R-Peak Detection in Holter ECG Signals Using Non-Negative Matrix Factorization

Holter monitoring is mainly used for medical follow-up and diagnosis of patients with suspected cardiac arrhythmia such as heart rhythm irregularities that can be missed during classical electrocardiogram recording (ECG). However, these long-term continuous recordings represent a large amount of data that cannot be processed by hand. In this article, we present a new method based on Non-negative Matrix Factorization (NMF) to detect R-peaks in Holter signals. The approach consists in two stages: source separation based on the different time-frequency patterns of the QRS complexes and the other waves of the signal (P and T waves) and R-peak detection using Automatic Objective Thresholding (AOT). The proposed approach is validated on the MIT-BIH Arrhythmia database and achieves an average sensitivity of 99.59% and a precision of 99.69%. Using the MIT-BIH Noise Stress Test database, we also show the ability of our approach to discriminate R-peaks in signals contaminated with different noises.