Machine learning data sources in pediatric sleep research: assessing racial/ethnic differences in electronic health record-based clinical notes prior to model training.

Introduction: Pediatric sleep problems can be detected across racial/ethnic subpopulations in primary care settings. However, the electronic health record (EHR) data documentation that describes patients' sleep problems may be inherently biased due to both historical biases and informed presence. This study assessed racial/ethnic differences in natural language processing (NLP) training data (e.g., pediatric sleep-related keywords in primary care clinical notes) prior to model training. Methods: We used a predefined keyword features set containing 178 Peds B-SATED keywords. We then queried all the clinical notes from patients seen in pediatric primary care between the ages of 5 and 18 from January 2018 to December 2021. A least absolute shrinkage and selection operator (LASSO) regression model was used to investigate whether there were racial/ethnic differences in the documentation of Peds B-SATED keywords. Then, mixed-effects logistic regression was used to determine whether the odds of the presence of global Peds B-SATED dimensions also differed across racial/ethnic subpopulations. Results: Using both LASSO and multilevel modeling approaches, the current study found that there were racial/ethnic differences in providers' documentation of Peds B-SATED keywords and global dimensions. In addition, the most frequently documented Peds B-SATED keyword rankings qualitatively differed across racial/ethnic subpopulations. Conclusion: This study revealed providers' differential patterns of documenting Peds B-SATED keywords and global dimensions that may account for the under-detection of pediatric sleep problems among racial/ethnic subpopulations. In research, these findings have important implications for the equitable clinical documentation of sleep problems in pediatric primary care settings and extend prior retrospective work in pediatric sleep specialty settings.

Rural-urban differences in social and emotional protective factors and their association with child health and flourishing.

BACKGROUND: Children in rural communities experience higher mortality rates and less access to health care services than those in urban communities. Protective factors like social support also vary by geography, but their contribution to differences in child health is understudied. Understanding geographic variation in protective health factors could provide insight into their impact on health and guide future intervention strategies. RESEARCH OBJECTIVE: To examine protective factors' association with child flourishing and child health status in rural and urban communities. METHODS: Publicly available data from the National Survey of Children's Health, 2018-2021, with nonmissing geographic data (N = 150,493) were used to assess the relationship between protective factors and child flourishing and health by rurality. Multivariate survey-weighted probit models examined these relationships, adjusting for child and caregiver characteristics. FINDINGS: More than a third of children were not flourishing, according to parental report. An estimated 62% of rural children were flourishing compared to 66% of urban children (P<0.001). Urban caregivers also were more likely to report better adult mental and physical health status. Nevertheless, rural children were reported to receive more social support than urban children, while their caregivers reported more emotional support and living in supportive and safe neighborhoods (P<0.001). Rural caregivers reported more support from places of worship and less from counselors/other mental health care providers than urban caregivers. CONCLUSIONS: Despite higher reported caregiver emotional support and child social support, fewer rural children are flourishing. Health systems and community organizations able to leverage these existing social and emotional protective factors in rural communities could help close this gap.

Does ethnic-racial socialization matter? A within-person analysis of racial discrimination and sleep health among Black and Latinx emerging adults.

OBJECTIVES: Emerging work suggests that racism-related stressors may contribute to adverse sleep health, yet little is known about how culturally relevant resources may influence the relationship between racism-related stressors and adverse sleep health. The aim of this study was to examine associations between weekly reports of racial hassles and young adults' sleep health (i.e., sleep onset latency, total sleep time, sleep quality) and to determine whether various forms of parental ethnic-racial socialization would moderate these associations. METHODS: Participants were 141 college students (Mage = 20.7 years, standard deviation (SD) = 1.22, 70% female) who identified as either Black (n = 88; 62.4%) or Latinx (n = 53; 37.6%). Participants completed an initial 1.5-hour assessment in the laboratory and 4 weekly sleep diary surveys (assessed sleep health and depressive symptoms). RESULTS: Weekly racial hassles are related to greater sleep onset latency, decreased total sleep time, and poorer sleep quality. The promotion of mistrust and cultural socialization significantly moderated associations between weekly racial hassles and sleep onset latency and total sleep time, respectively. CONCLUSIONS: These results provide supportive evidence that parental ethnic-racial socialization practices, a preemptive cultural resource, may be an understudied mechanism in sleep health research. Future research is needed to clarify the role of parental ethnic-racial socialization in promoting sleep health equity among youth and young adults.

Social Needs as a Risk Factor for Positive Postpartum Depression Screens in Pediatric Primary Care.

