Search

Contains fulltext : 237675.pdf (Publisher’s version ) (Open Access), In the face of the COVID-19 pandemic, the swift response of mental health research funders and institutions, service providers, and academics enabled progress toward understanding the mental health consequences. Nevertheless, there remains an urgent need to understand the true extent of the short- and long-term effects of the COVID-19 pandemic on mental health, necessitating ongoing research. Although the speed with which mental health researchers have mobilized to respond to the pandemic so far is to be commended, there are valid concerns as to whether speed may have compromised the quality of our work. As the pandemic continues to evolve, we must take time to reflect on our initial research response and collectively consider how we can use this to strengthen ensuing COVID-19 mental health research and our response to future crises. Here, we offer our reflections as members of the UK mental health research community to discuss the continuing progress and persisting challenges of our COVID-19 response, which we hope can encourage reflection and discussion among the wider research community. We conclude that (1) Fragmentation in our infrastructure has challenged the efficient, effective and equitable deployment of resources, (2) In responding quickly, we may have overlooked the role of experts by experience, (3) Robust and open methods may have been compromised by speedy responses, and (4) This pandemic may exacerbate existing issues of inequality in our workforce.

Contains fulltext : 218229.pdf (publisher's version ) (Open Access), Background: The predictive accuracy of suicidal behaviour has not improved over the last decades. We aimed to explore the potential of machine learning to predict future suicidal behaviour using population-based longitudinal data. Method: Baseline risk data assessed within the Scottish wellbeing study, in which 3508 young adults (18-34 years) completed a battery of psychological measures, were used to predict both suicide ideation and suicide attempts at one-year follow-up. The performance of the following algorithms was compared: regular logistic regression, K-nearest neighbors, classification tree, random forests, gradient boosting and support vector machine. Results: At one year follow up, 2428 respondents (71%) finished the second assessment. 336 respondents (14%) reported suicide ideation between baseline and follow up, and 50 (2%) reported a suicide attempt. All performance metrics were highly similar across methods. The random forest algorithm was the best algorithm to predict suicide ideation (AUC 0.83, PPV 0.52, BA 0.74) and the gradient boosting to predict suicide attempt (AUC 0.80, PPV 0.10, BA 0.69). Limitations: The number of respondents with suicidal behaviour at follow up was small. We only had data on psychological risk factors, limiting the potential of the more complex machine learning algorithms to outperform regular logistical regression. Conclusions: When applied to population-based longitudinal data containing multiple psychological measurements, machine learning techniques did not significantly improve the predictive accuracy of suicidal behavior. Adding more detailed data on for example employment, education or previous health care uptake, might result in better performance of machine learning over regular logistical regression.

Background Psychological treatments occupy an important place in evidence-based mental health treatments. Now is an exciting time to fuel treatment research: a pressing demand for improvements is poised alongside new opportunities from closer links with sister scientific and clinical disciplines. The need to improve mental health treatment is great; even the best treatments do not work for everyone, treatments have not been developed for many mental disorders, and the implementation of treatments needs to address worldwide scalability. Psychological treatments have yet to benefit from numerous innovations that have occurred in science, particularly those that have emerged in the past 20 years, and arguably vice versa. This Commission comprises ten parts that each outline an area in which we see substantial opportunity and scope for advancements that will move psychological treatments research forward.

The debate about the relative importance of nature versus nurture has been around for decades, but despite this, there has been very little evidence about how these might in fact interact to drive evolution in the wild. Recently, the identification of a comparable methodology for analyzing both genetic and social effects of phenotypic variation, revealed that fitness variation in a free-living population of dolphin was driven by a strong social and genetic interaction. This study not only provides evidence that nature and nurture do interact to drive phenotypic evolution but also represents a step towards partitioning the effects of genetic, social, environmental factors, and their multiway interactions to better understand phenotypic evolution in the wild.