Applying Decision of Tree, Naïve Base and Random Forest Algorithms’ in Diseases Prediction

Abstract

Medicinal services information principally contains all the patients' data just as the gatherings associated with social insurance businesses. The rate stockpiling of such kind of information is expanded quickly. Due to the constant expanding the size of electronic medicinal services information turns out to be perplexing. It turns out to be hard to separate the important data from it by utilizing the customary strategies. Because of progression in the field of measurements, arithmetic, and each other control, presently it is conceivable to extricate the significant examples from it and can be utilized for clinical dynamic. Information mining is valuable in such a circumstance where enormous assortments of human services information are accessible. This paper incorporates a correlation between Decision tree, Naïve base and Random Forest calculations on diabetes and pulse dataset. After information order, the outcomes show that Random Forest's calculation had a more precise arrangement with 98% exactness.

Keywords: Data Mining; Decision tree; Naive base; Random forestClassification; blood pressure