Machine learning-based health environmental-clinical risk scores in European children.

BACKGROUND: Early life environmental stressors play an important role in the development of multiple chronic disorders. Previous studies that used environmental risk scores (ERS) to assess the cumulative impact of environmental exposures on health are limited by the diversity of exposures included, especially for early life determinants. We used machine learning methods to build early life exposome risk scores for three health outcomes using environmental, molecular, and clinical data. METHODS: In this study, we analyzed data from 1622 mother-child pairs from the HELIX European birth cohorts, using over 300 environmental, 100 child peripheral, and 18 mother-child clinical markers to compute environmental-clinical risk scores (ECRS) for child behavioral difficulties, metabolic syndrome, and lung function. ECRS were computed using LASSO, Random Forest and XGBoost. XGBoost ECRS were selected to extract local feature contributions using Shapley values and derive feature importance and interactions. RESULTS: ECRS captured 13%, 50% and 4% of the variance in mental, cardiometabolic, and respiratory health, respectively. We observed no significant differences in predictive performances between the above-mentioned methods.The most important predictive features were maternal stress, noise, and lifestyle exposures for mental health; proteome (mainly IL1B) and metabolome features for cardiometabolic health; child BMI and urine metabolites for respiratory health. CONCLUSIONS: Besides their usefulness for epidemiological research, our risk scores show great potential to capture holistic individual level non-hereditary risk associations that can inform practitioners about actionable factors of high-risk children. As in the post-genetic era personalized prevention medicine will focus more and more on modifiable factors, we believe that such integrative approaches will be instrumental in shaping future healthcare paradigms.

Growing up in different environments can greatly affect children's health later in life. This research looked at how living in cities, being exposed to chemicals, and other experiences before birth and during childhood, work together to influence children's mental, cardiovascular and respiratory health. We used advanced computer programs to help us understand these effects and estimate health risk scores. These scores are simple numerical measures that help us quantify the likelihood of children developing health issues based on their environmental exposures. Using those scores, the study identified key factors impacting children's health, in particular psycho-social, perceived environmental and prenatal pollutant exposures for mental health. It also revealed complex patterns and interactions between environmental factors. The results highlighted the potential of such risk scores to support the identification of actionable factors in high-risk children, informing tailored prevention measures in healthcare.

Road traffic noise and children's inattention.

BACKGROUND: An increasing number of children are exposed to road traffic noise levels that may lead to adverse effects on health and daily functioning. Childhood is a period of intense growth and brain maturation, and children may therefore be especially vulnerable to road traffic noise. The objective of the present study was to examine whether road traffic noise was associated with reported inattention symptoms in children, and whether this association was mediated by sleep duration. METHODS: This study was based on the Norwegian Mother and Child Cohort Study conducted by the Norwegian Institute of Public Health. Parental reports of children's inattention at age 8 were linked to modelled levels of residential road traffic noise. We investigated the association between inattention and noise exposure during pregnancy (n = 1934), noise exposure averaged over 5 years (age 3 to 8 years; n = 1384) and noise exposure at age 8 years (n = 1384), using fractional logit response models. The participants were children from Oslo, Norway. RESULTS: An association with inattention at age 8 years was found for road traffic noise exposure at age 8 years (coef = .0083, CI = [.0012, .0154]; 1.2% point increase in inattention score per 10 dB increase in noise level), road traffic noise exposure average for the last 5 years (coef = .0090, CI = [.0016, .0164]; 1.3% point increase/10 dB), and for pregnancy road traffic noise exposure for boys (coef = .0091, CI = [.0010, .0171]), but not girls (coef = -.0021, CI = [-.0094, .0053]). Criteria for doing mediation analyses were not fulfilled. CONCLUSION: Results indicate that road traffic noise has a negative impact on children's inattention. We found no mediation by sleep duration.

Green spaces and spectacles use in schoolchildren in Barcelona.

