Computerized analysis of antepartum fetal heart rate

Comparison of phase rectified signal averaging and short term variation in predicting perinatal outcome in early onset fetal growth restriction

OBJECTIVES

To compare short term variation (STV) and phase rectified signal averaging (PRSA) and their association with fetal outcome in early onset fetal growth restriction (FGR).

METHODS

Data were used from a retrospective cohort study of women who were admitted for FGR and/or pre-eclampsia and who were delivered by pre-labor Cesarean section or had a fetal death before 32 weeks' gestation. Computerized cardiotocography (cCTG) registrations of the 5 days before delivery or fetal death were used for calculation of STV and PRSA. PRSA was expressed as the average acceleration capacity (AAC) and average deceleration capacity (ADC). FHR decelerations were classified visually as absent, 1-2 per hour or recurrent. Abnormality of STV and of PRSA was either analyzed as a single parameter or in combination with recurrent decelerations. Endpoints were defined as composite adverse condition at birth consisting of fetal death, low Apgar score, low umbilical pH, the need for resuscitation after birth and as major neonatal morbidity or neonatal death.

RESULTS

Included were 367 pregnancies of which 20 resulted in fetal death. An abnormal cCTG with either recurrent decelerations and/or low STV or recurrent decelerations and/or low PRSA were similarly associated with composite adverse condition at birth (n=99), but neither with major neonatal morbidity.

CONCLUSIONS

PRSA and STV have similar efficacy for measuring fetal heart rate variation in early onset FGR. An increased risk of a composite adverse condition at birth is indicated by a low value of either parameter and/or the presence of recurrent decelerations.

The role of the fetal biophysical profile in the management of fetal growth restriction

Growth-restricted fetuses are at risk of hypoxemia, acidemia, and stillbirth because of progressive placental dysfunction. Current fetal well-being, neonatal risks following delivery, and the anticipated rate of fetal deterioration are the major management considerations in fetal growth restriction. Surveillance has to quantify the fetal risks accurately to determine the delivery threshold and identify the testing frequency most likely to capture future deterioration and prevent stillbirth. From the second trimester onward, the biophysical profile score correlates over 90% with the current fetal pH, and a normal score predicts a pH >7.25 with a 100% positive predictive value; an abnormal score on the other hand predicts current fetal acidemia with similar certainty. Between 30% and 70% of growth-restricted fetuses with a nonreactive heart rate require biophysical profile scoring to verify fetal well-being, and an abnormal score in 8% to 27% identifies the need for delivery, which is not suspected by Doppler findings. Future fetal well-being is not predicted by the biophysical profile score, which emphasizes the importance of umbilical artery Doppler and amniotic fluid volume to determine surveillance frequency. Studies with integrated surveillance strategies that combine frequent heart rate monitoring with biophysical profile scoring and Doppler report better outcomes and stillbirth rates of between 0% and 4%, compared with those between 8% and 11% with empirically determined surveillance frequency. The variations in clinical behavior and management challenges across gestational age are better addressed when biophysical profile scoring is integrated into the surveillance of fetal growth restriction. This review aims to provide guidance on biophysical profile scoring in the in- and outpatient management of fetal growth restriction.

Computerized fetal heart rate analysis in early preterm fetal growth restriction

OBJECTIVE

To assess the value of computerized cardiotocography (cCTG) with calculation of fetal heart rate (FHR) short-term variability (STV) in early preterm fetal growth restriction (FGR) for prevention of fetal death and neonatal asphyxia, neonatal morbidity, and 2-year neurodevelopmental impairment.

METHODS

This was a retrospective cohort study of all women who were admitted to the Amsterdam University Medical Center-AMC between 2003 and 2015 due to FGR and/or pre-eclampsia, and who were delivered by prelabor Cesarean section, or had a fetal death, before 32 weeks' gestation. STV of all available cCTG registrations during the 5 days preceding fetal death or delivery was calculated retrospectively, and FHR decelerations were classified visually as absent, 1-2/h or recurrent (> 2/h). Adverse outcome endpoints were defined as fetal death, neonatal asphyxia at birth (including fetal death), neonatal death, major neonatal morbidity and 2-year neurodevelopmental outcome. A simulation analysis was performed to assess the incidence of adverse outcome using two thresholds for cCTG: (1) highly abnormal (STV < 2.6 ms before 29 weeks and < 3.0 ms thereafter, and/or recurrent FHR decelerations); and (2) moderately abnormal (STV < 3.5 ms before 29 weeks and < 4.0 ms thereafter, and/or recurrent FHR decelerations). Three management strategies were assessed using a strict schedule for the frequency of cCTG recordings: (1) cCTG without use of fetal arterial Doppler; (2) cCTG with additional fetal arterial Doppler after 29 weeks; and (3) cCTG with additional fetal arterial Doppler after 27 weeks.

