Removal of ECG Artifacts Affects Respiratory Muscle Fatigue Detection—A Simulation Study

Kahl, Lorenz; Hofmann, Ulrich G.

doi:10.3390/s21165663

Cited by 3 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Complex time-domain methods have been proposed for peripheral muscles based on wavelets and entropy [ 69 ] or in-depth analysis of spectral densities [ 70 ]. Their potential applicability to diaphragmatic sEMG signals has been demonstrated in a simulation study [ 71 ], but needs clinical investigation. Importantly, whether fatigue assessment is relevant for patients in the ICU or chronic ventilation setting is at present unclear.…”

Section: Postprocessingmentioning

confidence: 99%

Analysis and applications of respiratory surface EMG: report of a round table meeting

Jonkman,

Warnaar,

Baccinelli

et al. 2024

Crit Care

View full text Add to dashboard Cite

Surface electromyography (sEMG) can be used to measure the electrical activity of the respiratory muscles. The possible applications of sEMG span from patients suffering from acute respiratory failure to patients receiving chronic home mechanical ventilation, to evaluate muscle function, titrate ventilatory support and guide treatment. However, sEMG is mainly used as a monitoring tool for research and its use in clinical practice is still limited—in part due to a lack of standardization and transparent reporting. During this round table meeting, recommendations on data acquisition, processing, interpretation, and potential clinical applications of respiratory sEMG were discussed. This paper informs the clinical researcher interested in respiratory muscle monitoring about the current state of the art on sEMG, knowledge gaps and potential future applications for patients with respiratory failure.

show abstract

Section: Postprocessingmentioning

confidence: 99%

Analysis and applications of respiratory surface EMG: report of a round table meeting

Jonkman,

Warnaar,

Baccinelli

et al. 2024

Crit Care

View full text Add to dashboard Cite

show abstract

“…However, the power spectrum of the ECG's principal component is in the ranges of 1 ~ 20 Hz, signal amplitude will decrease as frequency increases and quickly disappear in the frequency range above 12 Hz; thus, the frequency component from 1 to 12 Hz will be selected to recognize as many ECG rhythms as possible. These spectra are not affected by high frequency components above 20 Hz such as power line interference (50/60 Hz), some forms of muscle artifacts; and are also not affected by interference of very low frequency components (<0.5 Hz) such as baseline drift and respiratory [18,19]. Heart rate and P waves appear in the frequency range of 0.67~5 Hz, T waves in the frequency range 1~7 Hz, QRS components in the frequency range: 10-50 Hz.…”

Section: Spectral Range Of the Main Components In The Received Signalmentioning

confidence: 99%

Enhanced ECG Record Quality: Integrated Artifact Suppression Using Soft Threshold on Wavelet Coefficients and Adaptive Filter Model

Hai¹

2023

MMEP

View full text Add to dashboard Cite

The Independent Component Analysis (ICA) method has been demonstrated as an effective tool for separating desired signals and artifacts in the processing of biomedical signals, particularly in electrocardiogram (ECG) recordings through blind source separation (BSS). Unwanted components, which propagate through the body to the electrodes and mix with the recorded signal, are analyzed into independent components (ICs). However, the unwanted ICs identified as artifacts may also contain valuable information, resulting in a loss of information if these ICs are removed entirely. To address this issue, a combined solution of wavelet decomposition and ICA is proposed. Wavelet decompositions are performed on the unwanted ICs, and the application of a threshold level to the wavelet coefficients minimizes the loss of information in the received signal. A proposed solution utilizing the wavelet-based ICA (wICA) algorithm effectively removes artifacts, reducing distortion in the amplitude and phase of the ECG signal. Consequently, the resulting electrocardiogram closely corresponds to the patient's actual heart electrical signal variations, aiding in accurate clinical diagnoses. ECG signals are affected by various artifact components, including highly influential EMG or motion artifacts, which can manifest simultaneously, randomly, or intermittently. An inflexible threshold level is not entirely appropriate for these cases. In this study, a solution integrating the wICA system with an adaptive filter model is proposed to overcome the limitation of a fixed threshold level. This combined system can provide the best prediction of artifact impacts to establish adaptive threshold values. Experimental results have shown that this new approach significantly improves the ability to remove artifacts from ECG records, with a correlation value of 0.9832 compared to the reference clean signal.

show abstract

ECG Signal Analysis Using Convolution Neural Networks to avoid Uncertainty in Classification

Balaji¹,

Jaya²,

Prasad³

2023

J. Uncert. Sys.

View full text Add to dashboard Cite

This paper presents the study of electrocardiogram (ECG) signals analysis using convolution neural networks (CNNs) to avoid uncertainty in classification. MIT-BIH ECG dataset with five classes of beats, i.e., nonectopic, supraventricular, ventricular, fusion, unknown, is used for testing and training. The role of pre-processing of dataset was analyzed in improving the network efficiency. All the classes were balanced by doing under-sampling. The data was transformed by adding Gaussian noise to generalize training. CNN was designed with convolutional layer, max-pooling layer, concatenation layer and fully connected layer to classify the ECG signal. A dropout layer with the value of 0.4 was incorporated. Dropout layers are critical in CNN training because they minimize the training data from overfitting which leads to reduce the uncertainty in classification. Sigmoid activation function is used for eventual classification decision making. The presented network offers a high accuracy of 89.2%.

show abstract

Removal of ECG Artifacts Affects Respiratory Muscle Fatigue Detection—A Simulation Study

Cited by 3 publications

References 33 publications

Analysis and applications of respiratory surface EMG: report of a round table meeting

Analysis and applications of respiratory surface EMG: report of a round table meeting

Enhanced ECG Record Quality: Integrated Artifact Suppression Using Soft Threshold on Wavelet Coefficients and Adaptive Filter Model

ECG Signal Analysis Using Convolution Neural Networks to avoid Uncertainty in Classification

Contact Info

Product

Resources

About