Prediction of mental effort derived from an automated vocal biomarker using machine learning in a large-scale remote sample.

Introduction: Biomarkers of mental effort may help to identify subtle cognitive impairments in the absence of task performance deficits. Here, we aim to detect mental effort on a verbal task, using automated voice analysis and machine learning. Methods: Audio data from the digit span backwards task were recorded and scored with automated speech recognition using the online platform NeuroVocalixTM, yielding usable data from 2,764 healthy adults (1,022 male, 1,742 female; mean age 31.4 years). Acoustic features were aggregated across each trial and normalized within each subject. Cognitive load was dichotomized for each trial by categorizing trials at >0.6 of each participants' maximum span as "high load." Data were divided into training (60%), test (20%), and validate (20%) datasets, each containing different participants. Training and test data were used in model building and hyper-parameter tuning. Five classification models (Logistic Regression, Naive Bayes, Support Vector Machine, Random Forest, and Gradient Boosting) were trained to predict cognitive load ("high" vs. "low") based on acoustic features. Analyses were limited to correct responses. The model was evaluated using the validation dataset, across all span lengths and within the subset of trials with a four-digit span. Classifier discriminant power was examined with Receiver Operating Curve (ROC) analysis. Results: Participants reached a mean span of 6.34 out of 8 items (SD = 1.38). The Gradient Boosting classifier provided the best performing model on test data (AUC = 0.98) and showed excellent discriminant power for cognitive load on the validation dataset, across all span lengths (AUC = 0.99), and for four-digit only utterances (AUC = 0.95). Discussion: A sensitive biomarker of mental effort can be derived from vocal acoustic features in remotely administered verbal cognitive tests. The use-case of this biomarker for improving sensitivity of cognitive tests to subtle pathology now needs to be examined.

Health Professionals' Perspectives on the Nature of Distress and Low Mood in Young People with Cancer.

PURPOSE: Young people with cancer are at increased risk of depression, yet evidence-based psychological interventions that are tailored to the specific needs of young people with cancer are scarce, and depression in this group may be particularly challenging to recognize and treat. The aims of this study were to (1) explore the views of health professionals in recognizing and treating low mood in young people with cancer and (2) identify the key components of an effective online treatment package for depression in this population. METHODS: Eighteen NHS health professionals with a range of professional backgrounds working directly with young people with cancer were interviewed using a semi-structured interview schedule. Responses were analyzed using thematic analysis. RESULTS: Five themes emerged: (1) one size doesn't fit all-the nature of depression is complex and varied, and symptoms fluctuate greatly in relation to physical health; (2) distress is completely understandable-it is important not to pathologize a normal reaction; (3) a stepping stone intervention-online interventions may promote engagement with face-to-face therapy; (4) connecting with others-the intervention should promote sharing experiences with others to reduce isolation; and (5) ownership and empowerment-lack of independence may be a cause of distress, and young people should have control of the intervention. CONCLUSION: The nature of depression in young people with cancer is complex and multifaceted. Online guided self-help may be useful when added as a component or first step of a treatment package including face-to-face talking therapies.

A Brain Marker for Developmental Speech Disorders.

OBJECTIVE: To characterize the organization of speech- and language-related white matter tracts in children with developmental speech and/or language disorders. STUDY DESIGN: We collected magnetic resonance diffusion-weighted imaging data from 41 children, ages 9-11 years, with developmental speech and/or language disorders, and compared them with 45 typically developing controls with the same age range. We used probabilistic tractography of diffusion-weighted imaging to map language (3 segments of arcuate fasciculus, extreme capsule system) and speech motor (corticobulbar) tracts bilaterally. The corticospinal and callosal tracts were used as control regions. We compared the mean fractional anisotropy and diffusivity values between atypical and control groups, covarying for nonverbal IQ. We then examined differences between atypical subgroups: developmental speech disorder (DSD), developmental language disorder, and co-occurring developmental speech and language disorder. RESULTS: Fractional anisotropy in the left corticobulbar tract was lower in the DSD than in the control group. Radial and mean diffusivity were higher in the DSD than the developmental language disorder, co-occurring developmental speech and language disorder, or control groups. There were no group differences for any metrics in the language or control tracts. CONCLUSIONS: Atypical development of the left corticobulbar tract may be a neural marker for DSD. This finding is in line with reports of speech disorder after left corticobulbar damage in children and adults with brain injury. By contrast, we found no association between diffusion metrics in language-related tracts in developmental language disorder, and changes for language disorders are likely more complex.

