Computer-based intrapartum fetal monitoring and beyond: A review of the 2nd Workshop on Signal Processing and Monitoring in Labor (October 2017, Oxford, UK)

Artificial intelligence based cardiotocogram assessment during labor

OBJECTIVE

To assess whether artificial intelligence, inspired by clinical decision-making procedures in delivery rooms, can correctly interpret cardiotocographic tracings and distinguish between normal and pathological events.

STUDY DESIGN

A method based on artificial intelligence was developed to determine whether a cardiotocogram shows a normal response of the fetal heart rate to uterine activity (UA). For a given fetus and given the UA and previous FHR, the method predicts a fetal heart rate response, under the assumption that the fetus is still in good condition and based on how that specific fetus has responded so far. We hypothesize that this method, when having only learned from fetuses born in good condition, is incapable of predicting the response of a compromised fetus or an episode of transient fetal distress. The (in)capability of the method to predict the fetal heart rate response would then yield a method that can help to assess fetal condition when the obstetrician is in doubt. Cardiotocographic data of 678 deliveries during labor were selected based on a healthy outcome just after birth. The method was trained on the cardiotocographic data of 548 fetuses of this group to learn their heart rate response. Subsequently it was evaluated on 87 fetuses, by assessing whether the method was able to predict their heart rate responses. The remaining 43 cardiotocograms were segment-by-segment annotated by three experienced gynecologists, indicating normal, suspicious, and pathological segments, while having access to the full recording and neonatal outcome. This future knowledge makes the expert annotations of a quality that is unachievable during live interpretation.

RESULTS

The comparison between abnormalities detected by the method (only using past and present input) and the annotated CTG segments by gynecologists (also looking at future input) yields an area under the curve of 0.96 for the distinction between normal and pathological events in majority-voted annotations.

CONCLUSION

The developed method can distinguish between normal and pathological events in near real-time, with a performance close to the agreement between three gynecologists with access to the entire CTG tracing and fetal outcome. The method has a strong potential to support clinicians in assessing fetal condition in clinical practice.

AI-driven decision support systems and epistemic reliance: a qualitative study on obstetricians' and midwives' perspectives on integrating AI-driven CTG into clinical decision making

BACKGROUND

Given that AI-driven decision support systems (AI-DSS) are intended to assist in medical decision making, it is essential that clinicians are willing to incorporate AI-DSS into their practice. This study takes as a case study the use of AI-driven cardiotography (CTG), a type of AI-DSS, in the context of intrapartum care. Focusing on the perspectives of obstetricians and midwives regarding the ethical and trust-related issues of incorporating AI-driven tools in their practice, this paper explores the conditions that AI-driven CTG must fulfill for clinicians to feel justified in incorporating this assistive technology into their decision-making processes regarding interventions in labor.

METHODS

This study is based on semi-structured interviews conducted online with eight obstetricians and five midwives based in England. Participants were asked about their current decision-making processes about when to intervene in labor, how AI-driven CTG might enhance or disrupt this process, and what it would take for them to trust this kind of technology. Interviews were transcribed verbatim and analyzed with thematic analysis. NVivo software was used to organize thematic codes that recurred in interviews to identify the issues that mattered most to participants. Topics and themes that were repeated across interviews were identified to form the basis of the analysis and conclusions of this paper.

RESULTS

There were four major themes that emerged from our interviews with obstetricians and midwives regarding the conditions that AI-driven CTG must fulfill: (1) the importance of accurate and efficient risk assessments; (2) the capacity for personalization and individualized medicine; (3) the lack of significance regarding the type of institution that develops technology; and (4) the need for transparency in the development process.

CONCLUSIONS

Accuracy, efficiency, personalization abilities, transparency, and clear evidence that it can improve outcomes are conditions that clinicians deem necessary for AI-DSS to meet in order to be considered reliable and therefore worthy of being incorporated into the decision-making process. Importantly, healthcare professionals considered themselves as the epistemic authorities in the clinical context and the bearers of responsibility for delivering appropriate care. Therefore, what mattered to them was being able to evaluate the reliability of AI-DSS on their own terms, and have confidence in implementing them in their practice.

Intelligent antepartum fetal monitoring via deep learning and fusion of cardiotocographic signals and clinical data

Purpose

Cardiotocography (CTG), which measures uterine contraction (UC) and fetal heart rate (FHR), is a crucial tool for assessing fetal health during pregnancy. However, traditional computerized cardiotocography (cCTG) approaches have non-negligible calibration errors in feature extraction and heavily rely on the expertise and prior experience to define diagnostic features from CTG or FHR signals. Although previous works have studied deep learning methods for extracting CTG or FHR features, these methods still neglect the clinical information of pregnant women.

Methods

In this paper, we proposed a multimodal deep learning architecture (MMDLA) for intelligent antepartum fetal monitoring that is capable of performing automatic CTG feature extraction, fusion with clinical data and classification. The multimodal feature fusion was achieved by concatenating high-level CTG features, which were extracted from preprocessed CTG signals via a convolution neural network (CNN) with six convolution layers and five fully connected layers, and the clinical data of pregnant women. Eventually, light gradient boosting machine (LGBM) was implemented as fetal status assessment classifier. The effectiveness of MMDLA was evaluated using a dataset of 16,355 cases, each of which includes FHR signal, UC signal and pertinent clinical data like maternal age and gestational age.

