Analysis of Data for Diabetics Patient

Abstract

Diabetes, a disease responsible for different kinds of diseases such as heart attack, kidney disease, blindness and renal failure etc. The most common disorder is the endocrine (hormone) system, occurs when blood sugar levels in the body consistently stay above normal. There are two types of diabetic; one is body's inability to make insulin and another is body not responding to the effects of insulin. In our developing country Bangladesh, Diabetes is a costly disease whose risk is increasing at alarming rate. This paper evaluates the selected classification algorithms for the classification of some Diabetes patient datasets. Classification algorithms considered here are Naive Bayes classification (NBC), Bagging algorithm, KStar algorithm, Logistic algorithm and Hoeffding tree. These algorithms are evaluated based on four criteria: Accuracy, Precision, Sensitivity and Specificity. Collected datasets of diabetes affected people are firstly preprocessed then some investigation based on mentioned algorithm has been executed successfully. From the investigation result it is found that, KStar algorithm is the best as it gives high accuracy with the low error. Here it is said that, some parameters are responsible for diabetes.