Heart disease is a disease that has a high mortality rate, with more than 12 million deaths occurring throughout the world. Diagnosis of heart disease is very challenging due to the complex interdependence of several attribute factors. The problem that frequently encountered is the lack of accuracy in the classification process. Thus, a system is needed to carry out early diagnosis of heart disease. The structure of this research is to take a heart disease dataset from Kaggle. Then the data will be cleaned with preprocessing. The preprocessing process carried out is changing table names, checking missing values, and normalizing. 820 data will be trained using a Support Vector Machine and 205 data will be tested to find out how well the model can perform classification. The results of training and testing from a total of 1025 data will form a classification model. The model formed using the Support Vector Machine obtained confusion matrix results of 88 is True Positive data, 93 is True Negative data, 10 is False Positive data, and 14 is False Negative data. So the results of model training produce an accuracy of 88%.