Computational Intelligence for Automatic Detection Cardiac Arrhythmia from ECG Signals: Taxonomy and Open Issues

Abstract

Cardiac arrhythmia is a medical disorder, in which the heart beats sporadically or irregularly leading to serious health consequences if left untreated. Early detection of arrhythmias is essential for timely intervention and management of the condition. Recently, there has been a growing interest in using computational intelligence techniques to automatically detect arrhythmias from electrocardiogram (ECG) signals. This approach offers the potential to improve the accuracy and efficiency of arrhythmia detection, as well as reduce the workload on healthcare professionals. This work reviews the current state-of-the-art ML methods for detecting arrhythmias including deep neural networks, support vector machines, and random forests. We will also discuss the challenges associated with using these techniques, such as the need for large and diverse datasets, and the interpretation of model outputs. We also highlight the open research that require further research and development to fully realize the potential of these algorithms in clinical practice.