Heart disease ruins one of the primary causes of death worldwide, imposing the improvement of accurate and trustworthy prediction models for quick finding and intervention. The aim of this study is to evaluate and compare the performance of the prediction results by the three machine learning approaches Random Forest (RF), Artificial Neural Networks (ANN), and Extreme Gradient Boosting (XGBoost). The experimental work used on two benchmark datasets: Heart.csv and Heart Failure Clinical Records Dataset downloaded from the kaggle.com. To achieve high effectiveness data pre-processing, feature selection, and model fitting strategies were used. The results of three methods compared based on evaluation metrics such as accuracy, false positive rates, precision, recall and F1-score. To increase prediction accuracy, we used an efficient technique that involved data pre-processing, feature selection, and model fitting. To evaluate all these three models’ interpretability and computational efficiency a comparative analysis performed based on the metrics Accuracy, Precision, Recall and F1-Score. On both datasets Heart.csv and Heart_Failure_Clinical_Records_Dataset(downloaded from Kaggle.com website), Random Forest reliably achieved the highest prediction accuracy (95.5% & 90% respectively), trailed closely by XGBoost (93.9% & 91.67% respectively), while ANNreturned (89% & 90.33% respectively) depending on hyper parameter tuning. In terms of false positive rates, RF established lower FPR than XGBoost and ANN, obtained balanced sensitivity and specificity effectively. Feature selection enriched RF and XGBoost more significantly than ANN, representing that tree-based approaches inherently lever redundant features well. From the above experimental result shows that, while all three models have excellent predictive abilities, the Random Forest method’s improved performance and interpretability make it better suitable for clinical applications. Our study emphasises the relevance of ML approaches in detecting the heart diseases in advance, take timely medical decisions, and lowering patients’ risk of cardiovascular disease.