Inappropriate antibiotic prescribing and its determinants among outpatient children in 3 low- and middle-income countries: A multicentric community-based cohort study

BackgroundAntibiotic resistance is a global public health issue, particularly in low- and middle-income countries (LMICs), where antibiotics required to treat resistant infections are not affordable. LMICs also bear a disproportionately high burden of bacterial diseases, particularly among children, and resistance jeopardizes progress made in these areas. Although outpatient antibiotic use is a major driver of antibiotic resistance, data on inappropriate antibiotic prescribing in LMICs are scarce at the community level, where the majority of prescribing occurs. Here, we aimed to characterize inappropriate antibiotic prescribing among young outpatient children and to identify its determinants in 3 LMICs. Methods and findingsWe used data from a prospective, community-based mother-and-child cohort (BIRDY, 2012 to 2018) conducted across urban and rural sites in Madagascar, Senegal, and Cambodia. Children were included at birth and followed-up for 3 to 24 months. Data from all outpatient consultations and antibiotics prescriptions were recorded. We defined inappropriate prescriptions as antibiotics prescribed for a health event determined not to require antibiotic therapy (antibiotic duration, dosage, and formulation were not considered). Antibiotic appropriateness was determined a posteriori using a classification algorithm developed according to international clinical guidelines. We used mixed logistic analyses to investigate risk factors for antibiotic prescription during consultations in which children were determined not to require antibiotics. Among the 2,719 children included in this analysis, there were 11,762 outpatient consultations over the follow-up period, of which 3,448 resulted in antibiotic prescription. Overall, 76.5% of consultations resulting in antibiotic prescription were determined not to require antibiotics, ranging from 71.5% in Madagascar to 83.3% in Cambodia. Among the 10,416 consultations (88.6%) determined not to require antibiotic therapy, 25.3% (n = 2,639) nonetheless resulted in antibiotic prescription. This proportion was much lower in Madagascar (15.6%) than in Cambodia (57.0%) or Senegal (57.2%) (p < 0.001). Among the consultations determined not to require antibiotics, in both Cambodia and Madagascar the diagnoses accounting for the greatest absolute share of inappropriate prescribing were rhinopharyngitis (59.0% of associated consultations in Cambodia, 7.9% in Madagascar) and gastroenteritis without evidence of blood in the stool (61.6% and 24.6%, respectively). In Senegal, uncomplicated bronchiolitis accounted for the greatest number of inappropriate prescriptions (84.4% of associated consultations). Across all inappropriate prescriptions, the most frequently prescribed antibiotic was amoxicillin in Cambodia and Madagascar (42.1% and 29.2%, respectively) and cefixime in Senegal (31.2%). Covariates associated with an increased risk of inappropriate prescription include patient age greater than 3 months (adjusted odds ratios (aOR) with 95% confidence interval (95% CI) ranged across countries from 1.91 [1.63, 2.25] to 5.25 [3.85, 7.15], p < 0.001) and living in rural as opposed to urban settings (aOR ranged across countries from 1.83 [1.57, 2.14] to 4.40 [2.34, 8.28], p < 0.001). Diagnosis with a higher severity score was also associated with an increased risk of inappropriate prescription (aOR = 2.00 [1.75, 2.30] for moderately severe, 3.10 [2.47, 3.91] for most severe, p < 0.001), as was consultation during the rainy season (aOR = 1.32 [1.19, 1.47], p < 0.001). The main limitation of our study is the lack of bacteriological documentation, which may have resulted in some diagnosis misclassification and possible overestimation of inappropriate antibiotic prescription. ConclusionIn this study, we observed extensive inappropriate antibiotic prescribing among pediatric outpatients in Madagascar, Senegal, and Cambodia. Despite great intercountry heterogeneity in prescribing practices, we identified common risk factors for inappropriate prescription. This underscores the importance of implementing local programs to optimize antibiotic prescribing at the community level in LMICs. Author summary Why was this study done? Antibiotic resistance is a major public health issue in low- and middle-income countries (LMICs), particularly among children, who face a disproportionately large share of the global burden of bacterial disease.Antibiotic overuse, as a result of inappropriate prescribing, is a major driver of antibiotic resistance, but relevant data from LMICs are scarce at the community level, where the majority of antibiotic prescribing occurs.Data regarding the prevalence and risk factors of inappropriate prescribing among outpatient children in LMICs are needed to understand its extent and causes and to inform intervention. What did the researchers do and find? Using data from a mother-and-child cohort in urban and rural sites of Madagascar, Senegal, and Cambodia, the appropriateness of outpatient antibiotic prescribing was assessed among all children ( = 2,719) having at least 1 outpatient consultation from birth up to 24 months of age.We identified that approximately 3 quarters of all antibiotic prescriptions were inappropriate.We found that 15.5%, 57.0%, and 57.2% of consultations not requiring antibiotic therapy, nonetheless, resulted in antibiotic prescription in Madagascar, Cambodia, and Senegal, respectively.Risk factors for inappropriate prescription include older patient age (being older than 3 months), disease with a higher severity score, consultation during the rainy season, and residence in rural areas. What do these findings mean? Inappropriate antibiotic prescribing is pervasive among outpatient children in LMICs, although there is great heterogeneity across countries in prescribing practices.Locally adapted antibiotic stewardship programs are needed to optimize pediatric antibiotic prescribing, while taking into account the specific contexts associated with high-risk populations across diverse LMICs.