<![CDATA[Diabetes mellitus is a non-communicable disease that has spread throughout the world. Factors that can cause a person to suffer from diabetes mellitus include high blood pressure, obesity, history of diabetes mellitus in the family, age, as well as unhealthy lifestyle and diet. Another factor that triggers the high rate of death due to diabetes mellitus is the delay in diagnosis due to the small number of medical personnel, especially in small towns. Several clinical trials must be carried out to determine whether someone has diabetes mellitus or not; and the clinical trial process takes a long time. Based on these problems, a decision support system was made for the identification of diabetes mellitus using the K-Nearest Neighbor classification method with 8 variables, namely the number of pregnancies, glucose levels, blood pressure, triceps skinfold thickness, insulin, body mass index (BMI), family history of diabetes mellitus, and age. Based on implementation and testing, with a value of k = 23, an accuracy rate of 0.96 or 96% is obtained, the accuracy level is considered high enough so that this study is considered to have succeeded in implementing the KNN method for a decision support system for early identification of diabetes mellitus.]]>
Copyrights © 2021
