Implementing changes after patient suicides in mental health services: A systematic review.

Suicides by mental health patients account for around a quarter of all suicides (Walby et al, 2018). Within services a range of approaches have been developed and implemented to reduce the risk of patient suicides. After every patient death by suicide, a review is carried out to identify recommendations which may assist in preventing future suicides. It is therefore important to identify the most effective methods for implementing these recommendations. The objective of this systematic review, completed in Northern Ireland, was to identify how recommendations from Serious Adverse Incident (SAI) reviews can be effectively implemented to contribute to reducing deaths by suicide within mental health services. Eleven electronic databases were searched for relevant work from 1 January 2005-30 November 2020. Quantitative, qualitative and mixed methods studies were included. A narrative synthesis was carried out of published and unpublished work on the effectiveness of implementing recommendations, after a death by suicide in mental health services. The review, which includes 41 published papers and reports, found that the literature is focused on producing recommendations to reduce future risk of suicide in mental health services. There is a lack of focus on the extent and effectiveness of the implementation of these. Recommendations have often not been tested or operationalised, limiting the translational value of these contributions. Leadership and culture are also identified as key drivers for change in mental health services. This review demonstrates that high quality research is being complete in this area, however, the majority of published research presents recommendations from reviews of mental health patient suicides. There is a lack of research focusing on implementing recommendations and evaluation of implementation, once recommendations have been made.

Characteristics of Lifeline, Crisis Line, Service Users Who Have Died by Suicide.

OBJECTIVE: Despite their widespread use, there is limited evidence on whether crisis lines are effective, how to identify callers at risk or the best ways of supporting callers to prevent suicide. This study compared the features of callers and call patterns in service users who had died by suicide with those who were currently alive from 2008 to 2011. METHODS: Using information contained on Contact's (Northern Ireland's "Lifeline" service) Client Information Management System (CIMS), 118 deaths by suicide from 2008 to 2011 were compared with a matched control group (matched on age, gender, and main presenting issue on first contact) who had not died by suicide. RESULTS: Clients who had "check-in" calls were significantly less likely to die by suicide. Those with a substance dependency or those who had made a prior suicide attempt were significantly more likely to die by suicide. Duration of service access had a negative association with suicide risk. CONCLUSIONS: "Check-in" calls are an important part of the service. Information on previous suicide attempts and substance dependency may be useful in identifying callers who may benefit from proactive support and outreach. Wider interventions are needed to promote service user follow-up and to encourage longer term engagement with the service.

Data analytics of call log data to identify caller behaviour patterns from a mental health and well-being helpline.

This work presents an analysis of 3.5 million calls made to a mental health and well-being helpline, seeking to answer the question, what different groups of callers can be characterised by specific usage patterns? Calls were extracted from a telephony informatics system. Each call was logged with a date, time, duration and a unique identifier allowing for repeat caller analysis. We utilized data mining techniques to reveal new insights into help-seeking behaviours. Analysis was carried out using unsupervised machine learning (K-means clustering) to discover the types of callers, and Fourier transform was used to ascertain periodicity in calls. Callers can be clustered into five or six caller groups that offer a meaningful interpretation. Cluster groups are stable and re-emerge regardless of which year is considered. The volume of calls exhibits strong repetitive intra-day and intra-week patterns. Intra-month repetitions are absent. This work provides new data-driven findings to model the type and behaviour of callers seeking mental health support. It offers insights for computer-mediated and telephony-based helpline management.

Predicting Caller Type From a Mental Health and Well-Being Helpline: Analysis of Call Log Data.

BACKGROUND: This paper presents an analysis of call data records pertaining to a telephone helpline in Ireland among individuals seeking mental health and well-being support and among those who are in a suicidal crisis. OBJECTIVE: The objective of our study was to examine whether rule sets generated from decision tree classification, trained using features derived from callers' several initial calls, could be used to predict what caller type they would become. METHODS: Machine learning techniques were applied to the call log data, and five distinct patterns of caller behaviors were revealed, each impacting the helpline capacity in different ways. RESULTS: The primary findings of this study indicate that a significant model (P<.001) for predicting caller type from call log data obtained from the first 8 calls is possible. This indicates an association between callers' behavior exhibited during initial calls and their behavior over the lifetime of using the service. CONCLUSIONS: These data-driven findings contribute to advanced workload forecasting for operational management of the telephone-based helpline and inform the literature on helpline caller behavior in general.