<![CDATA[Diabetes is a chronic disease caused by impaired insulin production, which causes an increase in blood sugar levels and has the potential to cause serious complications. Early detection of this disease is very important to prevent the risk of complications in patients. This research aims to implement a data mining method with the K-Nearest Neighbors (KNN) algorithm in the classification of diabetes, using attributes such as blood pressure, age, obesity and family history as variables. The KNN method is used to identify patterns in data that are relevant to potential diabetes, with stages of model learning and performance evaluation. The analysis results show that the KNN algorithm is able to classify data with a fairly good level of accuracy, showing its effectiveness in detecting possible diabetes in patients. The implementation of this algorithm shows potential as a supporting tool in the early diagnosis of diabetes.]]>
Copyrights © 2024
