Enhanced Heart Disease Detection using Hyperparameter-Tuned Random Forest Ensemble Method

Heart related disorders relics as for emostreason of mortality worldwide, emphasizing the significant need for accurate and timely detection methods. This work presents a machine learning approach tailored for detecting heart-related disorders, and the random forest algorithm is enhanced with an ensemble learning approach (RF-EM). Within the domain of heart disease detection, the Random Forest technique stands out for its effectiveness, mainly due to its ability to manage highdimensional datasets and large volumes of data efficiently. Its incorporation of randomness at two pivotal stages - through the random sampling of data points with replacement and the random feature selection at each split - acts as a protective measure against overfitting, a common challenge encountered in traditional decision tree models. Three distinct datasets - Cleveland, Stat log, and Hungarian - are utilized to train the RFEM model. Additionally, the model undergoes a meticulous hyperparameter tuning process to optimize its performance before training commencement. This rigorous approach ensures that the Random Forest Ensemble Method is finely tuned and trained on diverse datasets, bolstering its robustness and effectiveness in detecting heart disease. An exhaustive analysis shows that the Random Forest classifier achieves an accuracy of 96.31% with default hyperparameter settings. However, upon implementing hyperparameter optimization techniques, the precision is elevated to 97.61%. Additionally, by using the grid search Cross-Validation (CV) method, the precision is promoted to 97.90%. Such findings unequivocally illustrate that the proposed Random Forest Ensemble Method performs better in predicting heart disease.