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.

Computed tomographic and magnetic resonance imaging anatomy of the coelomic cavity in market-age commercial Pekin Ducks (Anas platyrhynchos domesticus).

Approximately 27 million ducks are raised commercially in the US each year and Pekin ducks (Anas platyrhynchos domesticus) are the most commonly raised breed. Additionally, an increasing number of Americans are raising small flocks of poultry, which often include ducks, in their own backyards. This creates a need to better understand the imaging anatomy of ducks. However, in avian species, superimposition of organs limits evaluation of the coelomic cavity using the most common imaging modality, radiography. The use of cross-sectional imaging including computed tomography (CT) and magnetic resonance imaging (MRI) has increased in veterinary medicine research and clinical use. An anatomic atlas is essential for guiding research and diagnostic imaging. To date, no CT or MRI atlas exists for Pekin ducks. The purpose of the study is to generate a CT atlas of market-age Pekin ducks as well as CT attenuation values and measurements of coelomic organs with corresponding gross and MRI images. A total of 20 market-age, commercial Pekin ducks were imaged. Five male and five female ducks were imaged with CT; four of these ten ducks, two male and two female, were frozen and sliced in approximately 5 mm transverse sections for gross anatomic reference images. Six additional ducks, three male and three female ducks, were dissected to measure major organs. Four additional ducks were imaged using CT and MRI and necropsied for gross anatomical comparisons and landmarks. The atlas contained here may be used for future research projects and clinically to aid in diagnosis of disease in ducks.

Porcine Deltacoronavirus Infection and Transmission in Poultry, United States1.

Coronaviruses cause respiratory and gastrointestinal diseases in diverse host species. Deltacoronaviruses (DCoVs) have been identified in various songbird species and in leopard cats in China. In 2009, porcine deltacoronavirus (PDCoV) was detected in fecal samples from pigs in Asia, but its etiologic role was not identified until 2014, when it caused major diarrhea outbreaks in swine in the United States. Studies have shown that PDCoV uses a conserved region of the aminopeptidase N protein to infect cell lines derived from multiple species, including humans, pigs, and chickens. Because PDCoV is a potential zoonotic pathogen, investigations of its prevalence in humans and its contribution to human disease continue. We report experimental PDCoV infection and subsequent transmission among poultry. In PDCoV-inoculated chicks and turkey poults, we observed diarrhea, persistent viral RNA titers from cloacal and tracheal samples, PDCoV-specific serum IgY antibody responses, and antigen-positive cells from intestines.