The Application Of Data Mining In Oral Treatment Based On Decision Tree

In recent years, with the rapid development of database technology and mass storage, people's ability to collect data is further improved. Facing the emergence of huge amounts of data, how to effectively use the raw data to analysis and predict the future status has become a major challenge to humanity. As a result, data mining emerged and developed rapidly. Currently, data mining has become a hot research topic, the knowledge,gained from data mining, can provide the basis for decision.Oral disease is a kind of common disease, and some complications of the disease will be shown in the mouth, the researchers will also study oral disease to provide strong support for the primary disease. In this regard, we try to use the data mining algorithms to discover rules, and present decision tree technology into the pathogenesis of oral disease and its primary research, hope through the research, mining laws from the data of a number of oral diseases, and structuring decision-making system for the disease prevention,and diagnosis.The raw data comes from the diagnosis and treatment of data in the database of HIS (Hospital Information System)system. Because of the noise and there is no integrity and inconsistency, the raw data can not be directly used, then data pretreatment is carried out. And use the IDS (Interative Dichotomic Version3)decision tree algorithm of data mining theory to mining the data. Then the decision tree model, which can predict some clinical disease by the information of oral disease, is created. Its accuracy is judged with the method of keeping rightness rate of training set and test set. On this basis, in order to further improve the accuracy, the ID3 algorithm is improved. In the end, we compared the accuracy of algorithm.The results shows that the accuracy of improved IDS algorithm is higher than before, and it is meaningful in regard to application.