Results

With an accuracy of 90.77% and an area under the curve (AUC) value of 0.9201, the multimodal features performed admirably. The data imbalance issue was also effectively resolved by the LGBM classifier, with a normal-F1 value of 0.9376 and an abnormal-F1 value of 0.8223.

Conclusion

In summary, the proposed MMDLA is conducive to the realization of intelligent antepartum fetal monitoring.

Optimizing fetal health prediction: Ensemble modeling with fusion of feature selection and extraction techniques for cardiotocography data

Cardiotocography (CTG) captured the fetal heart rate and the timing of uterine contractions. Throughout pregnancy, CTG intelligent categorization is crucial for monitoring fetal health and preserving proper fetal growth and development. Since CTG provides information on the fetal heartbeat and uterus contractions, which helps determine if the fetus is pathologic or not, obstetricians frequently use it to evaluate a child's physical health during pregnancy. In the past, obstetricians have artificially analyzed CTG data, which is time-consuming and inaccurate. So, developing a fetal health categorization model is crucial as it may help to speed up the diagnosis and treatment and conserve medical resources. The CTG dataset is used in this study. To diagnose the illness, 7 machine learning models are employed, as well as ensemble strategies including voting and stacking classifiers. In order to choose and extract the most significant and critical attributes from the dataset, Feature Selection (FS) techniques like ANOVA and Chi-square, as well as Feature Extraction (FE) strategies like Principal Component Analysis (PCA) and Independent Component Analysis (ICA), are being used. We used the Synthetic Minority Oversampling Technique (SMOTE) approach to balance the dataset because it is unbalanced. In order to forecast the illness, the top 5 models are selected, and these 5 models are used in ensemble methods such as voting and stacking classifiers. The utilization of Stacking Classifiers (SC), which involve Adaboost and Random Forest (RF) as meta-classifiers for disease detection. The performance of the proposed SC with meta-classifier as RF model, which incorporates Chi-square with PCA, outperformed all other state-of-the-art models, achieving scores of 98.79%,98.88%,98.69%,96.32%, and 98.77% for accuracy, precision, recall, specificity, and f1-score respectively.

Computerised Cardiotocography Analysis for the Automated Detection of Fetal Compromise during Labour: A Review

The measurement and analysis of fetal heart rate (FHR) and uterine contraction (UC) patterns, known as cardiotocography (CTG), is a key technology for detecting fetal compromise during labour. This technology is commonly used by clinicians to make decisions on the mode of delivery to minimise adverse outcomes. A range of computerised CTG analysis techniques have been proposed to overcome the limitations of manual clinician interpretation. While these automated techniques can potentially improve patient outcomes, their adoption into clinical practice remains limited. This review provides an overview of current FHR and UC monitoring technologies, public and private CTG datasets, pre-processing steps, and classification algorithms used in automated approaches for fetal compromise detection. It aims to highlight challenges inhibiting the translation of automated CTG analysis methods from research to clinical application and provide recommendations to overcome them.

Comparison of fetal heart rate baseline estimation by the cardiotocograph network and clinicians: a multidatabase retrospective assessment study

Background

This study aims to compare the fetal heart rate (FHR) baseline predicted by the cardiotocograph network (CTGNet) with that estimated by clinicians.

Material and methods

A total of 1,267 FHR recordings acquired with different electrical fetal monitors (EFM) were collected from five datasets: 84 FHR recordings acquired with F15 EFM (Edan, Shenzhen, China) from the Guangzhou Women and Children's Medical Center, 331 FHR recordings acquired with SRF618B5 EFM (Sanrui, Guangzhou, China), 234 FHR recordings acquired with F3 EFM (Lian-Med, Guangzhou, China) from the NanFang Hospital of Southen Medical University, 552 cardiotocographys (CTG) recorded using STAN S21 and S31 (Neoventa Medical, Mölndal, Sweden) and Avalon FM40 and FM50 (Philips Healthcare, Amsterdam, The Netherlands) from the University Hospital in Brno, Czech Republic, and 66 FHR recordings acquired using Avalon FM50 fetal monitor (Philips Healthcare, Amsterdam, The Netherlands) at St Vincent de Paul Hospital (Lille, France). Each FHR baseline was estimated by clinicians and CTGNet, respectively. And agreement between CTGNet and clinicians was evaluated using the kappa statistics, intra-class correlation coefficient, and the limits of agreement.

Results

The number of differences <3 beats per minute (bpm), 3-5 bpm, 5-10 bpm and ≥10 bpm, is 64.88%, 15.94%, 14.44% and 4.74%, respectively. Kappa statistics and intra-class correlation coefficient are 0.873 and 0.969, respectively. Limits of agreement are -6.81 and 7.48 (mean difference: 0.36 and standard deviation: 3.64).

Conclusion

An excellent agreement was found between CTGNet and clinicians in the baseline estimation from FHR recordings with different signal loss rates.

