Machine learning methods are being increasingly applied to physical healthcare. In this article we describe some of the potential benefits, challenges and limitations of this approach in a mental health context. We provide a number of examples where machine learning could add value beyond conventional statistical modelling.

Society is undergoing a shift in gender politics. Science and medicine are part of this conversation, not least as women's representation and pay continue to drop as one progresses through more senior academic and clinical levels. Naming and redressing these inequalities needs to be a priority for us all.

Conventional approaches to evidence that prioritise randomised controlled trials appear increasingly inadequate for the evaluation of complex mental health interventions. By focusing on causal mechanisms and understanding the complex interactions between interventions, patients and contexts, realist approaches offer a productive alternative. Although the approaches might be combined, substantial barriers remain.

In this editorial, we argue that current attitudes toward terminally ill patients are generally too paternalistic, and that it is wrong to assume that patients suffering from mental health issues (including depression) cannot consent to assisted suicide.

The DSM-5 definition of bipolar disorder elevates increased activity or energy as a cardinal symptom (alongside mood changes) for mania and hypomania (‘hypo/mania’). The ICD-10 likewise requires increases in activity and energy (alongside mood) for hypo/mania, as well as decreases for bipolar depression. Using bipolar disorder as an example, we propose that, when diagnostic criteria are revised, instruments used to measure clinical course and treatment response may need revisiting. Here, we highlight that the ‘gold-standard’ symptom rating scales for hypo/mania and depression were developed in an era when abnormalities of mood were viewed as the cardinal symptom of bipolar disorder. We contend that archetypal measures fail to give proportionate weighting to activity or energy, undermining their utility in monitoring bipolar disorder and treatment response in clinical and research practice.

The nature and extent of the sexual abuse of children and young people and the pervasiveness of inappropriate institutional responses to its occurrence continues to raise serious concerns. The work of the Inquiry is a powerful reminder of the role of mental health services in addressing the needs of victims and survivors.

In this paper, we explore ethnic inequalities in severe mental illness and care experiences. We consider the barriers to progressive and cohesive action and propose ways of overcoming these. Clinical and policy leadership must bring together hidden patient voices, divergent professional narratives and quality research.

Gender inequality and discrimination, as well as violence and victimisation towards women, have recently hit the headlines creating a media furore. We provide a timely discussion surrounding the impact of these issues on women's mental health and a discussion of the role of psychiatry in this context.

In this editorial, I suggest that no psychiatrist should be without a working knowledge of attachment theory, and it is a capability that all trainees should cover in the proposed new curriculum. I have focused on three domains of research to argue that attachment theory is relevant to practicing psychiatrists.

In this issue, Stigsdotter et al show that nature gardens offer similar benefits to cognitive–behavioural therapy for managing stress-related illnesses among people on sick leave. There is scope for pragmatic trials to establish the processes involved and highlight the co-benefits that nature gardens offer for health and the environment.

The 2015 Supreme Court judgment in Montgomery v Lanarkshire Health Board [2015] UKSC 11 established that consent to medical treatment requires shared decision-making based on dialogue between the clinician and patient. In this editorial, we examine what Montgomery means for standards of good psychiatric practice, and argue that it represents an opportunity for delivering best practice in psychiatric care.

Although antidepressant drugs are commonly effective, several meta-analyses of antidepressant drug trials undertaken decades after their introduction suggested that they were effectively acting as placebos. A recent meta-analysis concluded that they were effective. Both conclusions have been widely taken up by the media. This paper seeks to explain the disconnect.

Should psychiatrists be able to speculate in the press or social media about their theories? John Gartner argues the risk to warn the public of concerns about public figures overrides the duty of confidentiality; whereas Alex Langford suggests this is beyond the ethical remit of psychiatric practice.