Myopia is one of the major causes of low visual acuity during childhood, and hence of the need for spectacles. It is generally more prevalent in urban areas where children are often less exposed to green spaces than in rural areas. This study evaluated the association between exposure to green space and use of spectacles (as a surrogate measure for myopia) in a cohort of 2727 schoolchildren (7-10 years old) recruited from 39 primary schools in Barcelona (2012-2015). We assessed exposure to green spaces by characterizing outdoor surrounding greenness at home and school and during commuting using satellite data on greenness (Normalized Difference Vegetation Index). We also obtained data on the annual average time children spent playing in green spaces through questionnaires. Cross-sectional analyses were conducted based on prevalent cases of spectacles use at baseline data collection campaign and longitudinal analyses based on incident cases of spectacles use during the three-year period between the baseline and last data collection campaigns. An interquartile range (IQR) increase in exposure to green space at home (500m buffer) and school and during commuting was associated with respectively 14% (95% CI: 2%, 26%), 27% (95% CI: 6%, 44%), and 20% (95% CI: 5%, 33%) decrease in spectacles use in cross-sectional analyses. In longitudinal analyses, we observed a reduction of 23% (95% CI: 4%, 39%) and 34% (95% CI: 2%, 55%) associated with an IQR increase in greenness at home and school, respectively. Moreover, an IQR increase in time playing in green spaces was associated with a 28% (95% CI: 7%, 45%) reduction in the risk of spectacles use in the longitudinal analysis. Our observed reduced risk of spectacles use associated with higher contact with green space calls for more refined studies of the association between green spaces and refractive errors of visions.

Green spaces and cognitive development in primary schoolchildren.

Exposure to green space has been associated with better physical and mental health. Although this exposure could also influence cognitive development in children, available epidemiological evidence on such an impact is scarce. This study aimed to assess the association between exposure to green space and measures of cognitive development in primary schoolchildren. This study was based on 2,593 schoolchildren in the second to fourth grades (7-10 y) of 36 primary schools in Barcelona, Spain (2012-2013). Cognitive development was assessed as 12-mo change in developmental trajectory of working memory, superior working memory, and inattentiveness by using four repeated (every 3 mo) computerized cognitive tests for each outcome. We assessed exposure to green space by characterizing outdoor surrounding greenness at home and school and during commuting by using high-resolution (5 m × 5 m) satellite data on greenness (normalized difference vegetation index). Multilevel modeling was used to estimate the associations between green spaces and cognitive development. We observed an enhanced 12-mo progress in working memory and superior working memory and a greater 12-mo reduction in inattentiveness associated with greenness within and surrounding school boundaries and with total surrounding greenness index (including greenness surrounding home, commuting route, and school). Adding a traffic-related air pollutant (elemental carbon) to models explained 20-65% of our estimated associations between school greenness and 12-mo cognitive development. Our study showed a beneficial association between exposure to green space and cognitive development among schoolchildren that was partly mediated by reduction in exposure to air pollution.

The association between greenness and traffic-related air pollution at schools.

Greenness has been reported to improve mental and physical health. Reduction in exposure to air pollution has been suggested to underlie the health benefits of greenness; however, the available evidence on the mitigating effect of greenness on air pollution remains limited and inconsistent. We investigated the association between greenness within and surrounding school boundaries and monitored indoor and outdoor levels of traffic-related air pollutants (TRAPs) including NO2, ultrafine particles, black carbon, and traffic-related PM2.5 at 39 schools across Barcelona, Spain, in 2012. TRAP levels at schools were measured twice during two one-week campaigns separated by 6months. Greenness within and surrounding school boundaries was measured as the average of satellite-derived normalized difference vegetation index (NDVI) within boundaries of school and a 50m buffer around the school, respectively. Mixed effects models were used to quantify the associations between school greenness and TRAP levels, adjusted for relevant covariates. Higher greenness within and surrounding school boundaries was consistently associated with lower indoor and outdoor TRAP levels. Reduction in indoor TRAP levels was partly mediated by the reduction in outdoor TRAP levels. We also observed some suggestions for stronger associations between school surrounding greenness and outdoor TRAP levels for schools with higher number of trees around them. Our observed reduction of TRAP levels at schools associated with school greenness can be of public importance, considering the burden of health effects of exposure to TRAPs in schoolchildren.