DeepCTG® 1.0: an interpretable model to detect fetal hypoxia from cardiotocography data during labor and delivery

Introduction

Cardiotocography, which consists in monitoring the fetal heart rate as well as uterine activity, is widely used in clinical practice to assess fetal wellbeing during labor and delivery in order to detect fetal hypoxia and intervene before permanent damage to the fetus. We present DeepCTG® 1.0, a model able to predict fetal acidosis from the cardiotocography signals.

Materials and methods

DeepCTG® 1.0 is based on a logistic regression model fed with four features extracted from the last available 30 min segment of cardiotocography signals: the minimum and maximum values of the fetal heart rate baseline, and the area covered by accelerations and decelerations. Those four features have been selected among a larger set of 25 features. The model has been trained and evaluated on three datasets: the open CTU-UHB dataset, the SPaM dataset and a dataset built in hospital Beaujon (Clichy, France). Its performance has been compared with other published models and with nine obstetricians who have annotated the CTU-UHB cases. We have also evaluated the impact of two key factors on the performance of the model: the inclusion of cesareans in the datasets and the length of the cardiotocography segment used to compute the features fed to the model.

Results

The AUC of the model is 0.74 on the CTU-UHB and Beaujon datasets, and between 0.77 and 0.87 on the SPaM dataset. It achieves a much lower false positive rate (12% vs. 25%) than the most frequent annotation among the nine obstetricians for the same sensitivity (45%). The performance of the model is slightly lower on the cesarean cases only (AUC = 0.74 vs. 0.76) and feeding the model with shorter CTG segments leads to a significant decrease in its performance (AUC = 0.68 with 10 min segments).

Discussion

Although being relatively simple, DeepCTG® 1.0 reaches a good performance: it compares very favorably to clinical practice and performs slightly better than other published models based on similar approaches. It has the important characteristic of being interpretable, as the four features it is based on are known and understood by practitioners. The model could be improved further by integrating maternofetal clinical factors, using more advanced machine learning or deep learning approaches and having a more robust evaluation of the model based on a larger dataset with more pathological cases and covering more maternity centers.

Continuous fetal cerebral blood flow monitoring during labor: A feasibility study

BACKGROUND

Current methods for fetal surveillance during labor have significant limitations. Since continuous fetal cerebral blood flow velocity (CBFV) monitoring during labor may add valuable information about fetal well-being, we developed a new ultrasound system called VisiBeam. VisiBeam consists of a flat probe (diameter 11 mm) with a cylindric plane wave beam, a vacuum attachment (diameter 40 mm), a scanner, and a display.

AIMS

To assess the feasibility of VisiBeam for continuous fetal CBFV monitoring during labor, and to study changes in CBFV during uterine contractions.

STUDY DESIGN

Descriptive observational study.

SUBJECTS

Twenty-five healthy women in labor with a singleton fetus in cephalic presentation at term. A transducer was placed over a fontanelle and attached to the fetal head with vacuum suction.

OUTCOME MEASURES

Achievement of continuous good quality fetal CBFV measures, such as peak systolic velocity, time averaged maximum velocity and end diastolic velocity. Trend plots of velocity measures display changes in CBFV between and during uterine contractions.

RESULTS

Good quality recordings during and between contractions were achieved in 16/25 fetuses. In twelve fetuses, CBFV measures were stable during uterine contractions. Four fetuses showed patterns of reduced CBFV velocity measures during contractions.

CONCLUSIONS

Continuous fetal CBFV monitoring by VisiBeam was feasible in 64 % of the subjects during labor. The system displayed variations of fetal CBFV not available by today's monitoring techniques and motivates for further studies. However, improvement of the probe attachment is required to ensure good quality signal in a higher proportion of fetuses during labor.

Fetal heart rate responses in chronic hypoxaemia with superimposed repeated hypoxaemia consistent with early labour: a controlled study in fetal sheep

OBJECTIVE

Deceleration area (DA) and capacity (DC) of the fetal heart rate can help predict risk of intrapartum fetal compromise. However, their predictive value in higher risk pregnancies is unclear. We investigated whether they can predict the onset of hypotension during brief hypoxaemia repeated at a rate consistent with early labour in fetal sheep with pre-existing hypoxaemia.

DESIGN

Prospective, controlled study.

SETTING

Laboratory.

SAMPLE

Chronically instrumented, unanaesthetised near-term fetal sheep.

METHODS

One-minute complete umbilical cord occlusions (UCOs) were performed every 5 minutes in fetal sheep with baseline p_a O₂ <17 mmHg (hypoxaemic, n = 8) and >17 mmHg (normoxic, n = 11) for 4 hours or until arterial pressure fell <20 mmHg.

MAIN OUTCOME MEASURES

DA, DC and arterial pressure.

RESULTS

Normoxic fetuses showed effective cardiovascular adaptation without hypotension and mild acidaemia (lowest arterial pressure 40.7 ± 2.8 mmHg, pH 7.35 ± 0.03). Hypoxaemic fetuses developed hypotension (lowest arterial pressure 20.8 ± 1.9 mmHg, P < 0.001) and acidaemia (final pH 7.07 ± 0.05). In hypoxaemic fetuses, decelerations showed faster falls in FHR over the first 40 seconds of UCOs but the final deceleration depth was not different to normoxic fetuses. DC was modestly higher in hypoxaemic fetuses during the penultimate (P = 0.04) and final (P = 0.012) 20 minutes of UCOs. DA was not different between groups.

