Using categorical data analyses in suicide research: Considering clinical utility and practicality

Machine learning and the prediction of suicide in psychiatric populations: a systematic review

Machine learning (ML) has emerged as a promising tool to enhance suicidal prediction. However, as many large-sample studies mixed psychiatric and non-psychiatric populations, a formal psychiatric diagnosis emerged as a strong predictor of suicidal risk, overshadowing more subtle risk factors specific to distinct populations. To overcome this limitation, we conducted a systematic review of ML studies evaluating suicidal behaviors exclusively in psychiatric clinical populations. A systematic literature search was performed from inception through November 17, 2022 on PubMed, EMBASE, and Scopus following the PRISMA guidelines. Original research using ML techniques to assess the risk of suicide or predict suicide attempts in the psychiatric population were included. An assessment for bias risk was performed using the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) guidelines. About 1032 studies were retrieved, and 81 satisfied the inclusion criteria and were included for qualitative synthesis. Clinical and demographic features were the most frequently employed and random forest, support vector machine, and convolutional neural network performed better in terms of accuracy than other algorithms when directly compared. Despite heterogeneity in procedures, most studies reported an accuracy of 70% or greater based on features such as previous attempts, severity of the disorder, and pharmacological treatments. Although the evidence reported is promising, ML algorithms for suicidal prediction still present limitations, including the lack of neurobiological and imaging data and the lack of external validation samples. Overcoming these issues may lead to the development of models to adopt in clinical practice. Further research is warranted to boost a field that holds the potential to critically impact suicide mortality.

The Mental Imagery for Suicidality in Students Trial (MISST): study protocol for a feasibility randomised controlled trial of broad-minded affective coping (BMAC) plus risk assessment and signposting versus risk assessment and signposting alone

BACKGROUND

Going to university is an important milestone in many people's lives. It can also be a time of significant challenge and stress. There are growing concerns about mental health amongst student populations including suicide risk. Student mental health and counselling services have the potential to prevent suicide, but evidence-based therapies are required that fit these service contexts. The Broad-Minded Affective Coping intervention (BMAC) is a brief (6 sessions), positive imagery-based intervention that aims to enhance students access to past positive experiences and associated emotions and cognitions. Pilot data provides preliminary support for the BMAC for students struggling with suicidal thoughts and behaviours, but this intervention has not yet been evaluated in the context of a randomised controlled trial (RCT). The Mental Imagery for Suicidality in Students Trial (MISST) is a feasibility RCT that aims to determine the acceptability and feasibility of evaluating the BMAC as an intervention for university students at risk of suicide within a larger efficacy trial. Key feasibility uncertainties have been identified relating to recruitment, retention, and missing data. Intervention acceptability and safety will also be evaluated.

METHOD

MISST is a feasibility randomised controlled trial design, with 1:1 allocation to risk assessment and signposting plus BMAC or risk assessment and signposting alone. Participants will be university students who self-report experiences of suicidal ideation or behaviour in the past 3 months. Assessments take place at baseline, 8, 16, and 24 weeks. The target sample size is 66 participants. A subset of up to 20 participants will be invited to take part in semi-structured qualitative interviews to obtain further data concerning the acceptability of the intervention.

DISCUSSION

The BMAC intervention may provide an effective, brief talking therapy to help university students struggling with suicidal thoughts that could be readily implemented into university student counselling services. Depending on the results of MISST, the next step would be to undertake a larger-scale efficacy trial.

TRIAL REGISTRATION

The trial was preregistered (17 December 2021) on ISRCTN (ISRCTN13621293) and ClinicalTrials.gov (NCT05296538).