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.     

Fathers' interactions with their high-risk infants

Fathers' face-to-face interactions with their 4-month-old high-risk infants were compared to mothers' interactions with the same infants and to those interactions of fathers and mothers of normal infants. The high-risk infants were less attentive and less affectively responsive than normal infants, and their mothers were more active. Fathers of both high-risk and normal infants engaged in more game playing and laughed more frequently than mothers during interactions. Although the behaviors of the normal and high-risk infants differed, as did the behaviors of mothers interacting with them, the fathers engaged in similar amounts of activity, smiling, laughing and playing games with normal and high-risk infants. Fathers may be less disturbed than mothers by their high-risk infants' lesser responsivity.     

Representations and narratives during pregnancy

In this paper, we explore how maternal representations, and in particular their contents, are structured during pregnancy. Twenty-three primiparous women were recruited for participation in a longitudinal study about mothers' thoughts and feelings about their infants. A semistructured interview was conducted with each of the subjects in the third trimester of pregnancy. During the interview, subjects were also given five adjective lists based on the semantic differential model. Results from this sample indicate similarities in the content-free aspects of representations of self and baby, but differences in the content of these presentations. Implications of these results are discussed with regard to the construction of an internal representation of the child in the third trimester of pregnancy.     

Neonatal stress and coping in intensive care

Examples are given of research on (a) stressful procedures and assessments in the neonatal intensive care nursery and (b) natural caregiving stimulation and self-comforting behaviors that alleviate these stressful experiences. The data from the studies on stressful procedures and assessments revealed that (a) weaning from mechanical ventilation was associated with increased plasma cortisol levels; (b) heelsticks and tube insertions for gavage feedings were accompanied by decreases in oxygen tension (TcPO2); and (c) Brazelton neonatal behavior assessments were followed by increased cortisol levels and decreased growth hormone levels. To alleviate stress, various interventions were tried including caregiver comforting techniques and giving the neonates opportunities to comfort themselves by sucking on pacifiers. The caregiver intervention studies revealed that (a) a simple placement of hands on the head and abdomen of the NICU neonate resulted in a lesser need for oxygen and (b) massaging the NICU neonate resulted in greater weight gain and earlier discharge. In those studies that explored the infant's self-comforting, nonnutritive sucking behavior, the following results emerged: (a) sucking on pacifiers during heelsticks resulted in less crying and lower heart rate and respiration and (b) sucking on pacifiers during tube feedings resulted in smoother bottle feedings later and in greater weight gain. Thus, it appears that several forms of cost-effective interventions can alleviate these stressful procedures and facilitate infant growth and development.     

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.     

Mothers' Perceptions of Infants Labelled ‘Depressed’

Forty-four depressed and non-depressed mothers participated in a videotaped interaction with their own infant and then rated the videotape using the Infant Stereotyping Scale and the Interaction Rating Scale. In addition, one half of the mothers rated a videotape of an unfamiliar infant who was labelled psychologically ‘depressed’ and the other half rated a videotape of the same infant with no label given. Both the depressed and non-depressed mothers rated the ‘depressed’ labelled infant more negatively than the non-labelled infant on the attributes of physical potency, cognitive competence, sociability and difficult behaviour. Physical appearance was the only rating that was not biased by the ‘depressed’ label. Mothers' ratings of their own infants were more positive than their ratings of the non-labelled stimulus infant. Depressed mothers did not see their infants more negatively except on one rating. They rated the physical appearance of their own infant more negatively than non-depressed mothers.     

Infants of “depressed” mothers interact better with their nondepressed fathers

To determine whether infants of “depressed” mothers interact better with their nondepressed fathers, twenty-six 3- to 6-month-old infants were videotaped during face-to-face interactions with their parents. The “depressed” mother group consisted of twelve 3- to 6-month-old infants and their “depressed” mothers and nondepressed fathers. The control group was composed of 14 nondepressed mothers and nondepressed fathers and their 3- to 6-month-old infants. In the “depressed” mother group, the nondepressed fathers received better interaction ratings than the “depressed” mothers. In turn, the infants received better interaction ratings when they interacted with their nondepressed fathers than with their “depressed” mothers. In contrast, nondepressed fathers and mothers and their infants in the control group did not differ on any of their interaction ratings. These findings suggest that infants' difficult interaction behaviors noted during interactions with their “depressed” mothers may not extend to their nondepressed fathers. The data are discussed with respect to the notion that nondepressed fathers may “buffer” the effects of maternal depression on infant interaction behavior.     

Readers and service commissioners require clear financial disclosures: Comment on innovation,research integrity,and change: A conflict of interest management framework for program developers (Sanders et al., 2019)

Sanders et al.'s proposal for a management framework for conflicting interests among program developers is very welcome. The underlying principles of such a framework must nevertheless prioritise the need for researchers and commissioners of services to make objective assessments of the impact of interventions reported in journal articles. This is particularly important in the field of randomised trials which may influence public sector expenditure. Using a strict definition derived from known financial conflict of interest, we have demonstrated that child-based effect sizes are much lower for independent studies than for studies with developer involvement. On this basis, we propose that journals publishing evaluations of psychosocial interventions should agree a standardised format for declarations of conflicts of interest based on that recommended by the International Committee of Medical Journal Editors.     

Is future self-relevance necessary to increase saving for retirement? A replication study

Insufficient saving for retirement is one consequence of excessive discounting of the future but attempts to mitigate it often involve costly or time-intensive personalized interventions. Marques, Mariano, Lima, and Abrams, by contrast, found that using a generic Future Time Perspective questionnaire to increase future “self-relevance” was an effective method to increase money allocation to retirement when the salience of future aging was also higher. Originally conducted in Portugal, the present study aimed to replicate Marques et al’s findings in the UK context. In the present study (n = 219), participants were shown a website advertising a financial product. The results support Marques and colleagues’ assertion that, alone, a website priming future aging was insufficient to increase retirement savings in a money allocation task. However, in contrast to Marques et al’s original findings, we find no evidence that future self-relevance moderates the effect such that priming future aging becomes effective when individuals have higher future self-relevance. Instead, we find that aging primes are ineffective at increasing retirement saving regardless of whether individuals are high or low in future self-relevance. Possible explanations for this discrepancy in findings, including methodological and cultural differences, are explored as well as directions for future research.     

A Two-way Street: Mentor Stress and Depression Influence Relational Satisfaction and Attachment in Youth Mentoring Relationships

Over the past two decades, youth mentoring programs have increased in popularity as an intervention for children exposed to a range of stressful life circumstances. Such programs have been shown to promote positive youth development and reduce risk for emotional and behavioral problems; yet, the effect size of youth gains remains small. The current study examined the influence of college student mentors’ history of early life stress and baseline depressive symptoms on their effectiveness in youth mentoring relationships using 340 randomized mentor–youth pairs from College Mentors for Kids, a well-established mentoring program with chapters across the United States. Hierarchical linear models revealed that mentors with higher levels of depressive symptoms reported lower relationship satisfaction and increased avoidance in the mentoring relationship. In contrast, mentors who experienced higher levels of early life stress had youth who reported greater satisfaction in the mentoring relationship and decreased relational anxiety. These findings are some of the first to examine the impact of mentor characteristics on mentor–youth relationships and highlight the importance of considering factors relevant to psychosocial functioning and emotional distress when recruiting, training, and supporting college student mentors.