Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019:7:88357-88368.
doi: 10.1109/access.2019.2926199. Epub 2019 Jul 1.

Noise Detection in Electrocardiogram Signals for Intensive Care Unit Patients

Syed Khairul Bashar  1 , Eric Ding  2 , Allan J Walkey  3 , David D McManus  2 , Ki H Chon  1
Affiliations

Noise Detection in Electrocardiogram Signals for Intensive Care Unit Patients

Syed Khairul Bashar et al. IEEE Access. 2019.

Abstract

Long term electrocardiogram (ECG) signals recorded in an intensive care unit (ICU) are often corrupted by severe motion and noise artifacts (MNA), which may lead to many false alarms including inaccurate detection of atrial fibrillation (AF). We developed an automated method to detect MNA from ECG recordings in the Medical Information Mart for Intensive Care (MIMIC) III database. Since AF detection is often based on identification of irregular RR intervals derived from the QRS complexes, the main design focus of our MNA detection algorithm was to identify corrupted QRS complexes of the ECG signals. The MNA in the MIMIC III database contain not only motion-induced noise, but also a plethora of non-ECG waveforms, which must also be automatically identified. Our algorithm is designed to first discriminate between ECG and non-ECG waveforms using both time and spectral-domain properties. For the segments of data containing ECG waveforms, a time-frequency spectrum and its sub-band decomposition approach were used to identify MNA, and high frequency noise ECG segments, respectively. The algorithm was tested on data from 35 subjects in normal sinus rhythm and 25 AF subjects. The proposed method is shown to accurately discriminate between segments that contained real ECG waveforms and those that did not, even though the latter were numerous in some subjects. In addition, we found a significant reduction (> 94%) in false positive detection of AF in normal subjects when our MNA detection algorithm was used. Without using it, we inaccurately detected AF owing to the MNA.

Keywords: Atrial fibrillation; ICU; artifacts; electrocardiogram; false alarm; noise; peak; variance.

PubMed Disclaimer

Figures

Fig. 1.
Fig. 1.
Sample recordings showing (a) abrupt signal change and (b) low amplitude noise.
Fig. 2.
Fig. 2.
A sample 1 minute recording exhibiting a non-ECG shaped signal.
Fig. 3.
Fig. 3.
(a) 1 minute ECG segment; (b) PSD of the ECG segment shown in (a); (c) 1 minute non-ECG waveforms and (d) PSD of the signal segment shown in 3 (c).
Fig. 4.
Fig. 4.
Flow chart of the ECG-containing segment detection process.
Fig. 5.
Fig. 5.
(a) Sample 15 second ECG segment and (b) Time-frequency spectra of the Fig. 5 (a) signal obtained by VFCDM (log scale).
Fig. 6.
Fig. 6.
(a) DPA of the clean TFS (at ~2nd second) and (b) DPA of the noisy TFS (at ~6th second).
Fig. 7.
Fig. 7.
(a) DPA of the ECG segment shown in Fig. 5 (a). (b -c) VAR and INT values obtained from the DPA.
Fig. 8.
Fig. 8.
(a) Sample 1 minute ECG segment and (b) Noise artifact detection output for the data shown in (a) segment.
Fig. 9.
Fig. 9.
(a), (b) Sample 30 second ECG segments corrupted with HF muscle artifacts.
Fig. 10.
Fig. 10.
(a) Sample 10 second clean ECG segment; (b) the second VFCDM component of Fig. 10 (a); (c) sample 10 second HF corrupted ECG segment and (d) the second VFCDM component of Fig. 10 (c).
Fig. 11.
Fig. 11.
(a) Sample one minute NSR ECG segment and (b) Noise artifact detection output for this segment.
Fig. 12.
Fig. 12.
(a) Sample AF ECG segment and (b) Noise artifact detection output for this segment.
See this image and copyright information in PMC

References

    1. Donchin Y and Seagull FJ, “The hostile environment of the intensive care unit,” Curr. Opin. Crit. Care, vol. 8, no. 4, p. 316, August 2002. - PubMed
    1. Kishimoto Y, Kutsuna Y, and Oguri K, “Detecting motion artifact ECG noise during sleeping by means of a tri-axis accelerometer,” Conf. Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. IEEE Eng. Med. Biol. Soc. Annu. Conf, vol. 2007, pp. 2669–2672, 2007. - PubMed
    1. Behar J, Oster J, Li Q, and Clifford GD, “ECG signal quality during arrhythmia and its application to false alarm reduction,” IEEE Trans. Biomed. Eng, vol. 60, no. 6, pp. 1660–1666, June 2013. - PubMed
    1. Di Marco LY et al., “Evaluation of an algorithm based on single-condition decision rules for binary classification of 12-lead ambulatory ECG recording quality,” Physiol. Meas, vol. 33, no. 9, pp. 1435–1448, September 2012. - PubMed
    1. Clifford GD, Azuaje F, and McSharry P, Advanced Methods And Tools for ECG Data Analysis. Norwood, MA, USA: Artech House, Inc., 2006.