CONCLUSION

Chronically hypoxaemic fetuses had early onset of cardiovascular compromise during labour-like brief repeated UCOs. DA was unable to identify developing hypotension in this setting, while DC only showed modest differences between groups. These findings highlight that DA and DC thresholds need to be adjusted for antenatal risk factors, potentially limiting their clinical utility.

Computerized analysis of cardiotocograms in clinical practice and the SisPorto® system thirty-two years after: technological, physiopathological and clinical studies

OBJECTIVES

The objective of this study is to present the why, what and how about computerized analysis of cardiotocograms (cCTG) and the SisPorto system for cCTG.

CONTENT

A narrative review about cCTG and the SisPorto system for cCTG is presented. The meta-analysis of randomized controlled trials (RCT) performed so far have evidenced that cCGT compared to traditional CTG analysis may save time spent in hospital for women, in the antepartum period, and is objective with at least equivalent results in maternal and perinatal outcomes, both in the ante and intrapartum periods. The SisPorto system for cCTG closely follows the FIGO guidelines for fetal monitoring. It may be used both in the ante and intrapartum periods, alone or connected to a central monitoring station, with simultaneous monitoring of fetal and maternal signals, not only in singletons but also in twins. It has been assessed in technical, physiopathological and clinical studies, namely in one large multicentric international RCT during labor and two meta-analysis.

SUMMARY AND OUTLOOK

There is evidence that cCTG may be useful in clinical practice with advantages compared to traditional CTG analysis, although without clear impact on the decrease of preventable maternal and perinatal mortality and morbidity. More studies are warranted, namely on technical improvements and assessment in larger studies in a wider range of clinical settings.

Cardiotocography analysis by empirical dynamic modeling and Gaussian processes

Introduction: During labor, fetal heart rate (FHR) and uterine activity (UA) can be continuously monitored using Cardiotocography (CTG). This is the most widely adopted approach for electronic fetal monitoring in hospitals. Both FHR and UA recordings are evaluated by obstetricians for assessing fetal well-being. Due to the complex and noisy nature of these recordings, the evaluation by obstetricians suffers from high interobserver and intraobserver variability. Machine learning is a field that has seen unprecedented advances in the past two decades and many efforts have been made in computerized analysis of CTG using machine learning methods. However, in the literature, the focus is often only on FHR signals unlike in evaluations performed by obstetricians where the UA signals are also taken into account. Methods: Machine learning is a field that has seen unprecedented advances in the past two decades and many efforts have been made in computerized analysis of CTG using machine learning methods. However, in the literature, the focus is often only on FHR signals unlike in evaluations performed by obstetricians where the UA signals are also taken into account. In this paper, we propose to model intrapartum CTG recordings from a dynamical system perspective using empirical dynamic modeling with Gaussian processes, which is a Bayesian nonparametric approach for estimation of functions. Results and Discussion: In the context of our paper, Gaussian processes are capable for simultaneous estimation of the dimensionality of attractor manifolds and reconstructing of attractor manifolds from time series data. This capacity of Gaussian processes allows for revealing causal relationships between the studied time series. Experimental results on real CTG recordings show that FHR and UA signals are causally related. More importantly, this causal relationship and estimated attractor manifolds can be exploited for several important applications in computerized analysis of CTG recordings including estimating missing FHR samples, recovering burst errors in FHR tracings and characterizing the interactions between FHR and UA signals.

Computerized cardiotocography analysis during labor - A state-of-the-art review

Cardiotocography is defined as the recording of fetal heart rate and uterine contractions and is widely used during labor as a screening tool to determine fetal wellbeing. The visual interpretation of the cardiotocography signals by the practitioners, following common guidelines, is subject to a high interobserver variability, and the efficiency of cardiotocography monitoring is still debated. Since the 1990s, researchers and practitioners work on designing reliable computer-aided systems to assist practitioners in cardiotocography interpretation during labor. Several systems are integrated in the monitoring devices, mostly based on the guidelines, but they have not clearly demonstrated yet their usefulness. In the last decade, the availability of large clinical databases as well as the emergence of machine learning and deep learning methods in healthcare has led to a surge of studies applying those methods to cardiotocography signals analysis. The state-of-the-art systems perform well to detect fetal hypoxia when evaluated on retrospective cohorts, but several challenges remain to be tackled before they can be used in clinical practice. First, the development and sharing of large, open and anonymized multicentric databases of perinatal and cardiotocography data during labor is required to build more accurate systems. Also, the systems must produce interpretable indicators along with the prediction of the risk of fetal hypoxia in order to be appropriated and trusted by practitioners. Finally, common standards should be built and agreed on to evaluate and compare those systems on retrospective cohorts and to validate their use in clinical practice.

