A Novel Algorithm for Automated Human Single-Lead ECG Pre-Annotation and Beat-to-Beat Separation for Heartbeat Classification Using Autoencoders

An electrocardiogram (ECG) is used to check the electrical activity of the heart over a limited short-term or long-term period. Short-term observations are often used in hospitals or clinics, whereas long-term observations (often called continuous or stream-like ECG observations) are used to monitor the heart’s electrical activity on a daily basis and during different daily activities, such as sleeping, running, eating, etc. ECG can reflect the normal sinus rhythm as well as different heart problems, which might vary from Premature Atrial Contractions (PAC) and Premature Ventricular Contractions (PVC), to Sinus Arrest and many other problems. In order to perform such monitoring on a daily basis, it is very important to implement automated solutions that perform most of the work of the daily ECG analysis and could alert the doctors in case of any problem, and could even detect the type of the problem in order for the doctors to have an immediate report about the patient’s health status. This paper aims to provide a workflow for abnormal ECG signals detection from different sources of digitized ECG signals, including ambulatory devices. We propose an algorithm for ECG pre-annotation and beat-to-beat separation for heartbeat classification using Autoencoders. The algorithm includes the training of different models for different types of abnormal ECG signals, and has shown promising results for normal sinus rhythm and PVC compared to other solutions. This solution is proposed for no-noise and noisy signals as well