<![CDATA[Diabetes is a disease characterized by high levels of sugar in the blood which causes this disease to be very dangerous. If diabetes is not controlled properly it will lead to death. The death rate due to diabetes mellitus is relatively high because the patient does not feel the symptoms of diabetes or does not understand the characteristics of diabetes. To determine a person suffering from diabetes mellitus, several medical tests are needed so that the diagnostic results can be guaranteed authenticity and the clinical trial process certainly takes a long time. long. Based on these problems, a program for the classification of diabetes mellitus was made using the K-Nearest Neighbor (KNN) algorithm. The KNN algorithm is a method for classifying new objects based on training data that has the closest neighbor to the object. This study uses 8 variables, namely easy thirst, weight loss despite regular food consumption, high blood pressure, there is a history of diabetes in the family, wounds that are difficult to heal, frequent urination at night, results of blood sugar checks and age. The data used are 108 training data and 27 testing data resulting in 93% accuracy at K=9, 100% precision, 60% recall and 75% F1-Score. With an accuracy rate of 93%, this study is considered to have succeeded in applying the KNN method to classify diabetes mellitus.]]>
Copyrights © 2022
