Review on higher-order neural units to monitor cardiac arrhythmia patterns

Abstract

An electrocardiogram (ECG) is a non-invasive technique that checks for problems with the electrical activity of a patient's heart. ECG is economical and extremely versatile. Some of its characteristics make it a very useful tool to detect cardiac pathologies. The ECG records a series of characteristic waves called PQRST; however, the QRS complex analysis enables the detection of a type of arrhythmia in an ECG. Technological developments enable the storage of a large amount of data, from which knowledge extraction is impossible without a powerful data processing tool; in particular, an adequate signal processing tool, whose output provides reliable parameters as a basis to make a precise clinical diagnosis. Thus, ECG signal processing creates an opportunity to analyze and recognize possible arrhythmia patterns. This paper reviews the use of artificial neural networks (ANNs) to detect and recognize cardiac arrhythmia patterns. Recurrent neural networks (RNNs) and higher-order neural units are inspected. In addition, the potentials of using higher-order neural units such as the quadratic dynamic neural unit (D-QNU) and dynamic cubic neural unit (D-CNU) for cardiac arrhythmia detection are analyzed.