Arrhythmia classification is a critical area of research in cardiology, given the significant health risks associated with irregular heart rhythms. This research study presents a comprehensive survey of current methodologies employed for the detection and classification of arrhythmias from electrocardiogram (ECG) signals. The study examines a variety of methods, including sophisticated deep learning techniques like Convolutional Neural Networks (CNN) and Long Short-Term Memory Networks (LSTM) in addition to more conventional machine learning algorithms like Support Vector Machines (SVM), Random Forests (RF), and K-Nearest Neighbors (KNN). Additionally, the research study provides critical information that is relevant to medical diagnostics, such as the weak generalizability hampered by imbalanced datasets, whose management is well illustrated by the research study as a successful way to increase model performance.

Arrhythmias ECG Signals Data Imbalance Irregular Heart Rhythms Classification Techniques