Journal
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
Volume 70, Issue -, Pages -Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIM.2021.3051412
Keywords
Electrocardiogram (ECG); ESP32; QRS complex detection; signal shape; signal trend
Ask authors/readers for more resources
This article presents an embedded algorithm for detecting the QRS complex of an ECG signal, with high accuracy demonstrated through performance evaluation on the MIT-BIH database. The algorithm is based on shape and appearance features, suitable for microcontroller systems and potentially valuable in wearable systems for long-term monitoring.
Electrocardiogram (ECG) is one of the most useful medical examinations for the monitoring of cardiovascular diseases. The position and the duration of the QRS complex on the ECG signal are very important in the diagnosis of these diseases. Even though several R-peak (and hence QRS complex) detection algorithms are available, most are based on complex computations that require off-line processing on a personal computer (PC). However, with the advances in wearable devices and telemedicine, an algorithm that can run efficiently on a microcontroller (or embedded system) is needed. This article presents the development of an embedded algorithm for the detection of the QRS complex of an ECG signal. The algorithm is based on the shape and appearance of the signal. It extracts certain characteristics like the shape of the QRS complex, its slope, trend, and the duration between two successive QRS complexes, and then use them to increase detection accuracy. First, the R-peak is detected through the application of three levels of tests using adaptive thresholds. Second, from each R position, the positions of Q and S are detected using three other tests. To evaluate the performance of the algorithm, the MIT-BIH database was used and the sensitivity, positive prediction, and F1 score were used as evaluation metrics. The algorithm obtained average F1 scores of 99.67%, 99.73%, and 99.83% for the MIT-BIH Arrhythmia, Pacemaker Rhythm, and the Normal Sinus Rhythm Databases, respectively. Both normal and abnormal ECG signals were used in this performance test. The algorithm was then implemented on a microcontroller system, and its accuracy and run time were evaluated. The obtained Fl score results were the same as on the personal computer (PC) and an average run time of 16.23 mu s per sample was obtained. The performance of the algorithm was also compared to other commonly used algorithms. The proposed algorithm has great potential in wearable systems for long-term monitoring.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available