Fetal Electrocardiogram Extraction from the Mother’s Abdominal Signal Using the Ensemble Kalman Filter

Abstract

Fetal electrocardiogram (fECG) assessment is essential throughout pregnancy to monitor the wellbeing and development of the fetus, and to possibly diagnose potential congenital heart defects. Due to the high noise incorporated in the abdominal ECG (aECG) signals, the extraction of fECG has been challenging. And it is even a lot more difficult for fECG extraction if only one channel of aECG is provided, i.e., in a compact patch device. In this paper, we propose a novel algorithm based on the Ensemble Kalman filter (EnKF) for non-invasive fECG extraction from a single-channel aECG signal. To assess the performance of the proposed algorithm, we used our own clinical data, obtained from a pilot study with 10 subjects each of 20 min recording, and data from the PhysioNet 2013 Challenge bank with labeled QRS complex annotations. The proposed methodology shows the average positive predictive value (PPV) of 97.59%, sensitivity (SE) of 96.91%, and F1-score of 97.25% from the PhysioNet 2013 Challenge bank. Our results also indicate that the proposed algorithm is reliable and effective, and it outperforms the recently proposed extended Kalman filter (EKF) based algorithm.

Fetal QRS extraction from single-channel abdominal ECG using adaptive improved permutation entropy

“…All clinical recordings were collected anonymously under Institutional Review Board (IRB) approval #2020-6342 at the UCI. More details on the data and the collection process can be found in [16,41].…”

“…A variety of algorithms for fECG extraction have been proposed and implemented, categorized into groups such as adaptive filtering, Blind Source Separation (BSS), template subtraction, and hybrid techniques [11][12][13]. Adaptive filtering approaches include extended Kalman filter (EKF), ensemble Kalman filter (EnKF), deep learning, and artificial neural network (ANN) [14][15][16][17]. These methods face challenges such as high computational complexity and, in some cases, the requirement of multichannel abdominal ECG (aECG) signals [11][12][13][14][15][16][17].…”

“…Adaptive filtering approaches include extended Kalman filter (EKF), ensemble Kalman filter (EnKF), deep learning, and artificial neural network (ANN) [14][15][16][17]. These methods face challenges such as high computational complexity and, in some cases, the requirement of multichannel abdominal ECG (aECG) signals [11][12][13][14][15][16][17]. BSS methods are classified into singular value decomposition (SVD), principal component analysis (PCA), independent component analysis (ICA), and wavelet decomposition (WD) [18][19][20][21][22].…”

Enhancing Fetal Electrocardiogram Signal Extraction Accuracy through a CycleGAN Utilizing Combined CNN–BiLSTM Architecture

“…It depends on the local linearization of the nonlinear model achieved by employing the Jacobian operator [17]. The EKF proves to be a robust method for the extraction of singlechannel FECG signals [18]. Indeed, the performance of the EKF algorithm is contingent on local linearity.…”

The Development and Implementation of Innovative Blind Source Separation Techniques for Real-Time Extraction and Analysis of Fetal and Maternal Electrocardiogram Signals

“…This technique effectively separates maternal ECG (mECG) and other noise sources, enabling the accurate extraction of fECG, validated on simulated and real-world data, demonstrating high performance when assessed via API evaluation. Sarafan, S. et al [14] described a new algorithm using the Ensemble Kalman Filter (EnKF) to efficiently extract a fetal electrocardiogram (fECG) from a single-channel abdominal ECG (aECG), demonstrating superior performance to existing methods, with the results obtained from PhysioNet clinical data. Shi, X. et al [15] introduced an unsupervised multilevel fetal ECG signal quality assessment method using features based on entropy, statistics, and ECG signal quality index, as well as an autoencoder-based feature.…”