[Fetal electrocardiogram signal extraction and analysis method combining fast independent component analysis algorithm and convolutional neural network]

Fetal electrocardiogram (ECG) signals provide important clinical information for early diagnosis and intervention of fetal abnormalities. In this paper, we propose a new method for fetal ECG signal extraction and analysis. Firstly, an improved fast independent component analysis method and singular value decomposition algorithm are combined to extract high-quality fetal ECG signals and solve the waveform missing problem. Secondly, a novel convolutional neural network model is applied to identify the QRS complex waves of fetal ECG signals and effectively solve the waveform overlap problem. Finally, high quality extraction of fetal ECG signals and intelligent recognition of fetal QRS complex waves are achieved. The method proposed in this paper was validated with the data from the PhysioNet computing in cardiology challenge 2013 database of the Complex Physiological Signals Research Resource Network. The results show that the average sensitivity and positive prediction values of the extraction algorithm are 98.21% and 99.52%, respectively, and the average sensitivity and positive prediction values of the QRS complex waves recognition algorithm are 94.14% and 95.80%, respectively, which are better than those of other research results. In conclusion, the algorithm and model proposed in this paper have some practical significance and may provide a theoretical basis for clinical medical decision making in the future.

Frequency-Based Maternal Electrocardiogram Attenuation for Fetal Electrocardiogram Analysis

Fetal electrocardiogram (ECG) waveform analysis along with cardiac time intervals (CTIs) measurements are critical for the management of high-risk pregnancies. Currently, there is no system that can consistently and accurately measure fetal ECG. In this work, we present a new automatic approach to attenuate the maternal ECG in the frequency domain and enhance it with measurable CTIs. First, the coherent components between the maternal ECG and abdominal ECG were identified and subtracted from the latter in the frequency domain. The residual was then converted into the time domain using the inverse Fourier transform to yield the fetal ECG. This process was improved by averaging multiple beats. Two fetal cardiologists, blinded to the method, assessed the quality of fetal ECG based on a grading system and measured the CTIs. We evaluated the fetal ECG quality of our method and time-based methods using one synthetic dataset, one human dataset available in the public domain, and 37 clinical datasets. Among the 37 datasets analyzed, the mean average (± standard deviation) grade was 3.49 ± 1.22 for our method vs. 2.64 ± 1.26 for adaptive interference cancellation (p-value < 0.001), thus showing the frequency-based fetal ECG extraction was the superior method, as assessed from our clinicians' perspectives. This method has the potential for use in clinical settings.

Investigating myocardial performance in normal and sick fetuses by abdominal Doppler signal derived indices

INTRODUCTION

Fetal myocardial performance indices are applied to assess aspects of systolic and diastolic function in developing fetal heart. The aim of this study was to determine normal values of Tei Index (TI) and modified TI (KI) for systolic and diastolic performance in early (<30 weeks), Mid (30-35 weeks) and late (36-41 weeks) relating to both normal fetuses as well as fetuses carrying a variety of fetal abnormalities, which do not call for precise anatomic imaging.

MATERIAL AND METHODS

Fetal Electrocardiogram Signals (FES) and Doppler Ultrasound Signal (DUS) were simultaneously documented from 55 normal and 25 abnormal fetuses with a variety of abnormalities including Congenital Heart Diseases (CHDs) and a variety of non-CHDs. The isovolumic contraction time (ICT), isovolumic relaxation time (IRT), ventricular ejection time (VET) and ventricular filling time (VFT) were estimated from continuous DUS signals by a hybrid of Hidden Markov and Support Vector Machine based automated model. The TI and the KI were calculated by using the formula (ICT ​+ ​IRT)/VET and (ICT ​+ ​IRT)/VFT respectively.

RESULTS

The TI was not found to show any significant change from early to late fetuses, nor between normal and abnormal cases. On the other hand, KI was shown to significantly decline in values from early to late normal cases and from normal to abnormal groups. Significant correlation (r = -0.36; p < 0.01) of gestational ages with only KI (not TI) was found in this study.

CONCLUSION

Modified TI (KI) may be a useful index to monitor the normal development of fetal myocardial function and identify fetuses with a variety of CHD and non-CHD cases.

A systematic review on the utility of non-invasive electrophysiological assessment in evaluating for intra uterine growth restriction

Background

Non-invasive electrophysiological assessment (NIEA) is an evolving area in fetal surveillance and is attracting increasing research interest. There is however, limited data outlining its utility in evaluating intra uterine growth restriction (IUGR). The objective of this study was to carry out a systematic review to outline the utility of NIEA parameters in evaluating IUGR.

