Hemorrhagic shock is the cause of one third of deaths resulting from injury in the world. As the symptoms of hemorrhagic shock occur after shock has considerably progressed, it is difficult to diagnose shock early. The purpose of this study was to select an optimal survival prediction model using physiological parameters from rats during our hemorrhagic experiment. We measured physiological parameters in rats with hemorrhagic shock for artificial neural network (ANN), support vector machine (SVM), and k-nearest neighbor (KNN) models. We checked sensitivity, specificity, and accuracy to evaluate performance of ANN, SVM, and KNN models. Among them, the best performance of sensitivity, specificity, and accuracy of survival prediction model using SVM were 97.5 ±2.9 %, 99.3 ± 1.1 %, and 98.5 ± 1.2 %, respectively.