Investigating the uses of machine learning algorithms to inform risk factor analyses: The example of avian infectious bronchitis virus (IBV) in broiler chickens

Infectious bronchitis virus (IBV) is a contagious coronavirus causing respiratory and urogenital disease in chickens and is responsible for significant economic losses for both the broiler and table egg layer industries. Despite IBV being regularly monitored using standard epidemiologic surveillance practices, knowledge and evidence of risk factors associated with IBV transmission remain limited. The study objective was to compare risk factor modeling outcomes between a traditional stepwise variable selection approach and a machine learning-based random forest Boruta algorithm using routinely collected IBV antibody titer data from broiler flocks. IBV antibody sampling events (n = 1111) from 166 broiler sites between 2016 and 2021 were accessed. Ninety-two geospatial-related and poultry-density variables were obtained using a geographic information system and data sets from publicly available sources. Seventeen and 27 candidate variables were screened to potentially have an association with elevated IBV antibody titers according to the manual selection and machine learning algorithm, respectively. Selected variables from both methods were further investigated by construction of multivariable generalized mixed logistic regression models. Six variables were shortlisted by both screening methods, which included year, distance to urban areas, main roads, landcover, density of layer sites and year, however, final models for both approaches only shared year as an important predictor. Despite limited significance of clinical outcomes, this work showcases the potential of a novel explorative modeling approach in combination with often unutilized resources such as publicly available geospatial data, surveillance health data and machine learning as potential supplementary tools to investigate risk factors related to infectious diseases.

Effectiveness and diurnal variations of vegetative environmental buffers (VEBs) for mitigating NH3 and PM emissions from poultry houses

Air pollutants from poultry production, such as ammonia (NH3) and particulate matter (PM), have raised concerns due to their potential negative impacts on human health and the environment. Vegetative environmental buffers (VEBs), consisting of trees and/or grasses planted around poultry houses, have been investigated as a mitigation strategy for these emissions. Although previous research demonstrated that VEBs can reduce NH3 and PM emissions, these studies used a limited number of samplers and did not examine concentration profiles. Moreover, the differences between daytime and nighttime emissions have not been investigated. In this study, we characterized emission profiles from a commercial poultry house using an array with multiple sampling heights and explored the differences between daytime and nighttime NH3 and PM profiles. We conducted three sampling campaigns, each with ten sampling events (five daytime and five nighttime), at a VEB-equipped poultry production facility. NH3 and PM samples were collected downwind from the ventilation tunnel fans before, within, and after the VEB. Results showed that ground-level concentrations beyond the VEB decreased to 8.0% ± 2.7% for NH3, 13% ± 4% for TSP, 13% ± 4% for PM10, and 2.4% ± 2.8% for PM2.5 of the original concentrations from the exhaust tunnel fan, with greater reduction efficiency during daytime than nighttime. Furthermore, pollutant concentrations were positively intercorrelated. These findings will be valuable for developing more effective pollutant remediation strategies in poultry house emissions.