risk is challenging. Novel preventive strategies with wide influence across populations are required. Interest in the potential for both detrimental and supportive influences of social media/internet use on suicidal behaviour has been growing; however, the relationship remains unclear. RECENT FINDINGS: A systematic search of articles from database inception up to 25 January 2019 across five databases: Medline, PsycINFO, EMBASE, HMIC and CINAHL revealed nine independent studies investigating social media/internet use and suicide attempts in young people less than 19 years old (n = 346 416). An independent direct association was found between heavy social media/internet use and increased suicide attempts in seven studies (adjusted ORs ranged from 1.03 to 5.10), although adjusting for cyberbullying victimization and sleep disturbance reduced the strength of this association. Two studies found that some social media/internet use, versus no use, may be associated with fewer suicide attempts. There were no studies investigating the relationship between social media/internet use and completed suicide. SUMMARY: There is an independent association between problematic use of social media/internet and suicide attempts in young people. However, the direction of causality, if any, remains unclear. Further evaluation through longitudinal studies is needed.

Family-inclusive practice in a psychiatric intensive care unit.

Aims and MethodThe National Institute for Health and Care Excellence recommends involving the families of patients admitted to psychiatric hospital care, without specific guidance on how to do it. To improve family involvement in a National Health Service psychiatric intensive care unit, a relatives' and carers' clinic was set up. Fifty family members attended and completed questionnaires. Nine went on to take part in interviews, the results of which were analysed using thematic analysis. RESULTS: Families felt more informed and found the increased access to information useful. They felt that the process showed respect for them and their family member, and that their contribution was valued. Running throughout the interviews was the contrast with previous experiences; families reported feeling heard and understood and attributed this in part to timing and environment.Clinical implicationsThe clinic was viewed positively by families and met the trust's commitment to including carers, as well as national guidance which suggests it should be part of routine practice.Declaration of interestNone.

No better than chance? Developments in predicting adolescent suicide, a commentary on Mars et al. (2018) and Beckman et al. (2018).

Suicide is the second leading cause of death in young people aged 10-24 globally (Patton et al., 2009) and it is therefore of vital importance that we understand more about how to identify those at risk. Many of those who proceed to die by suicide will not have interacted with mental health services (Kidger et al., 2012), and therefore predictors of suicide attempts and completed suicides are relevant not only to mental health services but also to schools and communities. Despite years of research, it continues to be challenging to identify those young people who undergo transition from thinking about suicide to attempting suicide as well as those young people who undergo transition from self-harm to completed suicide. This commentary will look at the two accompanying papers by Mars et al. (2018) and Beckman et al. (2018); which seek to increase our understanding of which children and young people may proceed to engage with self-harm and die by suicide.

Poor school attendance and exclusion: a systematic review protocol on educational risk factors for self-harm and suicidal behaviours.

INTRODUCTION: Schools have an important role in recognising and preventing self-harm and suicidal behaviour in their students, however little is known about which educational factors are associated with heightened risk. We will systematically review the existing evidence on two key educational performance indicators that are routinely collected by school administrative systems: school attendance and exclusion. We will investigate their association with self-harm and suicidal behaviour in school-age children and adolescents. Knowledge of this association could help inform suicide prevention strategies at clinical, school and population levels. METHODS AND ANALYSIS: We will conduct a systematic search of Medline, EMBASE, PsycINFO, British Education Index and Education Resources Information Centre (ERIC) from 1 January 1990, and conduct a manual search for additional references. We aim to identify studies that explore the association between poor school attendance or exclusion and self-harm or suicidal behaviours in school-age children and adolescents. Two independent reviewers will screen titles, abstracts and full-text documents and independently extract relevant data for analysis. Study quality will be assessed using a modified Newcastle-Ottawa Scale. A descriptive analysis will be performed, and where appropriate, results will be combined in meta-analyses. ETHICS AND DISSEMINATION: This is a systematic review of published literature, and therefore ethical approval will not be sought. We will publish reports in health and education journals, present our work at conferences focused on school mental health and communicate our findings to practitioners and managers in public health, education and child mental health. PROSPERO REGISTRATION NUMBER: CRD42018088608.

Personality disorder services in England: findings from a national survey.

Aims and method We aimed to evaluate the availability and nature of services for people affected by personality disorder in England by conducting a survey of English National Health Service (NHS) mental health trusts and independent organisations. Results In England, 84% of organisations reported having at least one dedicated personality disorder service. This represents a fivefold increase compared with a 2002 survey. However, only 55% of organisations reported that patients had equal access across localities to these dedicated services. Dedicated services commonly had good levels of service use and carer involvement, and engagement in education, research and training. However, a wider multidisciplinary team and a greater number of biopsychosocial interventions were available through generic services. Clinical implications There has been a substantial increase in service provision for people affected by personality disorder, but continued variability in the availability of services is apparent and it remains unclear whether quality of care has improved.

Decreasing the risk of iatrogenic lymphoedema after axillary surgery: a threefold intervention.

Procedures such as venepuncture and cannulation can precipitate Breast Cancer Related Lymphoedema (BCRL) in patients who have undergone axillary surgery. We noted that procedures were inadvertently being performed on the side of surgery at our hospital, as susceptible patients were not clearly identifiable to staff. An online anonymous staff survey at our hospital revealed that 26.9% of responders had seen procedures being performed on at risk arms in non-emergency settings. 83.3% of responders felt an intervention to allow easy identification of at risk arms would be useful. Our intervention was threefold. Firstly, we created an 'At Risk Arm' alert on the computerised records system. Secondly, we produced a warning sign for each susceptible patient's bed. The signs are displayed above beds, and returned to notes for use if the patient is re-admitted. Thirdly, we informed GPs via discharge summaries of the need to perform procedures on the opposite side to surgery. A second staff survey was conducted after implementation. 46.2%of responders felt that the new interventions would decrease the chance of patients developing BCRL. 61.5% felt that susceptible patients being more identifiable to staff would decrease the likelihood of procedures being performed on at risk arms. Our project showed the importance of ensuring axillary surgery patients are clearly identifiable to hospital staff during admission. Further interventions could include wristbands or patient alert cards. This work could be extended to include primary care and outpatient settings.