The growing prevalence of cardiovascular diseases necessitates the development of efficient and accurate diagnostic tools. Electrocardiogram (ECG) signal classification, facilitated by machine learning algorithms, has emerged as a promising method for improving the diagnosis and early detection of heart diseases. This study presents a comparative analysis of various machine-learning algorithms, namely Gradient Boosting, Stacking Classifier, Voting Classifier, XGBoost, and CatBoost, for the classification of ECG signals. By leveraging advanced feature extraction techniques, we explore the effectiveness of these algorithms in distinguishing between normal and abnormal ECG patterns. The proposed methodology demonstrates the potential of machine learning in automating ECG signal analysis, thereby enhancing diagnostic accuracy and reducing the reliance on traditional, time-consuming manual interpretations. Additionally, the integration of these techniques offers a cost-effective solution, particularly in resource-constrained settings where access to expert cardiologists may be limited. The results of this study contribute to the ongoing efforts to improve heart disease detection systems using machine learning.

Keywords: ECG Classification, Machine Learning, Feature Extraction, Gradient Boosting, Stacking Classifier, Voting Classifier, XGBoost, CatBoost, Cardiovascular Diseases, Early Diagnosis.