Classification For Predicting Heart Disease Using The K Nearest Neighbor Method Sylvani General Hospital Binjai City

Abstract

The heart is a hollow organ and has four chambers or chambers located between the two lungs in the middle of the thoracic cavity. The heart has an important function in the human body, namely as a pump that presses blood so that it can flow to all parts of the body through arteries or veins. Disease caused by plaque buildup in the coronary arteries which supply oxygen to the heart muscle, resulting in severe damage to the heart is called coronary heart disease. Many factors can increase the risk of heart disease. These risk factors consist of risk factors that cannot be modified such as family history, age and gender and risk factors that can be modified such as hypertension, smoking habits, diabetes, dyslipidemia, obesity, lack of physical activity, diet and stress. K-Nearest Neighbor is a method for classifying new objects based on their (K) closest neighbors. K-NN includes a Supervised Learning algorithm where the results of querying new instances are classified based on the majority of categories in KNN. The class that appears the most will be the classification result class. This algorithm only stores feature vectors and classifies the learning data. In the classification phase, the same features are calculated for the test data (whose classification is unknown). The distance of this new vector to all data vectors is calculated, and the k closest ones are taken. The newly classified point is predicted to be among the most classified of these points. From the data with the majority categories there are Positive and Negative categories. From the majority number (Positive > Negative) it can be concluded that new data (data No. 20) (K1=1, K2=0.5, K3=0, K4=1, K5=0, K6=1, K7=0, 5, K8=1) is included in the Positive category.