Using Back Propagation Feedback Neural Networks and Recurrence Quantification Analysis of EEGs Predict Responses to Incision During Anesthesia

摘要: This paper presents a new approach to detect depth of anaesthesia by using recurrence quantification analysis electroencephalogram (EEG) and artificial neural network(ANN) . From 98 consenting patient experiments, distinct EEG recordings were collected prior incision during isoflurane different levels. The seven measures plot extracted from each four-channel time series. Prediction was made means ANN. Training testing the ANN used ‘leave-one-out' method. prediction tested monitoring responses incision. system able correctly classify purposeful in average accuracy 92.86% cases. method is also computationally fast acceptable real-time clinical performance obtained.