Comparison of Machine Learning Techniques for Heart Disease Diagnosis and Prediction

This study compares heart disease prediction accuracy by applying artificial algorithms, such as Logistic Regression, Decision Tree, and Random Forest. This research uses 319,795 data on factors causing heart disease as a dataset, coupled with the k-fold cross-validation method, to select the best model of the three algorithms based on F1 score, accuracy, precision, and recall. The results showed that Decision Tree with a linear kernel produced the highest accuracy of 74.59% at 10fold. Meanwhile, Random Forest achieved the highest accuracy of 74.75% at 10-fold, while Logistic Regression achieved the highest accuracy of 71.97%. The findings of this study illustrate that the use of artificial intelligence algorithms can be beneficial in improving the accuracy of heart disease classification, which will assist medical personnel in diagnosing diseases more quickly, accurately, and precisely.