Application Of Machine Learning K-Nearest Neighbour Algorithm To Predict Diabetes

Abstract

Diabetes is a chronic disease characterized by high blood sugar (glucose) levels or above abnormal values. This can occur when the body is no longer able to absorb glucose properly or when the intake of glucose is higher than needed. Glucose is the main energy source for the cells of the human body. Glucose that accumulates over the long term in the body can lead to complications and more serious and life-threatening diseases. As a result, patients with diabetes must be predicted prior to the onset of disease complications. Machine learning is one of the branches of artificial intelligence that can be used to provide predictive value to datasets of diabetic patients. The tested dataset has 390 observations with data on cholesterol levels, glucose, HDL cholesterol, cholesterol ratio, age, gender, blood pressure, BMI, waist and hip width with its ratio, and the patient's height and weight as variables. Predictions are applied using the K-Nearest Neighbor method, which shows an accuracy of 93.58% with a k value of 3, using 20% of all data as test data.

Keywords

• diabetes, k-nearest neighbor, prediction, machine learning