An Intelligent Model Based on Fuzzy Bayesian Networks to Predict Astrocytoma Malignant Degree

A modified fuzzy Bayesian network (FBN) is proposed in this study, which integrates fuzzy logic into Bayesian networks (BN) by using Gaussian mixture models (GMM). The GMM make a fuzzy procedure to do a soft discretization of continuous variables, when dealing with continuous inputs with fuzzy and uncertain nature. Based on the FBN, the fuzzy reasoning model for prediction and diagnosis can be designed. To validate the method, an intelligent model is built and used to classify the astrocytoma malignant degree. Experiment results show that the model achieves an accuracy of 83.33%. It outperforms the Bayesian network-based model using k-nearest neighbor classifiers (K-NN) to make a crisp discretization. This study provides a novel objective method to quantitatively assess the astrocytoma malignant level that can be used to assist doctors to diagnose the tumor