ECG-based heartbeat classification for arrhythmia detection : a survey.

Abstract

An electrocardiogram (ECG) measures the electric activity of the heart and has been widelyused for detecting heart diseases due to its simplicity and non-invasive nature. By analyzingthe electrical signal of each heartbeat, i.e., the combination of action impulse waveformsproduced by different specialized cardiac tissues found in the heart, it is possible to detectsome of its abnormalities. In the last decades, several works were developed to produceautomatic ECG-based heartbeat classification methods. In this work, we survey the currentstate-of-the-art methods of ECG-based automated abnormalities heartbeat classificationby presenting the ECG signal preprocessing, the heartbeat segmentation techniques, thefeature description methods and the learning algorithms used. In addition, we describesome of the databases used for evaluation of methods indicated by a well-known standarddeveloped by the Association for the Advancement of Medical Instrumentation (AAMI) anddescribed in ANSI/AAMI EC57:1998/(R)2008 (ANSI/AAMI, 2008). Finally, we discuss limitationsand drawbacks of the methods in the literature presenting concluding remarks and futurechallenges, and also we propose an evaluation process workflow to guide authors in futureworks.