Neural Detection of Mastitis From Dairy Herd Improvement Records

A back-propagation artificial neural network was employed to detect clinical mastitis using a file of 460,474test day records. Two data files were created to train the artificial neural networks, containing a relatively large (1:1)ratio and a relatively small (1:10) ratio in the incidence to non-incidence of clinical mastitis. These ratios were applied toeach of two input file designs; one comprised variables that are traditional in the modeling of mastitis (e.g., age, stage oflactation and somatic cell count) and a second included additional variables (e.g., season of calving, milk componentsand conformation class). Results from analyses of relative operating characteristics indicated that artificial neuralnetworks could discriminate between mastitic states with an overall accuracy of 86%. This discriminatory ability wassubject to patterns that existed in the training data files but was not affected by differing proportions of mastitic records.However, differing proportions of mastitic records had some effect on the particular purpose of the artificial neuralnetwork being developed: training with a higher proportion of mastitic cases increased the ability of an artificial neuralnetwork in discriminating positive from negative cases. Similar effects were obtained by modifying the threshold valueused to categorize the ANN output, which constitutes a much simpler approach than modifying the proportion of cases intraining data sets. Additional variables had little effect on the prediction accuracy, but this lack of effect needs to beverified for optimal artificial neural network configuration, data preprocessing, and new sources of information.