OBJECTIVE: The goal of this study was to examine the association between self-reported social needs and postpartum depression (PPD) symptoms of mothers screened in pediatric primary care clinics. METHODS: This retrospective cohort study used electronic health record data from 3616 pediatric patients (age 0-6 months), whose mothers completed the Edinburgh Postpartum Depression Scale (EPDS) and a social needs screening in a large pediatric primary care network between April 2021 and February 2022. Mothers were screened for four self-reported social needs (food, housing, transportation, and utilities). Logistic regression evaluated the association between the report of any social need and a positive EPDS screen (≥ 10), adjusting for demographic and clinical characteristics and ZIP code-level poverty. RESULTS: Overall, 8.6% of mothers screened positive for PPD and 10.0% reported any social needs. The odds of a positive depression screen were significantly higher among mothers who reported any social need compared to those not reporting a social need (OR 4.18, 95% CI 3.11-5.61). The prevalence of all depressive symptoms on the EPDS was significantly higher among those who reported any social need, relative to those reporting no needs. Mothers reporting any social needs were significantly more likely to report thoughts of self-harm (6.9% vs 1.5%, P < .005). CONCLUSIONS: Self-report of social need was significantly associated with positive PPD screens during infant well-child visits. Social needs may be a target of future interventions addressing PPD in pediatric settings. Improving care for social needs may have added benefit of alleviating the risk of PPD.

An Initial Development and Evaluation of a Culturally Responsive Police Interactions Training for Black Adolescents with Autism Spectrum Disorder.

The purpose of the current study was to conduct a qualitative and experimental analysis of a culturally informed police safety skills training for adolescents with autism spectrum disorder (ASD). The current study focused primarily on meeting the unique training needs of Black adolescents with autism spectrum disorder (ASD). A single case design was used to evaluate the initial efficacy and acceptability of a culturally responsive training method. Preliminary evidence about the physiological ramifications of police contact were also collected to begin to examine the broader behavioral and psychophysiological nature of youth's experiences. The current experimental design included in-person simulated contexts that youth, and caregivers, endorsed as relevant to their normal lives, which greatly strengthened the ecological validity of the approach.

Within-person associations between racial microaggressions and sleep among African American and Latinx young adults.

Emerging work suggests that experiences of racial discrimination may impact overall sleep health; however, there is limited work on the link between racial microaggressions and sleep. Using weekly diary data, the current study examined young adults' weekly reports of racial microaggressions across 4 weeks, and their relation to weekly reports of sleep-onset latency, reduced total sleep time and poorer sleep quality. This design allowed us to examine how within-person fluctuations in racial microaggressions corresponded with young adults' sleep. Data were collected among 140 African American (62.1%) and Latinx (37.9%) college students attending a Midwestern University. Students were randomly selected to participate; they were, on average, 20.70 years old (SD = 1.22) and the majority were female (69.3%). Participants self-reported their racial microaggressions and sleep behaviours (i.e. sleep-onset latency, total sleep time and sleep quality) each week (across 4 weeks). Multilevel modelling showed significant within-person effects of racial microaggressions for sleep onset and sleep quality, but not for total sleep duration. Specifically, on weeks that individuals reported increases in racial microaggressions, they reported greater sleep-onset duration and poorer sleep quality. The current findings provide preliminary evidence that racial microaggressions are associated with sleep-onset durations and sleep quality among African American and Latinx young adults. Although racial microaggressions are often considered subtle, they may impact the sleep health of young adults in marginalized groups.

Using Telehealth to Deliver Family-Based Cognitive Behavioral Treatment of Insomnia in a School-Aged Child With Autism Spectrum Disorder.

Chronic insomnia (>3 months) is common in children with autism. Cognitive behavioral treatment for insomnia in children (CBT-CI) holds promise for improving sleep and daytime functioning in school-aged children with autism and their parents, but typical delivery involving multiple in-person office visits limits accessibility. This case study describes telehealth delivery of CBT-CI (teleCBT-CI) with a 7-year 4-month-old biracial boy with autism spectrum disorder (ASD) and insomnia and his parents. He and his mother wore actigraphs and completed electronic sleep diaries for 2 weeks, and his mother completed the Aberrant Behavior Checklist at pre/post/1-month follow-up. He and both of his parents completed eight telehealth treatment sessions. TeleCBT-CI improved the boy's sleep (objective, subjective) and decreased irritability, lethargy, stereotypy, and hyperactivity. This case study shows that teleCBT-CI is feasible and can improve child sleep and functioning.