Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Animal Genomics and Improvement Laboratory » Research » Publications at this Location » Publication #315760

Title: Benchmarking dairy herd health status using routinely recorded herd summary data

Author
item PARKER GADDIS, KRISTEN - University Of Florida
item Cole, John
item CLAY, JOHN - Dairy Records Management Systems(DRMS)
item MALTECCA, CHRISTIAN - North Carolina State University

Submitted to: Journal of Dairy Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 9/25/2015
Publication Date: 2/1/2016
Citation: Parker Gaddis, K., Cole, J.B., Clay, J.S., Maltecca, C. 2016. Benchmarking dairy herd health status using routinely recorded herd summary data. Journal of Dairy Science. 99(2):1298-1314.

Interpretive Summary: Health of dairy cattle is of increasing importance in today’s industry. Health is a complex trait influenced by numerous variables including genetics and environment. A wealth of information is gathered regularly that could be used for improvement of dairy cattle health. This research sought to incorporate characteristics collected at herd level to predict health status. Prediction of health status can assist producers in monitoring and improving herd health. Identification of influential variables can aid in management decisions. This study provides evidence for the value of data recorded by producers and the potential of utilizing these data for benchmarking health status.

Technical Abstract: Genetic improvement of dairy cattle health through the use of producer-recorded data has been determined to be feasible. Low estimated heritabilities indicate that genetic progress will be slow. Variation observed in lowly heritable traits can largely be attributed to non-genetic factors, such as the environment. More rapid improvement of dairy cattle health may be attainable if herd health programs incorporate environmental and managerial aspects. More than 1,100 herd characteristics are regularly recorded on farm test days. These data were combined with producer-recorded health event data and parametric and nonparametric models were used to benchmark herd and cow health status. Health events were grouped into three categories for analyses: mastitis, reproductive, and metabolic. Both herd incidence and individual incidence were used as dependent variables. Models implemented included stepwise logistic regression, support vector machines, and random forests. At both the herd- and individual-level, random forest models attained the highest accuracy for predicting health status in all health event categories when evaluated with ten-fold cross-validation. Accuracy (SD) ranged from 0.61 (0.04) to 0.63 (0.04) when using random forest models at the herd level. Accuracy of prediction (SD) at the individual cow level ranged from 0.87 (0.06) to 0.93 (0.001) with random forest models. Highly significant variables and key words from logistic regression and random forest models were also investigated. All models identified several of the same key factors for each health event category, including movement out of the herd, size of the herd, and weather-related variables. It was concluded that benchmarking health status using routinely collected herd data is feasible. Nonparametric models were better suited to handle this complex data with numerous variables. These data mining techniques were able to perform prediction of health status and could add evidence to personal experience in herd management.