Version 1
: Received: 9 November 2017 / Approved: 9 November 2017 / Online: 9 November 2017 (05:47:22 CET)
How to cite:
Zhang, Y.; liu, H.; Wei, S.; Liu, C. Comparing Performance of Nonlinear Complexity Metrics for Assessing Quality of ECGs Collected in Real Time. Preprints2017, 2017110060. https://doi.org/10.20944/preprints201711.0060.v1
Zhang, Y.; liu, H.; Wei, S.; Liu, C. Comparing Performance of Nonlinear Complexity Metrics for Assessing Quality of ECGs Collected in Real Time. Preprints 2017, 2017110060. https://doi.org/10.20944/preprints201711.0060.v1
Zhang, Y.; liu, H.; Wei, S.; Liu, C. Comparing Performance of Nonlinear Complexity Metrics for Assessing Quality of ECGs Collected in Real Time. Preprints2017, 2017110060. https://doi.org/10.20944/preprints201711.0060.v1
APA Style
Zhang, Y., liu, H., Wei, S., & Liu, C. (2017). Comparing Performance of Nonlinear Complexity Metrics for Assessing Quality of ECGs Collected in Real Time. Preprints. https://doi.org/10.20944/preprints201711.0060.v1
Chicago/Turabian Style
Zhang, Y., Shoushui Wei and Chengyu Liu. 2017 "Comparing Performance of Nonlinear Complexity Metrics for Assessing Quality of ECGs Collected in Real Time" Preprints. https://doi.org/10.20944/preprints201711.0060.v1
Abstract
We compared performance of a novel encoding Lempel-Ziv complexity (ELZC) with approximate entropy (ApEn), sample entropy (SmpEn) and permutation entropy (PerEn) as nonlinear metric to assess ECG quality. Firstly to compare performance of discerning randomness and inherent nonlinear properties within time series, this study calculated the aforementioned four nonlinear complexity values on several typical artificial time series i.e., Gauss noise, two kinds of noisy time series, two kinds of Logistic series and periodic series, respectively. Then for analyzing sensitivity of the aforementioned four complexity methods to content level of different types noise within ECG recordings, we investigated variation trend of ELZC, ApEn, SmpEn and PerEn in several synthetic ECG recordings containing different types noise (i.e., baseline wander, muscle artefacts, electrode motion, power line and mixed noise) and different signal noise ratios (i.e., 15, 10, 5, 0, −5 and −10 dB). Finally, the four complexity methods were employed to classify the quality of real ECG recordings from the PhysioNet/Computing in Cardiology Challenge 2011 (CINC 2011) of the MIT databases, then receiver operating characteristic curves (ROC) and their corresponding area under curve (AUC) were yielded. The results showed ELZC could not only distinguish randomness and chaotic within time series but also reflect content level of noise within time series, and the highest AUC of PerEn, ELZC, SmpEn and ApEn were 0.850, 0.695, 0.474 and 0.461, respectively. The results demonstrated PerEn and ELZC were more effectively than ApEn and SmpEn for assessing ECG quality.
Keywords
ECG quality assessment; complexity; entropy; ROC
Subject
Computer Science and Mathematics, Applied Mathematics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
