Heart Disease Prediction Using Different Machine Learning Algorithms

Heart disease (HD) cases are increasing rapidly every day, so it is very crucial to detect them beforehand. In recent times, machine learning algorithms (MLA) are trending for heart or cardiovascular disease prediction in the healthcare field. Data mining techniques such as reinforcement, unsupervised, and supervised play a crucial role in examining the enormous amount of data in the medical field industry. The available dataset of HD individuals from the Cleveland database of the UCI repository is employed to test and verify the performance of MLA. This article makes an early prediction of HD by executing different MLA, for example, decision tree (DT), random forest (RF), and logistic regression (LR). After the comparative study of three algorithms, we found that the DT is the most efficient algorithm with the highest accuracy of 94.7 percent. This value is higher than the recently reported value of 83.87 percent.