Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.     

Annual Research Review: Developmental computational psychiatry

Most psychiatric disorders emerge during childhood and adolescence. This is also a period that coincides with the brain undergoing substantial growth and reorganisation. However, it remains unclear how a heightened vulnerability to psychiatric disorder relates to this brain maturation. Here, we propose ‘developmental computational psychiatry’ as a framework for linking brain maturation to cognitive development. We argue that through modelling some of the brain's fundamental cognitive computations, and relating them to brain development, we can bridge the gap between brain and cognitive development. This in turn can lead to a richer understanding of the ontogeny of psychiatric disorders. We illustrate this perspective with examples from reinforcement learning and dopamine function. Specifically, we show how computational modelling deepens an understanding of how cognitive processes, such as reward learning, effort learning, and social learning might go awry in psychiatric disorders. Finally, we sketch the promises and limitations of a developmental computational psychiatry.     

Annual Research Review: Adolescent mental health in the digital age: facts,fears, and future directions

Adolescents are spending an increasing amount of their time online and connected to each other via digital technologies. Mobile device ownership and social media usage have reached unprecedented levels, and concerns have been raised that this constant connectivity is harming adolescents’ mental health. This review synthesized data from three sources: (a) narrative reviews and meta-analyses conducted between 2014 and 2019, (b) large-scale preregistered cohort studies and (c) intensive longitudinal and ecological momentary assessment studies, to summarize what is known about linkages between digital technology usage and adolescent mental health, with a specific focus on depression and anxiety. The review highlights that most research to date has been correlational, focused on adults versus adolescents, and has generated a mix of often conflicting small positive, negative and null associations. The most recent and rigorous large-scale preregistered studies report small associations between the amount of daily digital technology usage and adolescents’ well-being that do not offer a way of distinguishing cause from effect and, as estimated, are unlikely to be of clinical or practical significance. Implications for improving future research and for supporting adolescents’ mental health in the digital age are discussed.     

Adolescent resilience: The potential impact of personal development in schools

Abstract The challenges and stresses faced by adolescents include entry into secondary school, the development of adolescent sexuality, family conflicts, parental mental illness, socio-cultural factors, substance use and abuse, work and career abuse, social and antisocial behaviour, and the carry-over of problems from childhood. The ways in which programmes through schools can address these issues, enhance resilience and promote adolescent mental health are discussed. The potential of personal development programmes could be utilized to this end, with targeted educational and group initiatives and evaluation of outcomes.     

Editorial: Bayesian benefits for child psychology and psychiatry researchers

For many scientists, performing statistical tests has become an almost automated routine. However, p‐values are frequently used and interpreted incorrectly; and even when used appropriately, p‐values tend to provide answers that do not match researchers' questions and hypotheses well. Bayesian statistics present an elegant and often more suitable alternative. The Bayesian approach has rarely been applied in child psychology and psychiatry research so far, but the development of user‐friendly software packages and tutorials has placed it well within reach now. Because Bayesian analyses require a more refined definition of hypothesized probabilities of possible outcomes than the classical approach, going Bayesian may offer the additional benefit of sparkling the development and refinement of theoretical models in our field.     

Quebec child mental health survey: prevalence of DSM-III-R mental health disorders

The Quebec Child Mental Health Survey (QCMHS) was conducted in 1992 on a representative sample of 2400 children and adolescents aged 6 to 14 years from throughout Quebec. Prevalences of nine Axis-I DSM-III-R (American Psychiatric Association, 1987) mental health disorders were calculated based on each informant (for 6-11-year-olds: child, parent, and teacher; for 12-14-year-olds: child and parent). Informant parallelism allows the classification of results of the demographic variables associated with disorders in the logistic regression models. This strategy applies to group variables (correlates of disorders) whereas informant agreement applies to individual diagnoses. Informant parallelism implies that results for two informants or more are in the same direction and significant. In the QCMHS, informant parallelism exists for disruptive disorders, i.e. in two ADHD regression models (child and parent) higher rates among boys and young children, and in three oppositional/conduct disorders regression models (child, parent, and teacher) higher rates among boys. No informant parallelism is observed in the logistic regression models for internalizing disorders, i.e. the patterns of association of demographic variables with anxiety and depressive disorders vary across informants. Urban-rural residence does not emerge as a significant variable in any of the logistic regression models. The overall 6-month prevalences reach 19.9% according to the parent and 15.8% according to the child. The implications of the results for policy makers and clinicians are discussed.     

儿童保健临床研究进展

随着人民生活水平的提高和医学模式的转变,对保健服务的需求和利用日益扩大。儿童保健医疗服务的内容也得以不断拓展,新知识、新技术、新的服务理念不断引入。2010年儿童保健学组组织专家在全国5个城市(北京、上海、广州、武汉、成都)进行3项《建议》(生长发育评估建议、正常儿喂养建议、多种维生素补充建议)的解读与推广[1-2],     

Editorial: Ingenious designs and causal inference in child psychology and psychiatry

The embryology of behaviour – This title of a book by the great developmental psychologist Arnold Gesell (Gesell, 1945 ) continues nicely to encapsulate for me a core endeavour in child psychology and psychiatry; in the use of scientific method to tease out causes and processes within developmental science and psychopathology. This edition of JCPP includes some tremendous examples of the increasing rigour and sophistication with which such questions are being addressed. Particularly encouraging for me, as primarily an interventionist, is the use of well‐designed randomized controlled trials (RCTs) for that end.     

