Search

IntroductionThis work explores the use of an automated facial coding software - FaceReader - as an alternative and/or complementary method to manual coding.MethodsWe used videos of parents (fathers, n = 36; mothers, n = 29) taken from the Avon Longitudinal Study of Parents and Children. The videos—obtained during real-life parent-infant interactions in the home—were coded both manually (using an existing coding scheme) and by FaceReader. We established a correspondence between the manual and automated coding categories - namely Positive, Neutral, Negative, and Surprise - before contingency tables were employed to examine the software’s detection rate and quantify the agreement between manual and automated coding. By employing binary logistic regression, we examined the predictive potential of FaceReader outputs in determining manually classified facial expressions. An interaction term was used to investigate the impact of gender on our models, seeking to estimate its influence on the predictive accuracy.ResultsWe found that the automated facial detection rate was low (25.2% for fathers, 24.6% for mothers) compared to manual coding, and discuss some potential explanations for this (e.g., poor lighting and facial occlusion). Our logistic regression analyses found that Surprise and Positive expressions had strong predictive capabilities, whilst Negative expressions performed poorly. Mothers’ faces were more important for predicting Positive and Neutral expressions, whilst fathers’ faces were more important in predicting Negative and Surprise expressions.DiscussionWe discuss the implications of our findings in the context of future automated facial coding studies, and we emphasise the need to consider gender-specific influences in automated facial coding research.

Background: Poor sleep is a common problem in adolescents aged 14 to 18 years. Difficulties with sleep have been found to have a bidirectional link to mental health problems., Objective: This new research sought to involve young people in the co-creation of a new app, particularly those from underserved communities. The Sleep Solved app uses science-based advice to improve sleep-related behaviors and well-being. The app was developed using the person-based approach, underpinned by the social cognitive theory and the social-ecological model of sleep health., Methods: Young people (aged 14-18 y) were recruited from across the United Kingdom to contribute to patient and public involvement (PPI) activities. In partnership with our peer researcher (MHJ), we used a multitude of methods to engage with PPI contributors, including web-based workshops, surveys, think-aloud interviews, focus groups, and app beta testing., Results: A total of 85 young people provided PPI feedback: 54 (64%) young women, 27 (32%) young men, 2 (2%) genderfluid people, 1 (1%) nonbinary person, and 1 (1%) who reported "prefer not to say." Their levels of deprivation ranged from among the 40% most deprived to the 20% least deprived areas. Most had self-identified sleep problems, ranging from 2 to 3 times per week to >4 times per week. Attitudes toward the app were positive, with praise for its usability and use of science-based yet accessible information. Think-aloud interviews and a focus group identified a range of elements that may influence the use of the app, including the need to pay attention to language choices and readability. User experiences in the form of narrated audio clips were used to normalize sleep problems and provide examples of how the app had helped these users., Conclusions: Young people were interested in using an app to better support their sleep and mental health. The app was co-created with strong links to theory- and evidence-based sleep hygiene behaviors. Future work to establish the effectiveness of the intervention, perhaps in a randomized controlled trial, would provide support for potential UK-wide rollout., (©Sarah E Bennett, Milly H Johnston, Georgia Treneman-Evans, James Denison-Day, Anthony Duffy, Amberly Brigden, Paula Kuberka, Nicholas Christoforou, Lee Ritterband, Jewel Koh, Robert Meadows, Doaa Alamoudi, Ian Nabney, Lucy Yardley. Originally published in JMIR Human Factors (https://humanfactors.jmir.org), 31.10.2024.)

Introduction: Around 2000 children are born in the UK per year with a neurodevelopmental genetic syndrome with significantly increased morbidity and mortality. Often little is known about expected growth and phenotypes in these children. Parents have responded by setting up social media groups to generate data themselves. Given the significant clinical evidence gaps, this research will attempt to identify growth patterns, developmental profiles and phenotypes, providing data on long-term medical and educational outcomes. This will guide clinicians when to investigate, monitor or treat symptoms and when to search for additional or alternative diagnoses., Methods and Analysis: This is an observational, multicentre cohort study recruiting between March 2023 and February 2026. Children aged 6 months up to 16 years with a pathogenic or likely pathogenic variant in a specified gene will be eligible. Children will be identified through the National Health Service and via self-recruitment. Parents or carers will complete a questionnaire at baseline and again 1 year after recruitment. The named clinician (in most cases a clinical geneticist) will complete a clinical proforma which will provide data from their most recent clinical assessment. Qualitative interviews will be undertaken with a subset of parents partway through the study. Growth and developmental milestone curves will be generated through the DECIPHER website (https://deciphergenomics.org) where 5 or more children have the same genetic syndrome (at least 10 groups expected)., Ethics and Dissemination: The results will be presented at national and international conferences concerning the care of children with genetic syndromes. Results will also be submitted for peer review and publication., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY. Published by BMJ.)

