The transmission dynamics of Campylobacter jejuni among broilers in semi-commercial farms in Jordan

Abstract

Campylobacter is the leading cause of foodborne bacterial gastroenteritis in humans worldwide, often associated with the consumption of undercooked poultry. In Jordan, the majority of broiler chicken production occurs in semi-commercial farms, where poor housing conditions and low bio-security are likely to promote campylobacter colonisation. While several studies provided estimates of the key parameters describing the within-flock transmission dynamics of campylobacter in typical high-income countries settings, these data are not available for Jordan and Middle-East in general. A Bayesian model framework was applied to a longitudinal dataset on Campylobacter jejuni infection in a Jordan flock to quantify the transmission rate of C. jejuni in broilers within the farm, the day when the flock first became infected, and the within-flock prevalence (WFP) at clearance. Infection with C. jejuni is most likely to have occurred during the first 8 days of the production cycle, followed by a transmission rate value of 0.13 new infections caused by one infected bird/day (95% CI 0.11-0.17), and a WFP at clearance of 34% (95% CI 0.24-0.47). Our results differ from published studies conducted in intensive poultry production systems in high-income countries but are well aligned with the expectations obtained by means of structured questionnaires submitted to academics with expertise on campylobacter in Jordan. This study provides for the first time the most likely estimates and credible intervals of key epidemiological parameters driving the dynamics of C. jejuni infection in broiler production systems commonly found in Jordan and the Middle-East and could be used to inform Quantitative Microbial Risk Assessment models aimed to assess the risk of human exposure/infection to campylobacter through consumption of poultry meat.

Keywords: Bayesian analysis; Jordan; broiler chicken; campylobacter.

Fig. 1.

The within-flock prevalence dynamics for a 5000-bird flock in Jordan with a density of birds of around 10 birds/m², obtained by fitting the model (including 95% credible intervals) to the longitudinal data points.