A systematic review of the effectiveness of machine learning for predicting psychosocial outcomes in acquired brain injury: Which algorithms are used and why?

Clinicians working in the field of acquired brain injury (ABI, an injury to the brain sustained after birth) are challenged to develop suitable care pathways for an individual client’s needs. Being able to predict psychosocial outcomes after ABI would enable clinicians and service providers to make advance decisions and better tailor care plans. Machine learning (ML, a predictive method from the field of artificial intelligence) is increasingly used for predicting ABI outcomes. This review aimed to examine the efficacy of using ML to make psychosocial predictions in ABI, evaluate the methodological quality of studies, and understand researchers’ rationale for their choice of ML algorithms. Nine studies were reviewed from five databases, predicting a range of psychosocial outcomes from stroke, traumatic brain injury, and concussion. Eleven types of ML were employed with a total of 75 ML models. Every model was evaluated as having high risk of bias, unable to provide adequate evidence for predictive performance due to poor methodological quality. Overall, there was limited rationale for the choice of ML algorithms and poor evaluation of the methodological limitations by study authors. Considerations for overcoming methodological shortcomings are discussed, along with suggestions for assessing the suitability of data and suitability of ML algorithms for different ABI research questions.     

The Nature of Client Agency Prior to Therapy: A Qualitative Study on Clients’ Narratives

Client agency is considered a crucial contributor to good treatment outcome. Recent studies, however, differ strongly in how they conceptualise and investigate agency. The current study explores the nature of client agency in ten clients’ pre-treatment interviews. Applying Consensual Qualitative Research, we constructed three overarching categories, subdivided into 14 sub-categories capturing both between- and within-person differences in agency before therapy. We found that all participants oscillated between the experience of a lack of grip on problems on the one hand and noticing their involvement in the problem and taking action on the other. These results present a dynamic conceptualisation of client agency. This allows us to ask pertinent questions for both future research and clinical practice.     

Regression II. Development through regression

As shown in our previous paper (‘Regression I. Experimental approaches to regression’, JAP, 65, 2, 345-65), the common mechanism of regression can be described as reversible dedifferentiation, which is understood as a relative increase of the proportion of low-differentiated (older) systems in actualized experience. Experimental data show that regression following disease (chronic tension headache) is followed by adaptation and an increase in system differentiation in that experience domain which contains systems responsible for that adaptation. The results of mathematical modelling support the idea that reversible dedifferentiation can be one of the mechanisms for increasing the effectiveness of adaptation through learning. Reversible dedifferentiation, which is phenomenologically described as regression, is a general mechanism for restructuring the organism-environment interactions in situations where behaviours that were effective in the past become ineffective. Reversible dedifferentiation has evolved as a component of adaptation when new behaviours are formed and large-scale modifications in the existing behaviours are required in the face of changes in the external and/or internal environment. Thus, the authors believe that this article provides evidence for Jung’s view that regression is not only a ‘return’ to past forms of thinking, affects and behaviour, but that regressive processes provide a significant impetus for psychological growth and development.     

Self-Compassion and Need Frustration Moderate the Effects of Upward Appearance Comparisons on Body Image Discrepancies

Abstract

Drawing from diverse theoretical frameworks, we examined predictors of discrepancy between current and ideal body image in a sample of 396 Greek adolescents. The participants completed assessments of the frequency of comparing oneself with someone of perceived better appearance, appearance evaluations, frustration of basic psychological needs, and appearance self-compassion. We found that upward appearance comparisons negatively predicted appearance evaluation, which in turn was a negative predictor of body image discrepancy. Moderated mediation analyses showed that appearance self-compassion buffered, whereas psychological need frustration augmented the negative effects of upward comparisons on appearance evaluation. Our findings contribute to the growing literature on body image discrepancies in adolescence by examining moderating factors that amplify or buffer such discrepancies, hence identifying viable intervention pathways.     

