The Research on Analyzing Risk Factors of Type 2 Diabetes Mellitus Based on Improved Apriori Algorithm

Abstract

Purpose: We do it to improve the efficiency of analyzing risk factors of Type 2 Diabetes. Method: We use the patients' data from the information department of one tertiary referral hospital in Lanzhou which include course note of disease and their health record form January 2009 to March 2014.We find out one improved algorithm applies to analyze risk factors of Type 2 Diabetes based on original Apriori Algorithm and it's requirement. And we analyze the efficiency by programming both of the algorithms with C#. Result: We can analyze the chart of frequent item and support degree, time and number of records, time and support degree. Conclusion: This new improved Apriori Algorithm has a high efficiency in analyzing risk factors of Type 2 Diabetes. I. Introduction. Diabetes Mellitus is due to the secretion of insulin and the role of defects caused by chronic high blood sugar with carbohydrates, metabolic disabled of fat and protein chronic disease characterized. Type 2 Diabetes Mellitus, which is called non-insulin-dependent Diabetes Mellitus as well and due to insulin resistance with relatively lack of insulin secretion, holds 90% to 95% of all the patients with Diabetes Mellitus. Diabetes Mellitus has been one of the most common chronic non-communicable diseases with the prevalence showing a rising trend in the whole world recent years. It is predicted that the global total number of adults with Diabetes Mellitus will grow from 171 million in 2000 to 366 million in 2030, with a growth of 1.14 times(1). So research on Diabetes Mellitus is very important. We find defect of Apriori Algorithm in research on mining association rules of Type 2 Diabetes Mellitus risk factors. First, Apriori Algorithm has to used to scan the database once when generate a frequent item set each time. And second, when generating k candidate item sets from (k-1) frequent item sets, it will product many candidate item sets which is unnecessary later and have a long time in data mining of risk factors and a low work efficiency. We propose a modified Apriori Algorithm suitable for risk factors of Type 2 Diabetes Mellitus with a large data and attribute value of risk factors.