Performance Comparison Analysis of Predicting the Heart Diseases using Machine Learning Algorithms

In the medical field, the process of Heart Disease (HD) prediction process is a challenging task even in the modern digital world. Even though the data generated by the healthcare industries are huge, the data scientists are working tremendously to determine the correlation between the various parameters that causes the HDs. Therefore, there exists a need to predict the HDs to safeguard the human kind. The proposed method uses the Machine Learning (ML) models to predict the HD based on the existing symptoms of the patients. The dataset from the UPI repository is used to evaluate the performance of the proposed models. The various parameters namely precision (p), recall (r), and accuracy (a) are used evaluate the performance measures of the ML models. Observing the results concluded that, the Random Forest model outperformed the other models such as XGBoost, Decision Tree and traditional Neural Network model regarding the prediction accuracy with respect to UCI dataset.