RESULTS

Included were 367 pregnancies (3295 cCTG recordings), of which 20 resulted in fetal death and 347 were delivered by Cesarean section before the onset of labor. Cesarean delivery was indicated by fetal condition in 94% of cases and by maternal condition in 6%. Median gestational age at delivery was 30 (interquartile range (IQR), 28-31) weeks and median birth weight was 900 (IQR, 740-1090) g. Six cases of fetal death were not anticipated by standard practice using visual assessment of CTG. A last highly abnormal cCTG was associated with fetal death and with neonatal asphyxia (including fetal death; n = 99), but not with major neonatal morbidity and 2-year neurodevelopmental outcome. Moderately abnormal cCTG had no significant association with any endpoint. Simulation analysis showed that a strategy that combined cCTG results with umbilicocerebral ratio or umbilical absent or reversed end-diastolic flow could detect all fetal deaths.

CONCLUSIONS

Computerized CTG in combination with fetal arterial Doppler, with a strict protocol for the frequency of recordings, is likely to be more effective than visual CTG assessment for preventing fetal death in early preterm FGR. Copyright © 2019 ISUOG. Published by John Wiley & Sons Ltd.

Reduced short-term variation following antenatal administration of betamethasone: Is reduced fetal size a predisposing factor?

OBJECTIVE

To assess the association between fetal size and the incidence of reduced short-term variability (STV) following bethametasone administration for fetal lung maturity.

STUDY DESIGN

This was a retrospective, multicenter, cohort study conducted in two Tertiary University Units. Only uncomplicated singleton pregnancies admitted for threatened preterm labor between 26 and 34 weeks and submitted to betamethasone for fetal lung maturity were included. Delivery occurring within 72h from betamethasone administration represented criteria for exclusion. Computerized cardiotocography was carried out on a daily basis. Cases were identified by persistently reduced STV, defined as <5th percentile for gestational age and lasting for at least 72h after the first dose of betamethasone. The primary outcome was estimated fetal weight (EFW) at ultrasound in fetuses with normal and in those with persistently reduced STV. Pregnancy outcomes were also evaluated.

RESULTS

Persistently reduced STV occurred in 33/405 of the included patients (8.1%). Compared to women with normal STV, those with persistently reduced STV had significantly lower EFW (1472±435 vs 1812±532g, p 0.04), lower birthweight (2353±635 vs 2857±796g, p<0.01) and earlier gestational age at delivery (35.1±4.2 vs 37.3±2.4weeks, p<0.01), whereas all the other variables including gestational age on admission were comparable.

CONCLUSIONS

Reduced STV following maternal betamethasone administration among appropriately grown fetuses seems to correlate with lower fetal size. Furthermore, fetuses with such abnormal response to steroids seem to carry a higher risk of perinatal complications, including lower birthweight and earlier gestational age at delivery.

FETAL HEART RATE VARIABILITY ANALYSIS FROM PHONOCARDIOGRAPHIC RECORDINGS

This paper presents an algorithm for classification of fetal health status using fetal heart rate variability (fHRV) analysis through phonocardiography. First, the fetal heart sound signals are acquired from the maternal abdominal surface using a specially developed Bluetooth-based wireless data recording system. Then, fetal heart rate (FHR) traces are derived from these signals. Ten numbers of linear and nonlinear features are extracted from each FHR trace. Finally, the multilayer perceptron (MLP) neural network is used to classify the health status of the fetus. Results show very promising performance toward the prediction of fetal wellbeing on the set of collected fetal heart sound signals. Finally, this work is likely to lead to an automatic screening device with additional potential of predicting fetal wellbeing.

FEATURE EXTRACTION AND CLASSIFICATION OF FETAL HEART RATE USING WAVELET ANALYSIS AND SUPPORT VECTOR MACHINES

Since the fetus is not available for direct observations, only indirect information can guide the obstetrician in charge. Electronic Fetal Monitoring (EFM) is widely used for assessing fetal well being. EFM involves detection of the Fetal Heart Rate (FHR) signal and the Uterine Activity (UA) signal. The most serious fetal incident is the hypoxic injury leading to cerebral palsy or even death, which is a condition that must be predicted and avoided. This research work proposes a new integrated method for feature extraction and classification of the FHR signal able to associate FHR with umbilical artery pH values at delivery. The proposed method introduces the use of the Discrete Wavelet Transform (DWT) to extract time-scale dependent features of the FHR signal and the use of Support Vector Machines (SVMs) for the categorization. The proposed methodology is tested on a data set of intrapartum recordings were the FHR categories are associated with umbilical artery pH values, This proposed approach achieved high overall classification performance proving its merits.