A deep feature fusion network for fetal state assessment

CTG (cardiotocography) has consistently been used to diagnose fetal hypoxia. It is susceptible to identifying the average fetal acid-base balance but lacks specificity in recognizing prenatal acidosis and neurological impairment. CTG plays a vital role in intrapartum fetal state assessment, which can prevent severe organ damage if fetal hypoxia is detected earlier. In this paper, we propose a novel deep feature fusion network (DFFN) for fetal state assessment. First, we extract spatial and temporal information from the fetal heart rate (FHR) signal using a multiscale CNN-BiLSTM network, increasing the features' diversity. Second, the multiscale CNN-BiLSM network and frequently used features are integrated into the deep learning model. The proposed DFFN model combines different features to improve classification accuracy. The multiscale convolutional kernels can identify specific essential information and consider signal's temporal information. The proposed method achieves 61.97%, 73.82%, and 66.93% of sensitivity, specificity, and quality index, respectively, on the public CTU-UHB database. The proposed method achieves the highest QI on the private database, verifying the proposed method's effectiveness and generalization. The proposed DFFN combines the advantages of feature engineering and deep learning models and achieves competitive accuracy in fetal state assessment compared with related works.

Clinical Assessment of Fetal Well-Being and Fetal Safety Indicators

Delivering safe clinical trials of novel therapeutics is central to enable pregnant women and their babies to access medicines for better outcomes. This review describes clinical monitoring of fetal well‐being and safety. Current pregnancy surveillance includes regular antenatal checks of blood pressure and urine for signs of gestational hypertension. Fetal and placental development is assessed routinely using the first‐trimester “dating” and mid‐trimester “anomaly” ultrasound scans, but the detection of fetal anomalies can continue throughout pregnancy using targeted sonography or magnetic resonance imaging (MRI). Serial sonography can be used to assess fetal size, well‐being, and placental function. Carefully defined reproducible imaging parameters, such as the head circumference (HC), abdominal circumference (AC), and femur length (FL), are combined to calculate an estimate of the fetal weight. Doppler analysis of maternal uterine blood flow predicts placental insufficiency, which is associated with poor fetal growth. Fetal doppler analysis can indicate circulatory decompensation and fetal hypoxia, requiring delivery to be expedited. Novel ways to assess fetal well‐being and placental function using MRI, computerized cardiotocography (CTG), serum circulating fetoplacental proteins, and mRNA may improve the assessment of the safety and efficacy of maternal and fetal interventions. Progress has been made in how to define and grade clinical trial safety in pregnant women, the fetus, and neonate. A new system for improved safety monitoring for clinical trials in pregnancy, Maternal and Fetal Adverse Event Terminology (MFAET), describes 12 maternal and 18 fetal adverse event (AE) definitions and severity grading criteria developed through an international modified Delphi consensus process. This fills a vital gap in maternal and fetal translational medicine research.

Improving Development of Drug Treatments for Pregnant Women and the Fetus

The exclusion of pregnant populations, women of reproductive age, and the fetus from clinical trials of therapeutics is a major global public health issue. It is also a problem of inequity in medicines development, as pregnancy is a protected characteristic. The current regulatory requirements for drugs in pregnancy are being analyzed by a number of agencies worldwide. There has been considerable investment in developing expertise in pregnancy clinical trials (for the pregnant person and the fetus) such as the Obstetric-Fetal Pharmacology Research Centers funded by the National Institute of Child Health and Human Development. Progress has also been made in how to define and grade clinical trial safety in pregnant women, the fetus, and neonate. Innovative methods to model human pregnancy physiology and pharmacology using computer simulations are also gaining interest. Novel ways to assess fetal well-being and placental function using magnetic resonance imaging, computerized cardiotocography, serum circulating fetoplacental proteins, and mRNA may permit better assessment of the safety and efficacy of interventions in the mother and fetus. The core outcomes in women’s and newborn health initiative is facilitating the consistent reporting of data from pregnancy trials. Electronic medical records integrated with pharmacy services should improve the strength of pharmacoepidemiologic and pharmacovigilance studies. Incentives such as investigational plans and orphan disease designation have been taken up for obstetric, fetal, and neonatal diseases. This review describes the progress that is being made to better understand the extent of the problem and to develop applicable solutions.

Associations between fetal heart rate variability and umbilical cord occlusions-induced neural injury: An experimental study in a fetal sheep model

INTRODUCTION

This study evaluated the association between fetal heart rate variability (HRV) and the occurrence of hypoxic-ischemic encephalopathy in a fetal sheep model.

MATERIAL AND METHODS

The experimental protocol created a hypoxic condition with repeated cord occlusions in three phases (A, B, C) to achieve acidosis to pH <7.00. Hemodynamic, gasometric and HRV parameters were analyzed during the protocol, and the fetal brain, brainstem and spinal cord were assessed histopathologically 48 h later. Associations between the various parameters and neural injury were compared between phases A, B and C using Spearman's rho test.

RESULTS

Acute anoxic-ischemic brain lesions in all regions was present in 7/9 fetuses, and specific neural injury was observed in 3/9 fetuses. The number of brainstem lesions correlated significantly and inversely with the HRV fetal stress index (r = -0.784; p = 0.021) in phase C and with HRV long-term variability (r = -0.677; p = 0.045) and short-term variability (r = -0.837; p = 0.005) in phase B. The number of neurological lesions did not correlate significantly with other markers of HRV.

CONCLUSIONS

Neural injury caused by severe hypoxia was associated with HRV changes; in particular, brainstem damage was associated with changes in fetal-specific HRV markers.

