ECG Classification Using Machine Learning

In contemporary healthcare, Electrocardiography (ECG) played a crucial role in the diagnosis and monitoring of heart conditions. This paper introduced an automated system that meticulously processed ECG records, with a focus on extracting essential parameters. The data were sourced from multiple databases, including the prestigious MIT-BIH Arrhythmia Database and many more databases. The evaluation phase involved the meticulous assessment of machine learning models, specifically Logistic Regression, Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), for the purpose of classifying ECG records. A noteworthy aspect of this research lies in its innovative approach to classify records of the datasets, thereby enabling the detection of a wide range of cardiac conditions, such as Normal Sinus, Tachycardia, Bradycardia, First-Degree Heart Block, Long QT Syndrome, ST Elevation, and ST Depression. The automated system presented in this paper offers significant support for efficient heart health assessment, which, in turn, facilitates timely interventions and well-informed decisions, potentially contributing to a reduction in the burden of cardiac conditions. This research contributes a comprehensive and valuable system for the processing of ECG records, which promises to aid medical practitioners and researchers in enhancing patient care and advancing early arrhythmia detection. Keywords: Electrocardiography, SVM, KNN, Cardiac Parameters, Machine Learning, Arrhythmia, Logistic Regression, Random Forest.