The Organization of Working Memory Networks is Shaped by Early Sensory Experience.

Early deafness results in crossmodal reorganization of the superior temporal cortex (STC). Here, we investigated the effect of deafness on cognitive processing. Specifically, we studied the reorganization, due to deafness and sign language (SL) knowledge, of linguistic and nonlinguistic visual working memory (WM). We conducted an fMRI experiment in groups that differed in their hearing status and SL knowledge: deaf native signers, and hearing native signers, hearing nonsigners. Participants performed a 2-back WM task and a control task. Stimuli were signs from British Sign Language (BSL) or moving nonsense objects in the form of point-light displays. We found characteristic WM activations in fronto-parietal regions in all groups. However, deaf participants also recruited bilateral posterior STC during the WM task, independently of the linguistic content of the stimuli, and showed less activation in fronto-parietal regions. Resting-state connectivity analysis showed increased connectivity between frontal regions and STC in deaf compared to hearing individuals. WM for signs did not elicit differential activations, suggesting that SL WM does not rely on modality-specific linguistic processing. These findings suggest that WM networks are reorganized due to early deafness, and that the organization of cognitive networks is shaped by the nature of the sensory inputs available during development.

The Effectiveness of Psychosocial Interventions for Psychological Outcomes in Pediatric Oncology: A Systematic Review.

CONTEXT: This review summarizes the current randomized controlled trials literature on psychological and physical outcomes of psychosocial interventions in pediatric oncology. OBJECTIVES: The objective of this study was to evaluate the effectiveness and impact of psychosocial interventions in children with cancer. METHODS: A search of the literature resulted in a total of 12 randomized clinical trials and these have evaluated psychosocial interventions in children younger than 18 years with current and previous diagnoses of cancer. Outcome measures were both psychological (e.g., symptoms of anxiety, depression, quality of life, and self-esteem) and physical (e.g., cancer symptoms, treatment adherence, and pain). Interventions identified included cognitive behavioral therapy (CBT; n = 4), joint CBT and physical exercise therapy (n = 1), family therapy (n = 2), therapeutic music video (n = 2), self-coping strategies (n = 1), a wish fulfillment intervention (n = 1), and joint family therapy and CBT (n = 1). RESULTS: Nine studies reported statistically significant improvements on psychological outcomes. These findings suggest that psychosocial interventions are effective at reducing anxiety and depressive symptoms as well as improving quality of life. Additionally, six studies found psychosocial interventions to have a positive impact on physical symptoms and well-being, including a reduction in procedural pain and symptom distress. CONCLUSION: These findings suggest that mental health needs in pediatric oncology patients can and should be addressed, potentially which will lead to better mental and physical health outcomes.

The English Version of the Gilles de la Tourette Syndrome-Quality of Life Scale for Children and Adolescents (C&A-GTS-QOL).

Gilles de la Tourette syndrome is a chronic neuropsychiatric disorder that can have a detrimental impact on the health-related quality of life of children with the condition. To date no patient-reported health-related quality of life measures have been developed for children and adolescents in the English language. This study validated the first disease-specific scale for the quantitative assessment of health-related quality of life in 118 children and adolescents with Gilles de la Tourette syndrome (C&A-GTS-QOL) following language adaptation from Italian to English in the United Kingdom. Standard statistical methods were used to test the psychometric properties of the rating scale. Principal component factor analyses led to the identification of six health-related quality of life domains (cognitive, copro-phenomena, psychological, physical, obsessive-compulsive, and activities of daily living), explaining 66.7% of the overall variance. The C&A-GTS-QOL demonstrated satisfactory scaling assumptions and acceptability; validity was supported by interscale correlations (range 0.2-0.7), confirmatory factor analysis, and correlation patterns with other rating scales and clinical variables.