IMPROVING PHASE-RECTIFIED SIGNAL AVERAGING FOR FETAL HEART RATE ANALYSIS

Low umbilical artery pH is a marker for neonatal acidosis and is associated with an increased risk for neonatal complications. The phase-rectified signal averaging (PRSA) features have demonstrated superior discriminatory or diagnostic ability and good interpretability in many biomedical applications including fetal heart rate analysis. However, the performance of PRSA method is sensitive to values of the selected parameters which are usually either chosen based on a grid search or empirically in the literature. In this paper, we examine PRSA method through the lens of dynamical systems theory and reveal the intrinsic connection between state space reconstruction and PRSA. From this perspective, we then introduce a new feature that can better characterize dynamical systems comparing with PRSA. Our experimental results on an open-access intrapartum Cardiotocography database demonstrate that the proposed feature outperforms state-of-the-art PRSA features in pH-based fetal heart rate analysis.

Fetal heart rate variability is a biomarker of rapid but not progressive exacerbation of inflammation in preterm fetal sheep

Perinatal infection/inflammation can trigger preterm birth and contribute to neurodevelopmental disability. There are currently no sensitive, specific methods to identify perinatal infection. We investigated the utility of time, frequency and non-linear measures of fetal heart rate (FHR) variability (FHRV) to identify either progressive or more rapid inflammation. Chronically instrumented preterm fetal sheep were randomly assigned to one of three different 5d continuous i.v. infusions: 1) control (saline infusions; n = 10), 2) progressive lipopolysaccharide (LPS; 200 ng/kg over 24 h, doubled every 24 h for 5d, n = 8), or 3) acute-on-chronic LPS (100 ng/kg over 24 h then 250 ng/kg/24 h for 4d plus 1 μg boluses at 48, 72, and 96 h, n = 9). Both LPS protocols triggered transient increases in multiple measures of FHRV at the onset of infusions. No FHRV or physiological changes occurred from 12 h after starting progressive LPS infusions. LPS boluses during the acute-on-chronic protocol triggered transient hypotension, tachycardia and an initial increase in multiple time and frequency domain measures of FHRV, with an asymmetric FHR pattern of predominant decelerations. Following resolution of hypotension after the second and third LPS boluses, all frequencies of FHRV became suppressed. These data suggest that FHRV may be a useful biomarker of rapid but not progressive preterm infection/inflammation.

Cardiotocography and Clinical Risk Factors in Early Term Labor: A Retrospective Cohort Study Using Computerized Analysis With Oxford System

OBJECTIVE

The role of cardiotocography (CTG) in fetal risk assessment around the beginning of term labor is controversial. We used routinely collected clinical data in a large tertiary hospital to investigate whether infants with "severe compromise" at birth exhibited fetal heart rate abnormalities in their first-hour CTGs and/or other clinical risks, recorded as per routine care.

MATERIALS AND METHODS

Retrospective data from 27,927 parturitions (single UK tertiary site, 2001-2010) were analyzed. Cases were included if the pregnancy was singleton, ≥36 weeks' gestation, cephalic presentation, and if they had routine intrapartum CTG as per clinical care. Cases with congenital abnormalities, planned cesarean section (CS), or CS for reasons other than "presumed fetal compromise" were excluded. We analyzed first-hour intrapartum CTG recordings, using intrapartum Oxford System (OxSys) computer-based algorithms. To reflect the effect of routine clinical care, the data was stratified into three exclusive groups: infants delivered by CS for "presumed fetal compromise" within 2 h of starting the CTG (Emergency CS, n = 113); between 2 and 5 h of starting the CTG (Urgent CS, n = 203); and the rest of deliveries (Others, n = 27,611). First-hour CTG and clinical characteristics were compared between the groups, sub-divided to those with and without severe compromise: a composite outcome of stillbirth, neonatal death, neonatal seizures, encephalopathy, resuscitation followed by ≥48 h in neonatal intensive care unit. Two-sample t-test, X² test, and Fisher's exact test were used for analysis.

RESULTS

Compared to babies without severe compromise, those with compromise had significantly higher proportion of cases with baseline fetal heart rate ≥150 bpm; non-reactive trace; reduced long-term and short-term variability; decelerative capacity; and no accelerations in the first-hour CTG across all groups. Prolonged decelerations(≥3 min) were also more common. Thick meconium and small for gestational age were consistently more common in compromised infants across all groups. There was more often thick meconium, maternal fever ≥38 C, sentinel events, and other clinical risk factors in the Emergency CS and Urgent CS compared to the Others group.

CONCLUSION

A proportion of infants born with severe compromise had significantly different first-hour CTG features and clinical risk factors.

