Survey on atrial fibrillation detection from a single-lead ECG wave for Internet of Medical Things

Abstract Recent advances of Internet of Medical Things have allowed for continuous heart rhythm monitoring in a comfortable fashion. Single lead Electrocardiograph (ECG) is first collected by the wearable devices, and then some intelligent approaches are employed for automatic recognition of heart rhythms. Because the single lead ECG wave is different from traditional 12-leads Holter-based ECG signal in terms of high noise/artifact and the missing of other channels, specific algorithms for pattern recognition of the single lead ECG waves have been proposed in recent years. This paper systematically surveys state-of-the-art methods for screening atrial fibrillation from a single lead ECG wave. The database and performance metrics for this problem are demonstrated, the data preprocessing and feature extraction techniques are collected, and then the learning methods in terms of machine learning and deep learning are comparatively summarized. Specifically, the techniques for data preprocessing are reviewed and the most common and powerful features are listed, which are capable of providing a guideline for researchers aiming at developing AF detection algorithms. Finally, we discuss the potential contributors that are probably helpful for screening the atrial fibrillation from a single lead ECG wave.