[Automatic diagnosis of malignant degree of brain glioma based on Bayesian network]

Bayesian network connects graph theory with statistics, being an important research direction in data mining. Compared with other approaches used for data mining, Bayesian network can combine prior knowledge with observed data. Besides that, it can handle incomplete data sets. This paper applies Bayesian network to predict the malignant degree of brain glioma. Totally 280 cases are collected, and some of them contain missing values. Preprocessing is taken to make them applicable to the algorithms. Unlike MLP network, both Bayesian network and decision tree use attribute-value pairs to represent diagnostic knowledge derived from treated cases. These could improve both the understandability and applicability of their results. Results of all these algorithms can achieve accuracy rate over 80%, which satisfies the requirement of neuroradiologists.