Diabetes Classification Analysis Using the Euclidean Distance Method Based on the K-Nearest Neighbors Algorithm

Abstract

Diabetes is a chronic disease characterized by high blood sugar (glucose) levels. Diabetes can increase the risk of a number of eye problems, some of which can lead to vision loss. It is estimated that 9.1 million Indonesians suffer from diabetes. Based on age group, most people with diabetes are in the 55-74 year age range. However, this disease is also experienced by young people in their 20s to 40s. One way to detect the classification of diabetes in machine learning is to use a dataset as training data so that performance testing can be carried out with the right classification method. The method used in this study is the K-Nearest Neighbor (KNN) algorithm, which is a method for classifying objects based on learning data that is closest to the object. The results of this study are Pattern Recognition in determining the right K value so that it shows a good accuracy value. At this stage, the value of K = 19 shows a good accuracy value, which is about 76% with an error rate of K = 19, which is about 24%

Diabetes Mellitus Early Detection Simulation using The K-Nearest Neighbors Algorithm with Cloud-Based Runtime (COLAB)

“…The highest accuracy obtained was 66.6667% with a value of k = 5. Mahalisa, et al [16] also explained in their research that object classification is very important. The number of attributes can affect the performance of an algorithm, in the simulation results a good accuracy value of 76% was obtained.…”