Birth weight, childhood and adolescent growth and diabetes risk factors in 21-year-old Asian Indians: the Pune Children's Study

Adolescents' health literacy is directly associated with their physical activity but indirectly with their body composition and cardiorespiratory fitness: mediation analysis of the Slovak HBSC study data

BACKGROUND

Health literacy is a core public health issue in relation to children and adolescents associated with multiple health behaviours and health outcomes. The aim of the study is to test the direct associations between health literacy, physical activity behaviour, health outcomes of body composition and cardiorespiratory fitness among Slovak adolescents and possible indirect effect of health literacy on health outcomes of body composition and cardiorespiratory fitness mediated by adolescents' physical activity behaviour.

METHODS

Data from the Slovak Health Behaviour in School-aged Children (HBSC) study conducted in 2022 were used. For the purposes of this study, a subsample of the adolescents (n = 508; mean age = 14.50; SD = 0.82; 54.3% boys) which provided HBSC questionnaire data on health literacy, moderate-to-vigorous physical activity and vigorous physical activity and participated in body composition (InBody 230) and cardiorespiratory fitness (20-m shuttle run test) measurements. Data were analysed using linear regression analysis.

RESULTS

The findings showed that higher health literacy of the adolescents was directly associated with higher frequency of physical activity represented by moderate-to-vigorous physical activity and vigorous physical activity and only with the visceral fat area in the crude model. Furthermore, there was an indirect effect of health literacy on cardiorespiratory fitness and most of the body composition variables (except the Body Mass Index) which was mediated by physical activity of the respondents.

CONCLUSIONS

Health literacy is indirectly associated to body composition and cardiorespiratory fitness through higher frequency of physical activity. It seems that health literacy as cognitive and social competencies need behavioural components to be involved in the proposed causal pathway between health literacy and health outcomes. Our findings may contribute to the process of creating a framework for future health literacy interventions in adolescents.

Harnessing machine learning models for non-invasive pre-diabetes screening in children and adolescents

BACKGROUND AND OBJECTIVES

Pre-diabetes has been identified as an intermediate diagnosis and a sign of a relatively high chance of developing diabetes in the future. Diabetes has become one of the most frequent chronic disorders in children and adolescents around the world; therefore, predicting the onset of pre-diabetes allows a person at risk to make efforts to avoid or restrict disease progression. This research aims to create and implement a cross-validated machine learning model that can predict pre-diabetes using non-invasive methods.

METHODS

We have analysed the national representative dataset of children and adolescents (5-19 years) to develop a machine learning model for non-invasive pre-diabetes screening. Based on HbA1c levels the data (n = 26,567) was segregated into normal (n = 23,777) and pre-diabetes (n = 2790). We have considered eight features, six hyper-tuned machine learning models and different metrics for model evaluation. The final model was selected based on the area under the receiver operator curve (AUC), Cohen's kappa and cross-validation score. The selected model was integrated into the screening tool for automated pre-diabetes prediction.

RESULTS

The XG boost classifier was the best model, including all eight features. The 10-fold cross-validation score was highest for the XG boost model (90.13%) and least for the support vector machine (61.17%). The AUC was highest for RF (0.970), followed by GB (0.968), XGB (0.959), ETC (0.918), DT (0.908), and SVM (0.574) models. The XGB model was used to develop the screening tool.

CONCLUSION

We have developed and deployed a machine learning model for automated real-time pre-diabetes screening. The screening tool can be used over computers and can be transformed into software for easy usage. The detection of pre-diabetes in the pediatric age may help avoid its enhancement. Machine learning can also show great competence in determining important features in pre-diabetes.

Cognitive function and behavioral problems in children born to mothers with preeclampsia: an Indian study

Studies from high-income countries report associations of preeclampsia (PE) with reduced cognitive function and adverse behavioural outcomes in children. We examined these associations in Indian children aged 5-7 years. Children of mothers with PE (n=74) and without PE (non-PE; n=234) were recruited at delivery at Bharati Hospital, Pune, India. The cognitive performance was assessed using 3 core tests from the Kaufman Assessment Battery and additional tests including Verbal fluency, Kohs block design, and Coding A (from Wechsler Intelligence Scale for Children). The parent-reported Strengths and Difficulties Questionnaire (SDQ) was used to assess children's behavioral characteristics. Scores were compared between children from PE and non-PE groups, and associations analyzed further using regression models, adjusted for potential confounders. After adjusting for age, sex, socio-economic status and maternal education, children of PE mothers had lower Kohs block design scores (adjusted odds ratio per score category 0.57, [95% CI 0.34-0.96] p=0.034; 0.62 [95%CI (0.36, 1.07), p=0.09 on further adjustment for birth weight and gestation) compared to children of mothers without PE. In the SDQ, there was a lower prevalence of abnormal 'conduct problem' scores in PE group than non-PE group (OR=0.33, 95% CI 0.13-0.83, p=0.018, in the fully adjusted model); there were no differences for other behavioral domains. This preliminary study in Indian children suggests that fetal exposure to maternal PE may have an adverse impact on visuo-spatial performance but does not adversely affect behavior. Further studies with larger sample sizes are essential to understand effects of maternal PE on cognitive/behavioral outcomes in children.