Use of a multiple logistic regression model to determine prognosis of dairy cows with right displacement of the abomasum or abomasal volvulus

Abstract

SUMMARY Data at admission and at surgery were collected on 458 cows with right displacement of the abomasum or abomasal volvulus, to derive multiple logistic regression models for predicting postsurgical outcome (productive, salvaged, or terminal). The derived models contained few and easily obtained variables. The weight associated with each variable was determined objectively. Three admission variables (heart rate, base excess, and plasma chloride concentration), and 5 surgical variables (heart rate, base excess, diagnosis, method of decompression used, and appearance of abomasal serosa) were used in the final models. Predicted outcomes that used the admission and surgical models were closely related with actual outcomes. Total correct classification for satisfactory (productive) versus unsatisfactory outcome (salvaged and terminal) was 78.2% for the admission model and 82.7% for the surgical model. Combining data on cows with productive and salvaged outcomes as satisfactory outcome, and terminal as unsatisfactory outcome, total correct classification was 90.7% for the admission model and 93.2% for the surgical model. Using predicted probabilities, the market value of productive and salvaged cows, and the medical and surgical costs, one can calculate the expected economic value of each outcome. Treatment can be justified if the sum of the expected value of productive and salvaged outcome exceeds the sum of the medical and surgical costs and the expected salvaged value of the cow that was not treated surgically.