Detection of Type 2 Diabetes Mellitus Disease with Data Mining Approach Using Support Vector Machine

摘要

Diabetes is a chronic disease and a majorudproblem of morbidity and mortality in developingudcountries. The International Diabetes Federationud(IDF) estimates that 285 million people around theudworld have diabetes. This total is expected to rise toud438 million within 20 years. Type 2 diabetes (TTD)udis the most common type of diabetes and accounts forud90-95% of all diabetes. Detection of TTD from various factors or symptoms became an issue which was not free from false presumptions accompanied by unpredictable effects. According to this context,data mining could be used as an alternative way,help us in knowledge discovery from data. This paper utilize support vector machine (SVM) in theuddata mining process to acquire information from historical data of patient medical records. It offers a decision-making support through early detection of TTD for physicians and others.