Abstract
Noise and low quality of ECG signals acquired from Holter or wearable devices deteriorate the accuracy and robustness of R-peak detection algorithms. This paper presents a generic and robust system for R-peak detection in Holter ECG signals. While many proposed algorithms have successfully addressed the problem of ECG R-peak detection, there is still a notable gap in the performance of these detectors on such low-quality ECG records. In this study, a novel implementation of the 1D Convolutional Neural Network (CNN) is used integrated with a verification model to reduce the number of false alarms. This CNN architecture consists of an encoder block and a corresponding decoder block followed by a sample-wise classification layer to construct the 1D segmentation map of R-peaks from the input ECG signal. Once the proposed model has been trained, it can solely be used to detect R-peaks possibly in a single channel ECG data stream quickly and accurately, or alternatively, such a solution can be conveniently employed for real-time monitoring on a lightweight portable device. The model is tested on two open-access ECG databases: The China Physiological Signal Challenge (2020) database (CPSC-DB) with more than one million beats, and the commonly used MIT-BIH Arrhythmia Database (MIT-DB). Experimental results demonstrate that the proposed systematic approach achieves 99.30% F1-score, 99.69% recall, and 98.91% precision in CPSC-DB, which is the best R-peak detection performance ever achieved. Results also demonstrate similar or better performance than most competing algorithms on MIT-DB with 99.83% F1-score, 99.85% recall, and 99.82% precision. Compared to all competing methods, the proposed approach can reduce the false-positives and false-negatives in Holter ECG signals by more than 54% and 82%, respectively. Finally, the simple and invariant nature of the parameters leads to a highly generic system and therefore applicable to any ECG dataset.
Highlights
ACCURATE detection of R-peaks is essential for the diagnosis of cardiovascular diseases (CVD) in electrocardiogram (ECG) ) signals
Many R-peak detection methods have been proposed throughout the last several decades, robust and accurate peak detection is still a challenging problem, especially in noisy, degraded, and dynamically varying rhythms, common in Holter registers
An extensive set of experimental results show that the proposed approach outperforms all state-of-the-art R-peak detection methods in CPSC-DB with a significant performance gap while it achieves a similar or better result in MIT-BIH Arrhythmia Database (MIT-DB) without explicit training in this dataset
Summary
ACCURATE detection of R-peaks is essential for the diagnosis of cardiovascular diseases (CVD) in electrocardiogram (ECG) ) signals. The QRS complex, which is dependent on the accurate detection of R-peak, is the most important feature in the diagnosis of several cardiac pathologies. The introduction of low-cost wearable ECG monitors gives us a significant motive to investigate highly accurate and robust automated detection of R-peaks in single-lead ECG signals. R-peak detection is severely affected by the ECG signals with such poor signal quality and high noise levels [2]. R-peak detection (segmentation) is the base of arrhythmia detection and classification. ECG-based applications are generally divided into four phases: preprocessing (filtering), ECG signal segmentation (QRS complex detection), feature extraction, and classification algorithms. Poor segmentation performance propagates the error to subsequent steps and directly reduces classification efficiency. Much of the work in the literature focuses on minimizing the number of false positives during the classification step, ignoring the fact that the error started to spread during the segmentation step [3], [4]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