Distance to Healthy Metabolic and Cardiovascular Dynamics From Fetal Heart Rate Scale-Dependent Features in Pregnant Sheep Model of Human Labor Predicts the Evolution of Acidemia and Cardiovascular Decompensation

The overarching goal of the present work is to contribute to the understanding of the relations between fetal heart rate (FHR) temporal dynamics and the well-being of the fetus, notably in terms of predicting the evolution of lactate, pH and cardiovascular decompensation (CVD). It makes uses of an established animal model of human labor, where 14 near-term ovine fetuses subjected to umbilical cord occlusions (UCO) were instrumented to permit regular intermittent measurements of metabolites lactate and base excess, pH, and continuous recording of electrocardiogram (ECG) and systemic arterial blood pressure (to identify CVD) during UCO. ECG-derived FHR was digitized at the sampling rate of 1,000 Hz and resampled to 4 Hz, as used in clinical routine. We focused on four FHR variability features which are tunable to temporal scales of FHR dynamics, robustly computable from FHR sampled at 4 Hz and within short-time sliding windows, hence permitting a time-dependent, or local, analysis of FHR which helps dealing with signal noise. Results show the sensitivity of the proposed features for early detection of CVD, correlation to metabolites and pH, useful for early acidosis detection and the importance of coarse time scales (2.5-8 s) which are not disturbed by the low FHR sampling rate. Further, we introduce the performance of an individualized self-referencing metric of the distance to healthy state, based on a combination of the four features. We demonstrate that this novel metric, applied to clinically available FHR temporal dynamics alone, accurately predicts the time occurrence of CVD which heralds a clinically significant degradation of the fetal health reserve to tolerate the trial of labor.

Deceleration area and capacity during labour-like umbilical cord occlusions identify evolving hypotension: a controlled study in fetal sheep

OBJECTIVE

Cardiotocography is widely used to assess fetal well-being during labour. The positive predictive value of current clinical algorithms to identify hypoxia-ischaemia is poor. In experimental studies, fetal hypotension is the strongest predictor of hypoxic-ischaemic injury. Cohort studies suggest that deceleration area and deceleration capacity of the fetal heart rate trace correlate with fetal acidaemia, but it is not known whether they are indices of fetal arterial hypotension.

DESIGN

Prospective, controlled study.

SETTING

Laboratory.

SAMPLE

Near-term fetal sheep.

METHODS

One minute of complete umbilical cord occlusions (UCOs) every 5 minutes (1:5 min, n = 6) or every 2.5 minutes (1:2.5 min, n = 12) for 4 hours or until fetal mean arterial blood pressure fell <20 mmHg.

MAIN OUTCOME MEASURES

Deceleration area and capacity during the UCO series were related to evolving hypotension.

RESULTS

The 1:5 min group developed only mild metabolic acidaemia, without hypotension. By contrast, 10/12 fetuses in the 1:2.5-min group progressively developed severe metabolic acidaemia and hypotension, reaching 16.8 ± 0.9 mmHg after 71.2 ± 6.7 UCOs. Deceleration area and capacity remained unchanged throughout the UCO series in the 1:5-min group, but progressively increased in the 1:2.5-min group. The severity of hypotension was closely correlated with both deceleration area (P < 0.001, R²  = 0.66, n = 18) and capacity (P < 0.001, R²  = 0.67, n = 18). Deceleration area and capacity predicted development of hypotension at a median of 103 and 123 minutes before the final occlusion, respectively.

CONCLUSIONS

Both deceleration area and capacity were strongly associated with developing fetal hypotension, supporting their potential to improve identification of fetuses at risk of hypotension leading to hypoxic-ischaemic injury during labour.

TWEETABLE ABSTRACT

Deceleration area and capacity of fetal heart rate identify developing hypotension during labour-like hypoxia.

Estimation of Consecutively Missed Samples in Fetal Heart Rate Recordings

During labor, fetal heart rate (FHR) is monitored externally using Doppler ultrasound. This is done continuously, but for various reasons (e.g., fetal or maternal movements) the system does not record any samples for varying periods of time. In many settings, it would be quite beneficial to estimate the missing samples. In this paper, we propose a (deep) Gaussian process-based approach for estimation of consecutively missing samples in FHR recordings. The method relies on similarities in the state space and on exploiting the concept of attractor manifolds. The proposed approach was tested on a short segment of real FHR recordings. The experimental results indicate that the proposed approach is able to provide more reliable results in comparison to several interpolation methods that are commonly applied for processing of FHR signals.

A review of fetal cardiac monitoring, with a focus on low- and middle-income countries

There is limited evidence regarding the utility of fetal monitoring during pregnancy, particularly during labor and delivery. Developed countries rely on consensus ‘best practices’ of obstetrics and gynecology professional societies to guide their protocols and policies. Protocols are often driven by the desire to be as safe as possible and avoid litigation, regardless of the cost of downstream treatment. In high-resource settings, there may be a justification for this approach. In low-resource settings, in particular, interventions can be costly and lead to adverse outcomes in subsequent pregnancies. Therefore, it is essential to consider the evidence and cost of different fetal monitoring approaches, particularly in the context of treatment and care in low-to-middle income countries.

This article reviews the standard methods used for fetal monitoring, with particular emphasis on fetal cardiac assessment, which is a reliable indicator of fetal well-being. An overview of fetal monitoring practices in low-to-middle income counties, including perinatal care access challenges, is also presented. Finally, an overview of how mobile technology may help reduce barriers to perinatal care access in low-resource settings is provided.

