Exploring the potential mediating role of systemic antibiotics in the association between early-life lower respiratory tract infections and asthma at age 5 in the CHILD study

Abstract

Objective: Lower respiratory tract infections (LRTIs) in early life are one of the strongest risk factors for childhood asthma and are often treated with systemic antibiotics (IV or oral). We aimed to explore the association between early-life LRTIs and systemic antibiotics on asthma development and the potential mediating role of antibiotics in this relationship.

Methods: Data were collected as part of the longitudinal, general Canadian population CHILD Study. LRTIs during the first 18 months of life were identified through parental symptom report at regular study visits. Systemic antibiotic use was defined as at least one dose of oral/intravenous antibiotics between birth and the 18-month visit and were further categorized by indication as either given for a respiratory indication (upper or lower respiratory symptoms) or non-respiratory indication. Asthma was diagnosed by in-study pediatricians at the 5-year study visit. Adjusted logistic regression models and mediation analyses via systemic antibiotics use were performed.

Results: Among 2,073 participants included in our analysis, 72 (4.9%) had asthma age 5, and 609 (29.3%) used systemic antibiotics before the 18-month visit. Among children who had taken antibiotics, 61.6% also had an LRTI in that period compared to 49.7% among children without exposure to systemic antibiotics (p < .001). Moderate-severe LRTIs before age 18 months were associated with higher odds of 5-year asthma [aOR 4.12 (95%CI 2.04-7.95) p < .001]. Antibiotics taken for respiratory indications were associated with higher odds of asthma at age 5 [aOR 2.36 (95%CI 1.59-3.48) p < .001]. Children who received systemic antibiotics for only non-respiratory indications during the first 18 months of life were not associated with increased odds of asthma [aOR 1.08 (95%CI 0.44-2.30) p = .851]. Using mediation analysis, 21.7% of the association between LRTI and asthma is estimated to be mediated through use of early-life systemic antibiotics. However, a significant direct effect of moderate-to-severe LRTIs on asthma risk remained in adjusted mediation models (p = .014).

Conclusion: Through mediation modeling we estimate that the increased risk of asthma at age 5 that is associated with moderate-severe LRTIs in infancy may be partially mediated by systemic antibiotics taken during the first 18 months of life. This underscores the importance of public health strategies focused on antibiotic stewardship and reducing early life LRTIs to mitigate asthma risk.

Keywords: antibiotics; clinical epidemiology; cohort study; mediation analyses; preschool asthma; respiratory tract infections.

Figure 1

Adjusted odds ratios (OR) and 95% confidence intervals (CI) of physician diagnosis of asthma at 5 years of age for LRTIs and antibiotics between birth and 18-month visit. Models adjusted by site, child sex, Caucasian, breastfeeding <3 m, prenatal smoke exposure, mode of delivery, family income, away from home <12 m, older siblings, and parental history of asthma.

Figure 2

Percent of CHILD study participants who had taken systemic antibiotics between birth and the 18-month visit by indication (any reason, only non-respiratory, any respiratory) and by severity of LRTIs reported by 18 months of age. (A) Percent (%) of participants who received any systemic antibiotic across LRTI severities, (B) percent of participants who took antibiotics due to only non-respiratory indications across LRTI severities, (C) percent of participants who took antibiotics by the 18-month visit due to respiratory indications by LRTI severity group.

Figure 3

Summary of mediation analyses. This figure illustrates the three mediation models performed: any systemic antibiotics (top), antibiotics for any respiratory indication (second from bottom) and respiratory indication among non-wheezers (bottom).