Methods

A systematic review of peer reviewed literature was performed, searching PUBMED, Ovid MEDLINE and EMBASE. The outcomes of interest included NIEA parameters [P wave duration, PR interval, QRS duration, QT interval, T/QRS ratio, short term variability (STV) and long term variability (LTV)] and a descriptive summary of relevant studies as well.

Results

Sixteen studies were identified as suitable for inclusion. The utility of NIEA parameters were investigated in tabular form. In particular, QRS and QT duration, T/QRS ratio, STV and PRSA analysis displayed utility and merit further consideration in evaluating for IUGR. Issues identified in the review were in relation to variances in definition of IUGR, small sample sizes and the lack of technological consistency across studies.

Conclusion

NIEA shows promise as an adjunct surveillance tool in fetal diagnostics for IUGR. Larger prospective studies should be directed towards establishing reliable parameters with a focus on uniformity of IUGR definition, technological consistency and the individualisation of NIEA parameters.

Electronic supplementary material

The online version of this article (10.1186/s12884-019-2357-9) contains supplementary material, which is available to authorized users.

The fetal electrocardiogram to detect the effects of betamethasone on fetal heart rate variability

BACKGROUND

Betamethasone is widely used to enhance fetal lung maturation in case of threatened preterm birth. Antenatal corticosteroids are known to reduce fetal heart rate variability (fHRV) in the days following administration. Since decreased fHRV is a marker for fetal distress, this transient decrease of fHRV can cause unnecessary medical intervention.

AIM

To describe the effect of betamethasone on fHRV, by applying spectral analysis on non-invasive fetal electrocardiogram (fECG) recordings.

STUDY DESIGN

Secondary analysis of a prospective cohort study.

SUBJECTS

Women with a singleton pregnancy, at risk for preterm delivery and receiving betamethasone, admitted to the obstetric high care unit in the period from March 2013 until July 2016.

OUTCOME MEASURES

The primary outcome measure was fHRV in both time- and frequency-domain. Secondary outcome measures included basal fetal heart rate (fHR) and fHR variance. FHRV parameters were then calculated separately for the quiet and active state.

RESULTS

Following 68 inclusions, 22 patients remained with complete series of measurements and sufficient data quality. FHRV parameters and fHR showed a decrease on day 2 compared to day 1, significant for short-term variability and high-frequency power. Similar results were found when analyzing for separate behavioral states. The number of segments in quiet state increased during days 1 and 2. Normalized values showed no difference for all behavioral states.

CONCLUSION

FHRV decreases on day 2 after betamethasone administration, while periods of fetal quiescence increase. No changes were found in the normalized values, indicating that the influence of autonomic modulation is minor. Clinical trial registration number NL43294.015.13.

A systematic review of cardiac time intervals utilising non-invasive fetal electrocardiogram in normal fetuses

BACKGROUND

Non-invasive fetal electrocardiogram (NIFECG) is an evolving technology in fetal surveillance which is attracting increasing research interest. There is however, only limited data outlining the reference ranges for normal cardiac time intervals (CTIs). The objective of our group was to carry out a systematic review to outline normal fetal CTIs using NIFECG.

METHODS

A systematic review of peer reviewed literature was performed, searching PUBMED,Ovid MEDLINE and EMBASE. The outcomes of interest included fetal CTIs (P wave duration, PR interval, QRS duration and QT interval) and a descriptive summary of relevant studies as well. The outcomes were grouped as early pre-term (≤ 32 weeks), moderate to late pre-term (32-37 weeks) and term (37-41 weeks).

RESULTS

8 studies were identified as suitable for inclusion. Reference ranges of CTIs were generated. Both PR interval and QRS duration demonstrated a linear correlation with advancing gestation. Several studies also demonstrated a reduction in signal acquisition between 27 and 32 weeks due to the attenuation by vernix caseosa. In this group, both the P wave and T waves were difficult to detect due to signal strength and interference.

CONCLUSION

NIFECG demonstrates utility to quantify CTIs in the fetus, particularly at advanced gestations. Larger prospective studies should be directed towards establishing reliable CTIs across various gestations.

