Privacy Preserving Mining Based Framework for Analyzing the Patient Behavior

The data driven mining technology was applied in the most of the existing data mining algorithms. The limitations of this method are that expert analysis is required before the derived information can be used. To analyze data for predicting the patients behavior here we assume the strategy of domain driven data mining and utilize associations rules, clustering and decision trees. The proposed system is named as the Combined Mining based patient Behavior Prediction System (CM-PBPS). In this paper, we are implementing domain driven data mining strategy and exploit clustering, decision trees, and association rules to explore data of patients behavior. This system specifies the patients who are infected by which diseases. For the implementation, initially for analyze the patient behavior the associations rules are used. After that for patient segmentation the clustering algorithm is used. For reducing the data imbalanced we delete the clusters of the patient who are not infected by diseases. At last decision tree was utilized to predict and analyze the rest of the data by using the derivative attributes and the attributes provided.