An Automatic System Based Linear Discriminant Analysis Artificial Neural Network For Detecting Of Post-Operative Patient Status

In medical literature, the detecting of post-operative patient status is very important topic. In this paper, An Automatic System based Linear Discriminant Analysis (LDA) and Artificial Neural Network (ANN) for Detecting of Postoperative Patient Status (A_LDA_ANN_DPPS) is introduced. This automatic system consists of three stages, which are feature extraction and feature reduction stage, classification stage, and testing stage. In feature extraction and feature reduction stage, the Linear Discriminant Analysis (LDA) is used for reduce the data dimensionality and also to clear out some irregularitises from the data. In classification stage, a ANN classifier is used for classification of reduced features in feature extraction and feature reduction stage. In this study, post-operative patient dataset obtained uci repository is used to create this A_LDA_ANN_DPPS system to determine based on hypothermia condition, whether patients in a postoperative recovery area should be sent to intensive care unit, general hospital floor or go home. In testing stage, the correct classification accuracy of this A_LDA_ANN_DPPS system is calculated. The testing results show that the correct classification accuracy of this A_LDA_ANN_DPPS system was obtained about 84.44 % high performance. Keywords—Automatic detecting system; Expert Systems; Linear Discriminant Analysis (LDA); Artificial Neural Network (ANN) classifier.