Guilt feelings and the intelligibility of moral duties

G.E.M. Anscombe argued that we should dispense with deontic concepts when doing ethics, if it is psychologically possible to do so. In response, I contend that deontic concepts are constitutive of the common moral experience of guilt. This has two consequences for Anscombe's position. First, seeing that guilt is a deontic emotion, we should recognize that Anscombe's qualification on her thesis applies: psychologically, we need deontology to understand our obligations and hence whether our guilt is warranted. Second, the fact that guilt is a deontic moral emotion debunks Anscombe's claim that deontic concepts are a relic of the Western, religious past: guilt feelings–hence the idea of moral duty as well–can be found in cultures without an ethics of divine command. Modern moral philosophers' interest in oughts and obligations is not an academic hobbyhorse, but a vital concern arising out of a primeval human emotion.     

The relationship between dysfunctional metacognitive beliefs and problematic social networking sites use

Social networking sites (SNSs) enrol new subscribers each day. However, problematic SNS use has undesirable effects on psychological functioning. Therefore, it is important to identify the factors that contribute to the development of problematic SNS use. Very few studies have focused on revealing the underlying mechanisms of problematic SNS use. Although many past studies have examined the relationship between metacognitive beliefs and Internet addiction, the association between metacognitive beliefs and problematic SNS use has not been adequately explored. In this study, we aimed to explore the association between metacognitive beliefs and problematic SNS use among young adults. A total of 308 individuals participated in this study. A socio-demographic data form, the Metacognitions Questionnaire-30 (MCQ-30), and Social Media Addiction Scale (SMAS) were administered. Group comparisons were performed using multivariate analysis of covariance. Pearson's correlational and multiple linear regression analyses were conducted to examine the associations between metacognitive beliefs and problematic SNS use. The SNS addicts scored higher in all of the SMAS assessments. When compared to non-addicts, SNS addicts obtained higher scores on all the subtests of the SMAS and MCQ-30 except cognitive self-consciousness. The negative beliefs about the uncontrollability and danger of worry, cognitive confidence, and need for control thoughts were associated with SMAS mood modification, relapse and conflict subdimensions. Our findings revealed that dysfunctional metacognitive beliefs are related to problematic SNS use among young adults. These findings indicate that mental health workers should consider the modification of metacognitive beliefs in the treatment of problematic SNS use.     

Counseling Military Populations: A Content Analysis of Counseling Journals From 1998 to 2018

Mental health scholarship of military populations is largely guided by researchers in psychiatry and psychology. Recent advocacy efforts have created increased opportunities for professional counselors to serve military clients, but the research within the profession has yet to be explored. A content analysis of 23 professional counseling journals from June 1998 to June 2018 was conducted to determine military population research trends. Findings indicated that counselors are researching topics similar to those of other mental health fields, such as posttraumatic stress, but are contributing to those topics conceptually rather than empirically. Topical areas in which counselors do produce more empirical studies include career counseling, and these studies relied on college student veteran populations. Suggestions for incorporating the philosophical principles of counseling into future research are provided to inform the trajectory of military scholarship in the profession.     

Psychometric and Validity Issues in Machine Learning Approaches to Personality Assessment: A Focus on Social Media Text Mining

In the age of big data, substantial research is now moving toward using digital footprints like social media text data to assess personality. Nevertheless, there are concerns and questions regarding the psychometric and validity evidence of such approaches. We seek to address this issue by focusing on social media text data and (i) conducting a review of psychometric validation efforts in social media text mining (SMTM) for personality assessment and discussing additional work that needs to be done; (ii) considering additional validity issues from the standpoint of reference (i.e. ‘ground truth’) and causality (i.e. how personality determines variations in scores derived from SMTM); and (iii) discussing the unique issues of generalizability when validating SMTM for personality assessment across different social media platforms and populations. In doing so, we explicate the key validity and validation issues that need to be considered as a field to advance SMTM for personality assessment, and, more generally, machine learning personality assessment methods. © 2020 European Association of Personality Psychology