Transitions from care to adulthood: messages to inform practice

Transition is the process of moving from a child focussed system to an adult orientated system. It is complicated for all children and a well-recognised point of weakness in health care. For looked after children transition is more complex with movements from social worker to personal advisor, from foster care (or children's home) to independent accommodation, from school to work, further or higher education or to none of these. It is also a time when the young person moves from children's health services to adult health services. Looked after children navigate these transition points with less support than many other children. Coincidentally, it occurs at an age when mental illness most commonly emerges. This paper describes the transitions in detail, considers the legislative framework, pathway plans and the mental health transition.     

Scaling up child and adolescent mental health services in South Africa: Human resource requirements and costs

Background:  Children and adolescents with mental health problems have poor service cover in low- and middle-income countries. Little is known about the resources that would be required to provide child and adolescent mental health services (CAMHS) in these countries. The purpose of this study was to calculate the human resources and associated costs required to scale up CAMHS in South Africa.
Methods:  A spreadsheet model was developed to calculate mental health service resources, based on an estimation of the need for services in a given population. The model can be adapted to specific settings by adjusting population size, age distribution, prevalence, comorbidity, levels of coverage, service utilisation rates, workloads, length of consultations and staff profile. Steps in the modelling include population identification; estimates of prevalence, service utilisation and staffing; and costing.
Results:  Using a nominal total population of 100,000 (of which 43,170 would be children and adolescents under 20 years of age), the following full-time equivalent staff are required at minimum coverage level: 5.8 in PHC facilities, .6 in general hospital outpatient departments (OPDs), .1 in general hospital inpatient facilities, 1.1 in specialist CAMHS OPDs, .6 in specialist CAMHS inpatient facilities, .5 in specialist CAMHS day services, and .8 in regional CAMHS teams. This translates into roughly $21.50 and $5.99 per child or adolescent per annum nationally for the full coverage and minimum coverage scenarios respectively. When comparing the results of this model with current realities in South Africa, there remains a substantial shortfall in existing levels of CAMHS provision.
Conclusions:  The model can be used as an advocacy tool to engage with planners and policy makers on a rational basis. It can also be adapted for use in other countries, and is intended to support wider calls for a global scaling up of mental health services.     

Current situation and comparison of school mental health in ASEAN countries

School‐based mental health interventions are considered to have potential for the promotion of mental health in developing countries. We held a workshop to discuss the promotion of mental health in schools in southeast Asian countries. This review report aimed to summarize the current situation of school mental health in Association of Southeast Asian Nations (ASEAN) countries as reported by their representatives in this workshop. To summarize the current situation of ASEAN countries in relation to school mental health, we qualitatively analyzed the content of the discussions from four perspectives: (i) laws and regulations: (ii) mental health services; (iii) teacher training on mental health; (iv) mental health education for students. With regard to school mental health laws and regulations, this report could not provide clear conclusions because the laws were reported through the personal understanding of the public officers. Our results show that mental health services in schools are centered on professionals such as guidance counselors, although the coverage varied among the different ASEAN countries. Only Singapore conducted mental health training for teachers in a comprehensive way, and the number of people who were actually trained in other countries was very limited. Cambodia, Malaysia, Myanmar, Philippines, Singapore, and Thailand included mental health education for students in health education or life skills subjects.     

Editorial: The rise and rise of developmental perspectives in child psychology and psychiatry

When developmental psychopathology emerged as a discipline in the late 1970s and early 1980s, its proponents were as careful to explain what it was not, as they were to define what it was (e.g. Sroufe & Rutter, 1984). In particular, they differentiated developmental psychopathology from child psychiatry, which is primarily concerned with the differential diagnosis, prognosis, and treatment of childhood disorders. In contrast, developmental psychopathology was defined as ‘the study of the origins and course of individual patterns of behavioral maladaptation, whatever the age of onset, whatever the causes, whatever the transformations in behavioral manifestation, and however complex the course of the developmental pattern may be’ (Sroufe & Rutter, 1984, p. 18).     

Commentary: G × E in child psychiatry and psychology: a broadening of the scope of enquiry as prompted by Munafò et al. (2014)

The accompanying Practitioner Review by Munafò et al. (2014) presents two main arguments: (1) that there are few (if any) examples of G × E in psychiatry so it cannot aid gene discovery, and (2) that genome‐wide association studies (GWAS) are already yielding important findings. With respect to the supposed weakness of G × E research, they fail to mention any of the substantial body of evidence in support of G × E – see various chapters in Dodge and Rutter (2011).     

Genetics and child psychiatry: I Advances in quantitative and molecular genetics

Advances in quantitative psychiatric genetics as a whole are reviewed with respect to conceptual and methodological issues in relation to statistical model fitting, new genetic designs, twin and adoptee studies, definition of the phenotype, pervasiveness of genetic influences, pervasiveness of environmental influences, shared and nonshared environmental effects, and nature-nurture interplay. Advances in molecular genetics are discussed in relation to the shifts in research strategies to investigate multifactorial disorders (affected relative linkage designs, association strategies, and quantitative trait loci studies); new techniques and identified genetic mechanisms (expansion of trinucleotide repeats, genomic imprinting, mitochondrial DNA, fluorescent in-situ hybridisation, behavioural phenotypes, and animal models); and the successful localisation of genes.