In 2021, Solent NHS Trust advertised for a fully remote consultant psychiatrist to meet increasing clinical demand. This pilot scheme was evaluated to determine its success. The job applications underwent content analysis, recruitment and support staff were interviewed, and in-depth rolling interviews were conducted with the three now-employed virtual psychiatrists.

We have gained an objective understanding of this new and innovative way of working and, overall, shown that fully remote working in the National Health Service (NHS) is feasible.

The findings were used to create a step-by-step guide for the remote hiring process, which outlines the necessary steps for conducting it in a safe, swift and successful way. This guide could help other NHS organisations to advertise, recruit and manage fully remote employees.

Depression is a significant mental health concern affecting the overall well-being of adolescents and young adults. Recently, the prevalence of depression has increased among young people. Nonetheless, there is little research delving into the longitudinal epidemiology of adolescent depression over time.

To investigate the longitudinal epidemiology of depression among adolescents and young adults aged 10–24 years.

Our research focused on young people (aged 10–24 years) with depression, using data from the Global Burden of Diseases, Injuries, and Risk Factors Study 2019. We explored the age-standardised prevalence, incidence and disability-adjusted life-years (DALYs) of depression in different groups, including various regions, ages, genders and sociodemographic indices, from 1990 to 2019.

The prevalence, incidence and DALYs of depression in young people increased globally between 1990 and 2019. Regionally, higher-income regions like High-Income North America and Australasia recorded rising age-standardised prevalence and incidence rates, whereas low- or middle-income regions mostly saw reductions. Nationally, countries such as Greenland, the USA and Palestine reported the highest age-standardised prevalence and incidence rates in 2019, whereas Qatar witnessed the largest growth over time. The burden disproportionately affected females across age groups and world regions. The most prominent age effect on incidence and prevalence rates was in those aged 20–24 years. The depression burden showed an unfavourable trend in younger cohorts born after 1980, with females reporting a higher cohort risk than males.

Between 1990 and 2019, the general pattern of depression among adolescents varied according to age, gender, time period and generational cohort, across regions and nations.

Internet-based interventions produce comparable effectiveness rates as face-to-face therapy in treating depression. Still, more than half of patients do not respond to treatment. Machine learning (ML) methods could help to overcome these low response rates by predicting therapy outcomes on an individual level and tailoring treatment accordingly. Few studies implemented ML algorithms in internet-based depression treatment using baseline self-report data, but differing results hinder inferences on clinical practicability. This work compares algorithms using features gathered at baseline or early in treatment in their capability to predict non-response to a 6-week online program targeting depression.

Our training and test sample encompassed 1270 and 318 individuals, respectively. We trained random forest algorithms on self-report and process features gathered at baseline and after 2 weeks of treatment. Non-responders were defined as participants not fulfilling the criteria for reliable and clinically significant change on PHQ-9 post-treatment. Our benchmark models were logistic regressions trained on baseline PHQ-9 sum or PHQ-9 early change, using 100 iterations of randomly sampled 80/20 train-test-splits.

Best performances were reached by our models involving early treatment characteristics (recall: 0.75–0.76; AUC: 0.71–0.77). Therapeutic alliance and early symptom change constituted the most important predictors. Models trained on baseline data were not significantly better than our benchmark.

Fair accuracies were only attainable by involving information from early treatment stages. In-treatment adaptation, instead of a priori selection, might constitute a more feasible approach for improving response when relying on easily accessible self-report features. Implementation trials are needed to determine clinical usefulness.

This paper aims to synthesise the literature on machine learning (ML) and big data applications for mental health, highlighting current research and applications in practice.

We employed a scoping review methodology to rapidly map the field of ML in mental health. Eight health and information technology research databases were searched for papers covering this domain. Articles were assessed by two reviewers, and data were extracted on the article's mental health application, ML technique, data type, and study results. Articles were then synthesised via narrative review.

Three hundred papers focusing on the application of ML to mental health were identified. Four main application domains emerged in the literature, including: (i) detection and diagnosis; (ii) prognosis, treatment and support; (iii) public health, and; (iv) research and clinical administration. The most common mental health conditions addressed included depression, schizophrenia, and Alzheimer's disease. ML techniques used included support vector machines, decision trees, neural networks, latent Dirichlet allocation, and clustering.

Overall, the application of ML to mental health has demonstrated a range of benefits across the areas of diagnosis, treatment and support, research, and clinical administration. With the majority of studies identified focusing on the detection and diagnosis of mental health conditions, it is evident that there is significant room for the application of ML to other areas of psychology and mental health. The challenges of using ML techniques are discussed, as well as opportunities to improve and advance the field.

With prevention and treatment of mental disorders a challenge for primary care and increasing capability of electronic medical records (EMRs) to facilitate research in practice, we aim to determine the prevalence and treatment of mental disorders by using routinely collected clinical data contained in EMRs.

We reviewed EMRs of patients randomly sampled from seven general practices, by piloting a study instrument and extracting data on mental disorders and their treatment.

Data were collected on 690 patients (age range 18–95, 52% male, 52% GMS-eligible). A mental disorder (most commonly anxiety/stress, depression and problem alcohol use) was recorded in the clinical records of 139 (20%) during the 2-year study period. While most patients with the common disorders had been prescribed medication (i.e. antidepressants or benzodiazepines), a minority had been referred to other agencies or received psychological interventions. ‘Free text’ consultation notes and ‘prescriptions’ were how most patients with disorders were identified. Diagnostic coding alone would have failed to identify 92% of patients with a disorder.

Although mental disorders are common in general practice, this study suggests their formal diagnosis, disease coding and access to psychological treatments are priorities for future research efforts.

Identifying patients with chronic musculoskeletal pain using database searches is difficult, as chronic pain is not represented with a unique diagnostic code in electronic primary care records.

This paper describes the development and implementation of a search strategy to identify patients with chronic musculoskeletal pain in primary care databases to invite them to participate in a randomised controlled trial.

We used an exploratory, iterative approach. The first phase involved consultations with IT specialists, practice managers and doctors to gain an understanding about the processes and issues of electronic coding. In the second and third phases, we determined the most appropriate search terms and strategies. In the final phase, we tested, modified and re-tested the search strategy until the quantity and quality of the output appeared good enough to be used in general practices with different IT systems. This strategy was then implemented to recruit participants for a trial.

We identified three main search ‘domains’: prescribing, coding and attendance. We found the most useful identifier for chronic pain was the use of repeat medication. Wide variations in coding terms for chronic pain were seen between practices and individuals. Understanding ‘coding cultures’ were necessary to inform the electronic searches. In the case of chronic pain, searching on repeat medication for analgesia, low dose antidepressants and carefully selected coding terms captured most relevant patients.