This study emphasises the critical role of quality sleep in physical and mental well-being, exploring its impact on bodily recovery and cognitive function. Investigating poor sleep quality in approximately 40% of individuals with insomnia symptoms, the research delves into its potential diagnostic relevance for depression and anxiety, with a focus on intervention in mental health by understanding sleep patterns, especially in young individuals. This study includes an exploration of phone usage habits among young adults during PPI sessions, providing insights for developing the SleepTracker app. This pivotal tool utilises phone usage and movement data from mobile device sensors to identify indicators of anxiety or depression, with participant information organised comprehensively in a table categorising condition related to phone usage and movement data. The analysis compares this data with survey results, incorporating scores from the Sleep Condition Indicator (SCI), Patient Health Questionnaire-9 (PHQ-9), and Generalised Anxiety Disorder-7 (GAD-7). Generated confusion matrices offer a detailed overview of the relationship between sleep metrics, phone usage, and movement data. In summary, this study reveals the accurate detection of negative sleep disruption instances by the classifier. However, improvements are needed in identifying positive instances, reflected in the F1-score of 0.5 and a precision result of 0.33. While early intervention potential is significant, this study emphasises the need for a larger participant pool to enhance the model's performance.

Background: Since the era of smartphones started in early 2007, they have steadily turned into an accepted part of our lives. Poor sleep is a health problem that needs to be closely monitored before it causes severe mental health problems, such as anxiety or depression. Sleep disorders (eg, acute insomnia) can also develop to chronic insomnia if not treated early. More specifically, mental health problems have been recognized to have casual links to anxiety, depression, heart disease, obesity, dementia, diabetes, and cancer. Several researchers have used mobile sensors to monitor sleep and to study changes in individual mood that may cause depression and anxiety., Objective: Extreme sleepiness and insomnia not only influence physical health, they also have a significant impact on mental health, such as by causing depression, which has a prevalence of 18% to 21% among young adults aged 16 to 24 in the United Kingdom. The main body of this narrative review explores how passive data collection through smartphone sensors can be used in predicting anxiety and depression., Methods: A narrative review of the English language literature was performed. We investigated the use of smartphone sensors as a method of collecting data from individuals, regardless of whether the data source was active or passive. Articles were found from a search of Google Scholar records (from 2013 to 2020) with keywords including "mobile phone," "mobile applications," "health apps," "insomnia," "mental health," "sleep monitoring," "depression," "anxiety," "sleep disorder," "lack of sleep," "digital phenotyping," "mobile sensing," "smartphone sensors," and "sleep detector.", Results: The 12 articles presented in this paper explain the current practices of using smartphone sensors for tracking sleep patterns and detecting changes in mental health, especially depression and anxiety over a period of time. Several researchers have been exploring technological methods to detect sleep using smartphone sensors. Researchers have also investigated changes in smartphone sensors and linked them with mental health and well-being., Conclusions: The conducted review provides an overview of the possibilities of using smartphone sensors unobtrusively to collect data related to sleeping pattern, depression, and anxiety. This provides a unique research opportunity to use smartphone sensors to detect insomnia and provide early detection or intervention for mental health problems such as depression and anxiety if insomnia is detected., (©Doaa Alamoudi, Emma Breeze, Esther Crawley, Ian Nabney. Originally published in JMIR mHealth and uHealth (https://mhealth.jmir.org), 17.02.2023.)

Behavioural coding is time-intensive and laborious. Thin slice sampling provides an alternative approach, aiming to alleviate the coding burden. However, little is understood about whether different behaviours coded over thin slices are comparable to those same behaviours over entire interactions. To provide quantitative evidence for the value of thin slice sampling for a variety of behaviours. We used data from three populations of parent-infant interactions: mother-infant dyads from the Grown in Wales (GiW) cohort ( n  = 31), mother-infant dyads from the Avon Longitudinal Study of Parents and Children (ALSPAC) cohort ( n  = 14), and father-infant dyads from the ALSPAC cohort ( n  = 11). Mean infant ages were 13.8, 6.8, and 7.1 months, respectively. Interactions were coded using a comprehensive coding scheme comprised of 11-14 behavioural groups, with each group comprised of 3-13 mutually exclusive behaviours. We calculated frequencies of verbal and non-verbal behaviours, transition matrices (probability of transitioning between behaviours, e.g., from looking at the infant to looking at a distraction) and stationary distributions (long-term proportion of time spent within behavioural states) for 15 thin slices of full, 5-min interactions. Measures drawn from the full sessions were compared to those from 1-, 2-, 3- and 4-min slices. We identified many instances where thin slice sampling (i.e., < 5 min) was an appropriate coding method, although we observed significant variation across different behaviours. We thereby used this information to provide detailed guidance to researchers regarding how long to code for each behaviour depending on their objectives., Competing Interests: Conflict of interestThe authors have no relevant financial or non-financial interests to disclose., (© The Author(s) 2023.)