Antepartum fetal heart rate feature extraction and classification using empirical mode decomposition and support vector machine

Background

Cardiotocography (CTG) is the most widely used tool for fetal surveillance. The visual analysis of fetal heart rate (FHR) traces largely depends on the expertise and experience of the clinician involved. Several approaches have been proposed for the effective interpretation of FHR. In this paper, a new approach for FHR feature extraction based on empirical mode decomposition (EMD) is proposed, which was used along with support vector machine (SVM) for the classification of FHR recordings as 'normal' or 'at risk'.

Methods

The FHR were recorded from 15 subjects at a sampling rate of 4 Hz and a dataset consisting of 90 randomly selected records of 20 minutes duration was formed from these. All records were labelled as 'normal' or 'at risk' by two experienced obstetricians. A training set was formed by 60 records, the remaining 30 left as the testing set. The standard deviations of the EMD components are input as features to a support vector machine (SVM) to classify FHR samples.

Results

For the training set, a five-fold cross validation test resulted in an accuracy of 86% whereas the overall geometric mean of sensitivity and specificity was 94.8%. The Kappa value for the training set was .923. Application of the proposed method to the testing set (30 records) resulted in a geometric mean of 81.5%. The Kappa value for the testing set was .684.

Conclusions

Based on the overall performance of the system it can be stated that the proposed methodology is a promising new approach for the feature extraction and classification of FHR signals.

Treatments of pelvic girdle pain in pregnant women: adverse effects of standard treatment, acupuncture and stabilising exercises on the pregnancy, mother, delivery and the fetus/neonate

BACKGROUND

Previous publications indicate that acupuncture is efficient for the treatment of pelvic girdle pain, PGP, in pregnant women. However, the use of acupuncture for PGP is rare due to insufficient documentation of adverse effects of this treatment in this specific condition. The aim of the present work was to assess adverse effects of acupuncture on the pregnancy, mother, delivery and the fetus/neonate in comparison with women that received stabilising exercises as adjunct to standard treatment or standard treatment alone.

METHODS

In all, 386 women with PGP entered this controlled, single-blind trial. They were randomly assigned to standard treatment plus acupuncture (n = 125), standard treatment plus specific stabilising exercises (n = 131) or to standard treatment alone (n = 130) for 6 weeks. Acupuncture that may be considered strong was used and treatment was started as early as in the second trimester of pregnancy. Adverse effects were recorded during treatment and throughout the pregnancy. Influence on the fetus was measured with cardiotocography (CTG) before-during and after 43 acupuncture sessions in 43 women. A standardised computerized method to analyze the CTG reading numerically (Oxford 8000, Oxford, England) was used. After treatment, the women rated their overall experience of the treatment and listed adverse events if any in a questionnaire. Data of analgesia and oxytocin augmentation during labour, duration of labour, frequency of preterm birth, operative delivery, Apgar score, cord-blood gas/acid base balance and birth weight were also recorded.

RESULTS

There were no serious adverse events after any of the treatments. Minor adverse events were common in the acupuncture group but women rated acupuncture favourably even despite this. The computerized or visually assessed CTG analyses of antenatal recordings in connection with acupuncture were all normal.

CONCLUSION

This study shows that acupuncture administered with a stimulation that may be considered strong led to minor adverse complaints from the mothers but had no observable severe adverse influences on the pregnancy, mother, delivery or the fetus/neonate.

Predicting the risk of metabolic acidosis for newborns based on fetal heart rate signal classification using support vector machines

Cardiotocography is the main method used for fetal assessment in every day clinical practice for the last 30 years. Many attempts have been made to increase the effectiveness of the evaluation of cardiotocographic recordings and minimize the variations of their interpretation utilizing technological advances. This research work proposes and focuses on an advanced method able to identify fetuses compromised and suspicious of developing metabolic acidosis. The core of the proposed method is the introduction of a support vector machine to "foresee" undesirable and risky situations for the fetus, based on features extracted from the fetal heart rate signal at the time and frequency domains along with some morphological features. This method has been tested successfully on a data set of intrapartum recordings, achieving better and balanced overall performance compared to other classification methods, constituting, therefore, a promising new automatic methodology for the prediction of metabolic acidosis.

