Class Association Rules based Feature Selection for Diagnosis of Dravet Syndrome

Medical science industry has huge amount of data, but most of this data is not mined to find out hidden information in data. Data mining techniques can be used to discover hidden patterns that can be effectively applied to disease diagnosis which will help the physicians to take effective decision. Due to the significance of data mining techniques, association rule mining which is one of the data mining techniques to find the hidden rules from the data is applied to disease diagnosis by various researchers. In this paper, we propose a class association rules based feature selection for the diagnosis of dravet syndrome. The proposed technique for the diagnosis of Dravet syndrome contain two important steps, namely preprocessing, feature selection through association rules, and the performance is compared between them.