Diversity, equity and inclusion considerations in mental health apps for young people: protocol for a scoping review.

INTRODUCTION: After COVID-19, a global mental health crisis affects young people, with one in five youth experiencing mental health problems worldwide. Delivering mental health interventions via mobile devices is a promising strategy to address the treatment gap. Mental health apps are effective for adolescent and young adult samples, but face challenges such as low real-world reach and under-representation of minoritised youth. To increase digital health uptake, including among minoritised youth, there is a need for diversity, equity and inclusion (DEI) considerations in the development and evaluation of mental health apps. How well DEI is integrated into youth mental health apps has not been comprehensively assessed. This scoping review aims to examine to what extent DEI considerations are integrated into the design and evaluation of youth mental health apps and report on youth, caregiver and other stakeholder involvement. METHODS AND ANALYSIS: We will identify studies published in English from 2009 to 29 September 2023 on apps for mental health in youth. We will use PubMed, Global Health, APA PsycINFO, SCOPUS, CINAHL PLUS and the Cochrane Database and will report according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses-Scoping Review Extension guidelines. Papers eligible for inclusion must be peer-reviewed publications in English involving smartphone applications used by adolescents or young adults aged 10-25, with a focus on depression, anxiety or suicidal ideation. Two independent reviewers will review and extract articles using a template developed by the authors. We will analyse the data using narrative synthesis and descriptive statistics. This study will identify gaps in the literature and provide a roadmap for equitable and inclusive mental health apps for youth. ETHICS AND DISSEMINATION: Ethics approval is not required. Findings will be disseminated through academic, industry, community networks and scientific publications.

Racial disparities in EEG research and their implications for our understanding of the maternal brain.

Racial disparities in maternal health are alarming and persistent. Use of electroencephalography (EEG) and event-related potentials (ERPs) to understand the maternal brain can improve our knowledge of maternal health by providing insight into mechanisms underlying maternal well-being, including implications for child development. However, systematic racial bias exists in EEG methodology-particularly for Black individuals-and in psychological and health research broadly. This paper discusses these biases in the context of EEG/ERP research on the maternal brain. First, we assess the racial/ethnic diversity of existing ERP studies of maternal neural responding to infant/child emotional expressions, using papers from a recent meta-analysis, finding that the majority of mothers represented in this research are of White/European ancestry and that the racially and ethnically diverse samples that are present are limited in terms of geography. Therefore, our current knowledge base in this area may be biased and not generalizable across racially diverse mothers. We outline factors underlying this problem, beginning with the racial bias in EEG equipment that systematically excludes individuals of African descent, and also considering factors specific to research with mothers. Finally, we highlight recent innovations to EEG hardware to better accommodate diverse hairstyles and textures, and other important steps to increase racial and ethnic representativeness in EEG/ERP research with mothers. We urge EEG/ERP researchers who study the maternal brain-including our own research group-to take action to increase racial diversity so that this research area can confidently inform understanding of maternal health and contribute to minimizing maternal health disparities.

Big Data, Small Personas: How Algorithms Shape the Demographic Representation of Data-Driven User Segments.

Derived from the notion of algorithmic bias, it is possible that creating user segments such as personas from data results in over- or under-representing certain segments (FAIRNESS), does not properly represent the diversity of the user populations (DIVERSITY), or produces inconsistent results when hyperparameters are changed (CONSISTENCY). Collecting user data on 363M video views from a global news and media organization, we compare personas created from this data using different algorithms. Results indicate that the algorithms fall into two groups: those that generate personas with low diversity-high fairness and those that generate personas with high diversity-low fairness. The algorithms that rank high on diversity tend to rank low on fairness (Spearman's correlation: -0.83). The algorithm that best balances diversity, fairness, and consistency is Spectral Embedding. The results imply that the choice of algorithm is a crucial step in data-driven user segmentation, because the algorithm fundamentally impacts the demographic attributes of the generated personas and thus influences how decision makers view the user population. The results have implications for algorithmic bias in user segmentation and creating user segments that not only consider commercial segmentation criteria but also consider criteria derived from ethical discussions in the computing community.