Clinical decision support system for venous thromboembolism risk classification

This paper presents a clinical decision support system using Artificial Neural Networks (ANN). The system uses Multilayer Perceptron (MLP) feed forward neural network to predict the risk of developing Venous Thromboembolism (VTE) in hospitalized patients. The developed system classifies the risk of VTE into five risk levels ranging from low to high. The input layer of the system consists of 35 input variables grouped into six categories representing the risk factors of VTE according to Caprini model. The output layer consists of one node indicating a value representing the level of VTE risk. The number of hidden nodes and layers is determined through an iterative process. The system is trained using Resilient Backpropagation algorithm (Rprop). The dataset used for training and testing the system consists of 150 medical records obtained from Jordan University Hospital (JUH). Stratified ten-fold cross validation scheme is applied to assess the generalization of the proposed system. The results of the experiment show that the accuracy of the system is 81%.