Non-invasive fetal monitoring using electrocardiography and phonocardiography: A preliminary study

BACKGROUND

Continuous fetal monitoring is commonly used during pregnancy and labor to assess fetal wellbeing. The most often used technology is cardiotocography (CTG), but this technique has major drawbacks in clinical use.

OBJECTIVES

Our aim is to test a non-invasive multimodal technique of fetal monitoring using phonocardiography (PCG) and electrocardiography (ECG) and to evaluate its feasibility in clinical practice, by comparison with CTG.

METHODS

This prospective open label study took place in a French university hospital. PCG and ECG signals were recorded using abdominal and thoracic sensors from antepartum women during the second half of pregnancy, simultaneously with CTG recording. Signals were then processed to extract fetal PCG and ECG and estimate fetal heart rate (FHR).

RESULTS

A total of 9 sets of recordings were evaluated. Very accurate fetal ECG and fetal PCG signals were recorded, enabling us to obtain FHR for several subjects. The FHR calculated from ECG was highly correlated with the FHR from the CTG reference (from 74% to 84% of correlation).

CONCLUSION

This work with preliminary signal processing algorithms proves the feasibility of the approach and constitutes the beginnings of a unique database that is needed to improve and validate the signal processing algorithms.

Electrocardiographic confirmation of a twin pregnancy in a mare at 8 months of gestation

A 15-year-old Warmblood mare, at 8 months of gestation, was presented to the Ghent University Faculty of Veterinary Medicine for evaluation of suspected stage one labor. Transrectal ultrasonography revealed no clear signs of placentitis or stage one labor. The combined thickness of uterus and placenta was 11 mm and the cervix was closed. Twin pregnancy was suspected by transabdominal ultrasonography but could not be confirmed with certainty. An electrocardiogram (ECG) was recorded from the mare's abdominal wall to register a fetal ECG. To confirm twin pregnancy, registration of both fetal ECGs simultaneously on the same ECG trace was attempted. Twelve different electrode configurations were used. In 11 recordings, one fetal ECG was visible. Only one specific right-sided electrode configuration showed both fetal ECGs at the same time, which confirmed twin pregnancy. Although electrocardiographic diagnosis of a twin pregnancy in a mare is possible, this case highlights the need for multiple electrode configurations and the high likelihood of false negatives.

The influence of betamethasone on fetal heart rate variability, obtained by non-invasive fetal electrocardiogram recordings

BACKGROUND

Betamethasone is widely used to enhance fetal lung maturation in case of threatened preterm labour. Fetal heart rate variability is one of the most important parameters to assess in fetal monitoring, since it is a reliable indicator for fetal distress.

AIM

To describe the effect of betamethasone on fetal heart rate variability, by applying spectral analysis on non-invasive fetal electrocardiogram recordings.

STUDY DESIGN

Prospective cohort study.

SUBJECTS

Patients that require betamethasone, with a gestational age from 24 weeks onwards.

OUTCOME MEASURES

Fetal heart rate variability parameters on day 1, 2, and 3 after betamethasone administration are compared to a reference measurement.

RESULTS

Following 68 inclusions, 12 patients remained with complete series of measurements and sufficient data quality. During day 1, an increase in absolute fetal heart rate variability values was seen. During day 2, a decrease in these values was seen. All trends indicate to return to pre-medication values on day 3. Normalised high- and low-frequency power show little changes during the study period.

CONCLUSIONS

The changes in fetal heart rate variability following betamethasone administration show the same pattern when calculated by spectral analysis of the fetal electrocardiogram, as when calculated by cardiotocography. Since normalised spectral values show little changes, the influence of autonomic modulation seems minor.

Circadian changes and sex-related differences in fetal heart rate parameters

BACKGROUND

Previous researchers have studied circadian changes in the fetal heart rate (FHR) on small sample sizes and in a strictly controlled environment. This study was undertaken to investigate these changes during the late second and third trimesters, using a portable fetal electrocardiogram recording device (Monica AN24) in pregnant women in home and hospital environments with unrestricted mobility.

METHODS

This was a prospective cohort study of 54 pregnant women with uncomplicated singleton pregnancies between 25 and 40 weeks gestation. FHR recordings were made up to 16 h at home or in the hospital setting in the United Kingdom. FHR data over 90 min periods were averaged and the day (7:00 am-11:00 pm) and night (11:00 pm-7:00 am) data from the same individual were compared. Data were examined for evidence of sex-related differences.

