Rates of childhood mental health problems are increasing in the UK. Early identification of childhood mental health problems is challenging but critical to children’s future psychosocial development. This is particularly important for children with social care contact because earlier identification can facilitate earlier intervention. Clinical prediction tools could improve these early intervention efforts.

Characterise a novel cohort consisting of children in social care and develop effective machine learning models for prediction of childhood mental health problems.

We used linked, de-identified data from the Secure Anonymised Information Linkage Databank to create a cohort of 26 820 children in Wales, UK, receiving social care services. Integrating health, social care and education data, we developed several machine learning models aimed at predicting childhood mental health problems. We assessed the performance, interpretability and fairness of these models.

Risk factors strongly associated with childhood mental health problems included age, substance misuse and being a looked after child. The best-performing model, a gradient boosting classifier, achieved an area under the receiver operating characteristic curve of 0.75 (95% CI 0.73–0.78). Assessments of algorithmic fairness showed potential biases within these models.

Machine learning performance on this prediction task was promising. Predictive performance in social care settings can be bolstered by linking diverse routinely collected data-sets, making available a range of heterogenous risk factors relating to clinical, social and environmental exposures.

Self-harm, self-poisoning or self-injury, irrespective of the motivation, is a central risk factor for suicide. Still, there is limited knowledge of self-harm among patients with substance use disorders (SUDs) who die by suicide.

We aimed to describe the prevalence of a history of self-harm and identify the factors associated with self-harm, comparing individuals who died by suicide with and without SUDs.

We used data from the Norwegian Surveillance System for Suicide in Mental Health and Substance Use Services, which is based on a national linkage between the Norwegian Cause of Death Registry and the Norwegian Patient Registry, to identify individuals who died by suicide within 1 year after last contact with mental health or substance use services (n = 1140). A questionnaire was retrieved for 1041 (91.3%) of these individuals. We used least absolute shrinkage and selection operator (LASSO) regression to select variables and compared patients with and without SUDs. Conditional selective inference was used to improve 90% confidence intervals and p-values.

The prevalence of self-harm was 55% in patients with SUDs and 52.6% in patients without SUDs. Suicidal ideation (odds ratio 2.98 (95% CI 1.74–5.10)) emerged as a factor shared with patients without SUDs, while personality disorders (odds ratio 1.96 (1.12–3.40)) and a history of violence (odds ratio 1.86 (1.20–2.87)) were unique factors for patients with SUDs.

A history of self-harm is prevalent in patients with SUDs who die by suicide and is associated with suicidal ideation, a history of violence and personality disorders in patients with SUDs.

Exposure to second-generation antipsychotics (SGAs) carries a risk of type 2 diabetes, but questions remain about the diabetogenic effects of SGAs.

To assess the diabetes risk associated with two frequently used SGAs.

This was a retrospective cohort study of adults with schizophrenia, bipolar I disorder or severe major depressive disorder (MDD) exposed during 2008–2013 to continuous monotherapy with aripiprazole or olanzapine for up to 24 months, with no pre-period exposure to other antipsychotics. Newly diagnosed type 2 diabetes was quantified with targeted minimum loss-based estimation; risk was summarised as the restricted mean survival time (RMST), the average number of diabetes-free months. Sensitivity analyses were used to evaluate potential confounding by indication.

Aripiprazole-treated patients had fewer diabetes-free months compared with olanzapine-treated patients. RMSTs were longer in olanzapine-treated patients, by 0.25 months [95% CI: 0.14, 0.36], 0.16 months [0.02, 0.31] and 0.22 months [0.01, 0.44] among patients with schizophrenia, bipolar I disorder and severe MDD, respectively. Although some sensitivity analyses suggest a risk of unobserved confounding, E-values indicate that this risk is not severe.

Using robust methods and accounting for exposure duration effects, we found a slightly higher risk of type 2 diabetes associated with aripiprazole compared with olanzapine monotherapy regardless of diagnosis. If this result was subject to unmeasured selection despite our methods, it would suggest clinician success in identifying olanzapine candidates with low diabetes risk. Confirmatory research is needed, but this insight suggests a potentially larger role for olanzapine in the treatment of well-selected patients, particularly for those with schizophrenia, given the drug's effectiveness advantage among them.