Neurological injuries occurring during high-risk surgical procedures can be detected by monitoring intraoperative evoked potential signals. In this communication, an automatic injury detection algorithm is proposed in which the EP signal is modeled as a pole-zero filter and then the model parameters are applied as inputs to a classifier type neural network. A recognition rate of 96% is achieved using an experimental model of brain injury.Neurological injuries occurring during high-risk surgical procedures can be detected by monitoring intraoperative evoked potential signals. In this communication, an automatic injury detection algorithm is proposed in which the EP signal is modeled as a pole-zero filter and then the model parameters are applied as inputs to a classifier type neural network. A recognition rate of 96% is achieved using an experimental model of brain injury.