Comparison of Machine Learning Algorithms for the Quality Assessment of Wearable ECG Signals Via Lenovo H3 Devices
Open Access
- 16 April 2021
- journal article
- research article
- Published by Springer Nature in Journal of Medical and Biological Engineering
- Vol. 41 (2) , 231-240
Abstract
Purpose: Electrocardiogram (ECG) signals collected from wearable devices are easily corrupted with surrounding noise and artefacts, where the signal-to-noise ratio (SNR) of wearable ECG signals is significantly lower than that from hospital ECG machines. To meet the requirements for monitoring heart disease via wearable devices, eliminating useless or poor-quality ECG signals (e.g., lead-falls and low SNRs) can be solved by signal quality assessment algorithms. Methods: To compensate for the deficiency of the existing ECG quality assessment system, a wearable ECG signal dataset from heart disease patients collected by Lenovo H3 devices was constructed. Then, this paper compares the performance of three machine learning algorithms, i.e., the traditional support vector machine (SVM), least-squares SVM (LS-SVM) and long short-term memory (LSTM) algorithms. Different non-morphological signal quality indices (i.e., the approximate entropy (ApEn), sample entropy (SaEn), fuzzy measure entropy (FMEn), Hurst exponent (HE), kurtosis (K) and power spectral density (PSD) features) extracted from the original ECG signals are fed into the three algorithms as input. Results: The true positive rate, true negative rate, sensitivity and accuracy are used to evaluate the performance of each method, and the LSTM algorithm achieves the best results on these metrics (97.14%, 86.8%, 97.46% and 95.47%, respectively). Conclusions: Among the three algorithms, the LSTM-based quality assessment method is the most suitable for the signals collected by the Lenovo H3 devices. The results also show that the combination of statistical features can effectively evaluate the quality of ECG signals.Keywords
Funding Information
- National Key Research and Development Program of China (2017YFB1303200)
- Jiangsu Provincial Key Research and Development Program (BE2017735)
- National Natural Science Foundation of China (61571113, 81871444, 62071241)
- National Natural Science Foundation of China (62001240)
- Zhejiang Provincial Natural Science Foundation of China (LY17F010003)
This publication has 25 references indexed in Scilit:
- Assessment of signal quality measured with a smart 12‐lead ECG acquisition T‐shirtAnnals of Noninvasive Electrocardiology, 2019
- Signal Quality Assessment and Lightweight QRS Detection for Wearable ECG SmartVest SystemIEEE Internet of Things Journal, 2018
- Comparing the Performance of Random Forest, SVM and Their Variants for ECG Quality Assessment Combined with Nonlinear FeaturesJournal of Medical and Biological Engineering, 2018
- A machine learning approach to multi-level ECG signal quality classificationComputer Methods and Programs in Biomedicine, 2014
- ECG quality assessment based on a kernel support vector machine and genetic algorithm with a feature matrixJournal of Zhejiang University SCIENCE C, 2014
- Electrocardiogram signal quality assessment using an artificially reconstructed target leadComputer Methods in Biomechanics and Biomedical Engineering, 2014
- ECG Signal Quality During Arrhythmia and Its Application to False Alarm ReductionIEEE Transactions on Biomedical Engineering, 2013
- Signal quality and data fusion for false alarm reduction in the intensive care unitJournal of Electrocardiology, 2012
- Electrocardiogram signal quality measures for unsupervised telehealth environmentsPhysiological Measurement, 2012
- Signal quality indices and data fusion for determining clinical acceptability of electrocardiogramsPhysiological Measurement, 2012