An X-ray on Methods Aiming at Arrhythmia Classification in Ecg Signals

Arrhythmias (i.e., irregular cardiac beat) classification in electrocardiogram (ECG) signals consists in an important issue for heart disease diagnosis due to the non-invasive nature of the ECG exam. In this paper, we present an X-ray, a generic view, on methods aiming at arrhythmia classification in ECG signals, which starts with signal preprocessing, and then segmentation of each heartbeat and so before classification, the feature extraction step. We also analyze and criticize the results of some arrhythmia classification methods present in the literature in terms of how the samples are chosen for train/test the classifier and the impact of this choice in their accuracies/sensitivities.