RESULTS

During the night, there was a significant reduction in basal heart rate (bFHR) and a significant increase in short term variation (STV) and long term variation (LTV) (P < 0.05). Basal FHR decreased (P < 0.002), whereas LTV increased (P = 0.014) with advancing gestation. Male fetuses showed greater day: night variation than females regardless of gestation (P = 0.014). There was a higher bFHR in fetuses monitored during the day in hospital (P = 0.04).

CONCLUSION

This study demonstrates that there are sex-, environment and time-related differences in the FHR parameters measured. These differences may need to be considered taken when interpreting FHR data.

A systematic review of prenatal screening for congenital heart disease by fetal electrocardiography

BACKGROUND

Congenital heart disease (CHD) is the most common severe congenital anomaly worldwide. Diagnosis early in pregnancy is important, but the detection rate by two-dimensional ultrasonography is only 65%-81%.

OBJECTIVES

To evaluate existing data on CHD and noninvasive abdominal fetal electrocardiography (ECG).

SEARCH STRATEGY

A systematic review was performed through a search of the Cochrane Library, PubMed, and Embase for studies published up to April 2016 using the terms "congenital heart disease," "fetal electrocardiogram," and other similar keywords.

SELECTION CRITERIA

Primary articles that described changes in fetal ECG among fetuses with CHD published in English were included.

DATA COLLECTION AND ANALYSIS

Outcomes of interest were changes in fetal ECG parameters observed for fetuses with congenital heart disease. Findings were reported descriptively.

MAIN RESULTS

Only five studies described changes observed in the fetal electrocardiogram for fetuses with CHD, including heart rate, heart rate variability, and PR, QRS, and QT intervals. Fetal ECG reflects the intimate relationship between the cardiac nerve conduction system and the structural morphology of the heart. It seems particularly helpful in detecting the electrophysiological effects of cardiac anatomic defects (e.g. hypotrophy, hypertrophy, and conduction interruption).

CONCLUSIONS

Fetal ECG might be a promising clinical tool to complement ultrasonography in the screening program for CHD.

An adaptive integrated algorithm for noninvasive fetal ECG separation and noise reduction based on ICA-EEMD-WS

High-resolution fetal electrocardiogram (FECG) plays an important role in assisting physicians to detect fetal changes in the womb and to make clinical decisions. However, in real situations, clear FECG is difficult to extract because it is usually overwhelmed by the dominant maternal ECG and other contaminated noise such as baseline wander, high-frequency noise. In this paper, we proposed a novel integrated adaptive algorithm based on independent component analysis (ICA), ensemble empirical mode decomposition (EEMD), and wavelet shrinkage (WS) denoising, denoted as ICA-EEMD-WS, for FECG separation and noise reduction. First, ICA algorithm was used to separate the mixed abdominal ECG signal and to obtain the noisy FECG. Second, the noise in FECG was reduced by a three-step integrated algorithm comprised of EEMD, useful subcomponents statistical inference and WS processing, and partial reconstruction for baseline wander reduction. Finally, we evaluate the proposed algorithm using simulated data sets. The results indicated that the proposed ICA-EEMD-WS outperformed the conventional algorithms in signal denoising.

Research of fetal ECG extraction using wavelet analysis and adaptive filtering

Extracting clean fetal electrocardiogram (ECG) signals is very important in fetal monitoring. In this paper, we proposed a new method for fetal ECG extraction based on wavelet analysis, the least mean square (LMS) adaptive filtering algorithm, and the spatially selective noise filtration (SSNF) algorithm. First, abdominal signals and thoracic signals were processed by stationary wavelet transform (SWT), and the wavelet coefficients at each scale were obtained. For each scale, the detail coefficients were processed by the LMS algorithm. The coefficient of the abdominal signal was taken as the original input of the LMS adaptive filtering system, and the coefficient of the thoracic signal as the reference input. Then, correlations of the processed wavelet coefficients were computed. The threshold was set and noise components were removed with the SSNF algorithm. Finally, the processed wavelet coefficients were reconstructed by inverse SWT to obtain fetal ECG. Twenty cases of simulated data and 12 cases of clinical data were used. Experimental results showed that the proposed method outperforms the LMS algorithm: (1) it shows improvement in case of superposition R-peaks of fetal ECG and maternal ECG; (2) noise disturbance is eliminated by incorporating the SSNF algorithm and the extracted waveform is more stable; and (3) the performance is proven quantitatively by SNR calculation. The results indicated that the proposed algorithm can be used for extracting fetal ECG from abdominal signals.