KLASIFIKASI MENGGUNAKAN METODE SUPPORT VECTOR MACHINE DAN RANDOM FOREST UNTUK DETEKSI AWAL RISIKO DIABETES MELITUS

Abstract

Diabetes Mellitus is one of the four leading causes of death and therefore possible treatments are of crucial importance to the world leaders. Prevention and control of Diabetes Mellitus are often done by implementing a healthy lifestyle. Thus, both people with risk factors and people diagnosed with Diabetes Mellitus can control their disease in order to prevent complications or premature death.. For a proper education and standardized disease management the early detection of Diabetes Mellitus is necessary, which led to this conducted study about the classification of early detection of Diabetes Mellitus risk by utilizing the use of Machine Learning. The classification algorithms used are the Support Vector Machine and Random Forest where the performance analysis of the two methods will be seen in classifying Diabetes Mellitus data. The type of data used in this study is secondary data obtained from the official website of the UCI Machine Learning Repository consisting of 520 diabetes patient data taken from Sylhet Diabetic Hospital in Bangladesh with 16 independent variables and 1 dependent variable. The dependent variable categorizes the test result into positive and negative Diabetes Mellitus classes. The results of this study indicate that the Random Forest classification algorithm produces a better classification performance on Accuracy (98.08%), Recall (97.87%), Precision (98.92), and F1_Score (88.40%).