Foetal heart rate power spectrum response to uterine contraction

Cardiotocography is the most diffused prenatal diagnostic technique in clinical routine. The simultaneous recording of foetal heart rate (FHR) and uterine contractions (UC) provides useful information about foetal well-being during pregnancy and labour. However, foetal electronic monitoring interpretation still lacks reproducibility and objectivity. New methods of interpretation and new parameters can further support physicians' decisions. Besides common time-domain analysis, study of the variability of FHR can potentially reveal autonomic nervous system activity of the foetus. In particular, it is clinically relevant to investigate foetal reactions to UC to diagnose foetal distress early. Uterine contraction being a strong stimulus for the foetus and its autonomic nervous system, it is worth exploring the FHR variability response. This study aims to analyse modifications of the power spectrum of FHR variability corresponding to UC. Cardiotocographic signal tracts corresponding to 127 UC relative to 30 healthy foetuses were analysed. Results mainly show a general, statistically significant (t test, p<0.01) power increase of the FHR variability in the LF 0.03-0.2 Hz and HF 0.2-1 in correspondence of the contraction with respect to a reference tract set before contraction onset. Time evolution of the power within these bands was computed by means of time-varying spectral estimation to concisely show the FHR response along a uterine contraction. A synchronised grand average of these responses was also computed to verify repeatability, using the contraction apex as time reference. Such modifications of the foetal HRV that follow a contraction can be a sign of ANS reaction and, therefore, additional, objective information about foetal reactivity during labour.

Can antepartum computerized cardiotocography predict the evolution of intrapartum acid-base status in normal fetuses?

BACKGROUND

To study the relationship between antepartum computerized cardiotocography (cCTG) and the evolution of intrapartum fetal acid-base balance in a low-risk population.

METHODS

Forty-nine healthy fetuses were prospectively followed up by antepartum cCTG (Oxford System 8002), fetal scalp blood sampling at the onset of the active phase of dilatation (3 cm) and at the beginning of the second stage of labor (10 cm) and study of acid-base status at birth in the umbilical cord. Correlation studies and linear regression analysis were performed.

RESULTS

Normal prelabor cCTG was followed by normal fetal acid-base balance in the different study periods. No relationship was found between cCTG parameters and the absolute values of fetal acid-base status. However, the more favorable the antepartum cCTG parameters were, the more favorable the fetal acid-base evolution during the active phase of dilatation was. In contrast, no significant correlations were found between antepartum cCTG and fetal acid-base changes during the second stage of labor.

CONCLUSIONS

In normal fetuses, a single antepartum cCTG identified correctly fetal well-being during labor and at birth and was able to predict fetal acid-base evolution during the active phase of dilatation. However, fetal biochemical changes during the second stage could not be predicted by any antepartum cCTG parameter.

Linear and nonlinear parameters for the analysis of fetal heart rate signal from cardiotocographic recordings

Antepartum fetal monitoring based on the classical cardiotocography (CTG) is a noninvasive and simple tool for checking fetal status. Its introduction in the clinical routine limited the occurrence of fetal problems leading to a reduction of the precocious child mortality. Nevertheless, very poor indications on fetal pathologies can be inferred from the even automatic CTG analysis methods, which are actually employed. The feeling is that fetal heart rate (FHR) signals and uterine contractions carry much more information on fetal state than is usually extracted by classical analysis methods. In particular, FHR signal contains indications about the neural development of the fetus. However, the methods actually adopted for judging a CTG trace as "abnormal" give weak predictive indications about fetal dangers. We propose a new methodological approach for the CTG monitoring, based on a multiparametric FHR analysis, which includes spectral parameters from autoregressive models and nonlinear algorithms (approximate entropy). This preliminary study considers 14 normal fetuses, eight cases of gestational (maternal) diabetes, and 13 intrauterine growth retarded fetuses. A comparison with the traditional time domain analysis is also included. This paper shows that the proposed new parameters are able to separate normal from pathological fetuses. Results constitute the first step for realizing a new clinical classification system for the early diagnosis of most common fetal pathologies.

Computer analysis of the fetal heart rate

Computer analysis of the fetal heart rate is a technology of the Information Age commercially available for research and clinical practice. Intelligent systems are engineered with algorithms or neural networks designed to simulate expert knowledge. Automated analysis has provided objective, standardized, and reproducible data used to research fetal heart rate responses in the antepartum and intrapartum setting. Perinatal information systems can integrate FHR analysis and data management.