This study investigates a proposal of new Bayesian network model for the diagnosis of the most frequent breast pathologies and their implementation under a medical diagnostic system as part of maintenance. It consists...
详细信息
This study investigates a proposal of new Bayesian network model for the diagnosis of the most frequent breast pathologies and their implementation under a medical diagnostic system as part of maintenance. It consists in reproducing the process of doctor's diagnosis that allows the identification of a disease through its symptoms. The proposed Bayesian network allows a representation of qualitative and quantitative knowledge expressing the uncertainty divided into four levels: clinical level, medical imaging level, biological level and diagnostic level. Bayesian networks are used to calculate the probabilities of the most likely a posteriori or causes, of an observed anomaly by using the clustering algorithm proposed by genietool and should be sufficient for our application. In order to improve the performances of the system and due to errors in the construction of the model which is supplied a priori by an expert, and the changes in the dynamics domains, we propose the maintenance of BN that implements the policies of updating a fixed structure and considers its reorganization by defining supplementary variables noted as maintenance actions that could be add them or deleted and their values can be edited.
暂无评论