Key points are not available for this paper at this time.
Abstract Background The rising global incidence of atopic dermatitis (AD) in children, particularly in Western industrialized countries, has garnered significant attention. The hygiene hypothesis, which posits that early exposure to pathogens is essential for immune system development, has been central to understanding this increase. Additionally, the application of advanced machine learning algorithms has unveiled new insights into the interactions between various risk factors. This study aims to explore the relationship between early childhood antibiotic usage, the duration of exclusive breastfeeding, indoor environmental factors, and the incidence of AD in children. By integrating machine learning techniques with the principles of the hygiene hypothesis, we seek to assess and interpret the significance of these risk factors. Methods In this community-based, 1:4 matched case-control study, we evaluated the prevalence of AD among preschool-aged children. Data were collected through questionnaires completed by the parents of 771 children diagnosed with AD and matched with controls based on ethnicity, gender, and age. Initial analyses identified pertinent characteristics, which were further examined through multivariable logistic regression to calculate odds ratios (ORs). Stratified analyses helped in assessing confounders and interactions, while the importance of variables was determined using a machine learning model. Results The renovation of the dwelling during the mother's pregnancy (OR = 1.50, 95%CI: 1.15–1.96) was identified as a risk factor for childhood AD. Furthermore, antibiotic use three or more times during the first year of life (OR = 1.92, 95%CI: 1.29–2.85) increased the risk of AD, independent of the parents' history of atopic disease and the child's mode of birth. Additionally, sustained exclusive breastfeeding for four months or more (OR = 1.59, 95%CI: 1.17–2.17) was found to be a risk factor for AD, particularly evident in the group with no parental history of atopic disease. Conversely, the presence of older siblings in the family (OR = 0.76, 95%CI: 0.63–0.92) and low birth weight of the child (OR = 0.62, 95%CI: 0.47–0.81) were identified as protective factors for AD. Machine learning modeling revealed that parental AD or allergic rhinitis had the greatest impact on child AD, followed by antibiotic use at age 0–1 years and the duration of exclusive breastfeeding. Conclusion Our findings support the broader form of the hygiene hypothesis. Machine learning analysis underscores the importance of focusing future AD prevention and healthcare efforts on children with a parental history of AD or allergic rhinitis. Additionally, minimizing antibiotic overuse is essential for AD prevention in children. Further research is needed to clarify the impact and mechanisms of extended exclusive breastfeeding on AD, to inform maternal and child healthcare practices.
Wang et al. (Thu,) studied this question.