Prediction on lengths of stay in the postanesthesia care unit following general anesthesia: Preliminary study of the neural network and logistic regression modelling

The length of stay in the postanesthesia care unit (PACU) following general anesthesia in adults is an important issue. A model, which can predict the results of PACU stays, could improve the utilization of PACU and operating room resources through a more efficient arrangement. The purpose of study was to compare the performance of neural network to logistic regression ana lysis using clinical sets of data from adult patients undergoing general an esthesia. An artificial neural network was trained with 409 clinical sets u sing backward error propagation and validated through independent testing o f 183 records. Twenty-two inputs were used to find determinants and to pred ict categorical values. Logistic regression analysis was performed to provi de a comparison. The neural network correctly predicted in 81.4% of situati ons and identified discriminating variables (intubated state, sex, neuromus cular blocker and intraoperative use of opioid), whereas the figure was 65. 0% in logistic regression analysis. We concluded that the neural network co uld provide a useful predictive model for the optimization of limited resou rces. The neural network is a new alternative classifying method for develo ping a predictive paradigm, and it has EI higher classifying performance co mpared to the logistic regression model.