Machine Learning for Cardiac Arrhythmia Detection: A Systematic Survey

Abstract

Abstract A significant global worry is a substantial rise in cardiac arrhythmia cases brought on by improper food and lifestyle choices. Manual analysis of the report of the electrocardiogram to detect the presence of an anomaly is a time-consuming task. Hence, it is necessary to create an automated diagnosis system that can deliver results quickly and accurately. Numerous machine learning-based models were created by researchers working in this field to determine the severity of cardiac arrhythmias. This article provides an organized and thorough assessment of previous research in the field, with a particular emphasis on machine learning methods developed by different authors to detect cardiac arrhythmia. Additionally, covered is the performance analysis of the different algorithms. The difficulties associated with developing a model for cardiac arrhythmia and its potential future impact are finally examined in the conclusion section.