Classification of Type 2 Diabetes Using Machine Learning Techniques

Diabetes is a lifelong chronic disease defined by disorders in protein, fat and carbohydrate metabolism as result of complete or partial deficiency insulin hormone secreted from the pancreas. This caused absence body. Normal also breaks down intestines to convert nutrients into glucose. Then, when this glucose passes through blood, level sugar blood rises. In healthy people, transported cells with help hormone, which Because can not be cell if there impaired effect body, increases develops an increase (hyperglycemia), called diabetes. Early diagnosis diseases that will occur insulin, vital for human great importance. The aim study use machine learning techniques diagnose Type 2 diabetes using medical laboratory data. As techniques, J48, Random Forest, Tree IBk algorithms WEKA programme were used. study, 400 patient data investigated. 6 tests such age, gender, glucose, HbA1C, HGB urine selected input All four used successfully trained. highest accuracy value was found 96.97% Forest algorithm, recall F-measure values 98.47% 96.24%, respectively.