Predicting complications of type 2 diabetes use decision tree algorithms

The incidence of diabetes has doubled globally in the last 01 years and approximately 011 million people are being infected. The prevalence of diabetes annually increased about %6 worldwide. In this research we explain the relation between observed complications of type 0 diabetic patients and some related features like Blood Glucose Level, Blood Pressure, Age and Family History of the patient. Find out knowledge for Patient classification based on their symptoms is the main aim of this paper. Therefore, physicians use this knowledge to prevent some complications in patients with regard to diet and exercise and medications.In this study, for the first time, the risk of micro vascular complications, macro vascular complications, or both in patients and the characteristics affected by them have been studied. A new model according to CRISP Standard Methodology prepared in this paper. According to data mining and its method shown that high blood pressure, age and family history had the most influence on observed complications. Base on creating a decision tree, some rules are extracted that can be used as a pattern to predict the probability of occurring these complications in patients. According to used algorithms, C0.1 algorithm which has the highest accuracy98. %46, the most affected factors are recognized. Base on the created rules, for a new instant with specified features, can predict that this patient probably suffer from which complication

کلیدواژه ها:

type 0 diabetic ، diabetic complications ، Data mining ، decision tree ، C0.1 Algorithm