Medical decision making diagnosis system integrating k-means and Naïve Bayes algorithms

Abstract

In this paper, by using data mining we can evaluate many patterns which will be use in future to make intelligent systems and decisions By data mining refers to various methods of identifying information or the adoption of solutions based on knowledge and data extraction of these data so that they can be used in various areas such as decision-making, the prediction value for the prediction and calculation. In our days the health industry has collected vast amounts of patient data, which, unfortunately, is not "produced" in order to give some hidden information, and thus to make effective decisions, which are connected with the base of the patient's data and are subject to data mining. This research work has developed a Decision Support in Heart Disease Prediction System (HDPS) using data mining modelling technique, namely, Naïve Bayes and K-means clustering algorithms that are one of the most popular clustering techniques; however, where the initial choice of the centroid strongly influences the final result. Using of medical data, such as age, sex, blood pressure and blood sugar levels, chest pain, electrocardiogram, analyzes of different study patient, etc. graphics can predict the likelihood of the patient. This paper shows the effectiveness of unsupervised learning techniques, which is a k-means clustering to improve teaching methods controlled, which is naive Bayes. It explores the integration of K-means clustering with naive Bayes in the diagnosis of disease patients. It also investigates different methods of initial centroid selection of the K-means clustering such as range, inlier, outlier, random attribute values, and random row methods in the diagnosis of heart disease patients. The results indicate that the integration of the K-means clustering with naïve Bayes with different initial centroid selecting naive Bayesian improve accuracy in diagnosis of the patient.