About this Research Topic
Electrical activity in the heart is coordinated with the mechanical contraction. Advances in nonlinear analysis techniques of electrical signal processing could lead to a better understanding, diagnosis, and treatment of cardiac diseases. Numerous ways to record electrical activity from the heart, including body-surface single- or multi-leads electrogram (ECG), intracardiac electrograms (iEGMs), signals from wearable devices etc., reflect different nature of such recordings. Therefore, development of various signal processing and data analysis techniques based on different nonlinear and machine learning (ML) approaches are warranted.
In addition to traditional methods of ECG analysis based on filtering, spectral analysis, statistical approaches etc., various nonlinear dynamic modeling and ML approaches have been recently developed to perform quantitative analysis of electrical signals from the heart. The aim of this Research Topic is to cover recent advances and novel research trends in such approaches aiming to discriminate between normal and abnormal cardiac rhythms, such as atrial (AF), ventricular fibrillation (VF), and other cardiac abnormalities to improve arrhythmia diagnosis in the hearts.
We welcome original research and review articles on the following themes:
• Discrimination between normal and abnormal electrical activity in the heart
• Single- and multi-lead ECG, IEGMs analysis
• Analysis and characterization of arrhythmia progression in the heart
• Dynamic modeling and ML approaches for prediction of cardiac arrhythmias
• Improving arrhythmia prediction based on data from wearable devices
Keywords: Machine Learning, Cardiac Rhythms, Dynamics, ECG/EMG Analysis, Arrhythmia Prediction
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.