Evaluation of predictive models to determine final outcome for feedlot cattle based on information available at first treatment for bovine respiratory disease

Abstract

Bovine respiratory disease (BRD) is the costliest health condi­tion affecting feedyards in North America. Accurate identifica­tion of severe disease has the potential to aid in establishing an intervention to prevent a case fatality in individual animals. The study objective was to evaluate the diagnostic ability of predictive models to determine the probability a calf at first BRD treatment would finish the feeding period with the group or incur a negative outcome (railed or died). Additional com­parisons were made to evaluate potential benefits to predictive model performance by the addition of weather data, utilization of a data balancing technique, and creation of models for indi­vidual feedlots.