Is short-term-variation of fetal-heart-rate a better predictor of fetal acidaemia in labour? A feasibility study

Background

Continuous intrapartum fetal monitoring is challenging and its clinical benefits are debated. The project evaluated whether short-term-variation (STV) and other computerised fetal heart rate (FHR) parameters (baseline FHR, long-term-variation, accelerations and decelerations) predicted acidaemia at birth. The aims of the study were to assess the changes in FHR pattern during labour and determine the feasibility of undertaking a definitive trial by reporting the practicalities of using the monitoring device, participant recruitment, data collection and staff training.

Methods

200 high-risk women carrying a term singleton, non-anomalous fetus, requiring continuous FHR monitoring in labour were consented to participate from the Jessop Wing maternity unit, Sheffield, UK. The trans-abdominal fetal ECG monitor was placed as per clinical protocol. During the monitoring session, clinicians were blinded to the computerised FHR parameters. We analysed the last hour of the FHR and its ability to predict umbilical arterial blood pH <7.20 using receiver operator characteristics (ROC) curves.

Results

Of 200 women, 137 cases were excluded as either the monitor did not work from the onset of labour (n = 30), clinical staff did not return or used the monitor on another patient (n = 37), umbilical cord blood not obtained (n = 25), FHR data not recorded within an hour of birth (n = 34) and other reasons (n = 11). In 63 cases included in the final analysis, the computer-derived FHR parameters did not show significant correlation with umbilical artery cord pH <7.20. Labour was associated with a significant increase in short and long term variation of FHR and number of deceleration (P<0.001). However, baseline FHR decreased significantly before delivery (P<0.001).

Conclusions

The project encountered a number of challenges, with learning points crucial to informing the design of a large study to evaluate the potential place of intrapartum computerised FHR parameters, using abdominal fetal ECG monitor before its clinical utility and more widespread adoption can be ascertained.

DISCOVERING CAUSALITIES FROM CARDIOTOCOGRAPHY SIGNALS USING IMPROVED CONVERGENT CROSS MAPPING WITH GAUSSIAN PROCESSES

Convergent cross mapping (CCM) is designed for causal discovery in coupled time series, where Granger causality may not be applicable because of a separability assumption. However, CCM is not robust to observation noise which limits its applicability on signals that are known to be noisy. Moreover, the parameters for state space reconstruction need to be selected using grid search methods. In this paper, we propose a novel improved version of CCM using Gaussian processes for discovery of causality from noisy time series. Specifically, we adopt the concept of CCM and carry out the key steps using Gaussian processes within a non-parametric Bayesian probabilistic framework in a principled manner. The proposed approach is first validated on simulated data, and then used for understanding the interaction between fetal heart rate and uterine activity in the last two hours before delivery and of interest in obstetrics. Our results indicate that uterine activity affects the fetal heart rate, which agrees with recent clinical studies.

Detecting Causality using Deep Gaussian Processes

Convergent cross mapping (CCM) is a state space reconstruction (SSR)-based method designed for causal discovery in coupled time series, where Granger causality may not be applicable due to a separability assumption. However, CCM requires a large number of observations and is not robust to observation noise which limits its applicability. Moreover, in CCM and its variants, the SSR step is mostly implemented with delay embedding where the parameters for reconstruction usually need to be selected using grid search-based methods. In this paper, we propose a Bayesian version of CCM using deep Gaussian processes (DGPs), which are naturally connected with deep neural networks. In particular, we adopt the framework of SSR-based causal discovery and carry out the key steps using DGPs within a non-parametric Bayesian probabilistic framework in a principled manner. The proposed approach is first validated on simulated data and then tested on data used in obstetrics for monitoring the well-being of fetuses, i.e., fetal heart rate (FHR) and uterine activity (UA) signals in the last two hours before delivery. Our results indicate that UA affects the FHR, which agrees with recent clinical studies.

Impact of Chronic Fetal Hypoxia and Inflammation on Cardiac Pacemaker Cell Development

Chronic fetal hypoxia and infection are examples of adverse conditions during complicated pregnancy, which impact cardiac myogenesis and increase the lifetime risk of heart disease. However, the effects that chronic hypoxic or inflammatory environments exert on cardiac pacemaker cells are poorly understood. Here, we review the current evidence and novel avenues of bench-to-bed research in this field of perinatal cardiogenesis as well as its translational significance for early detection of future risk for cardiovascular disease.

EXTRACTING INTERPRETABLE FEATURES FOR FETAL HEART RATE RECORDINGS WITH GAUSSIAN PROCESSES

During labor, fetal heart rate (FHR) and uterine activity (UA) are continuously monitored with Cardiotocography (CTG). The FHR and UA signals are visually inspected by obstetricians to assess the fetal well-being. However, due to the subjectivity of the visual inspection, the evaluations of CTG recordings performed by obstetricians have high inter- and intra-variability. The computerized analysis of FHR relies on features either hand-crafted by experts or automatically learned by machine learning methods. However, the popular interpretable FHR features, in general, have low correlation with the pH value of the umbilical cord blood at birth, which is the current gold standard for labeling FHRs in the computerized analysis of FHRs. The features found by machine learning methods, by contrast, usually have limited interpretability. In this paper, in a follow up of our previous work on FHR analysis using Gaussian processes (GPs), we explore the possibility of using the hyperparameters of GPs as interpretable features. Our results indicate that some GP features achieve high correlation with the pH values, while at the same time they are not highly correlated with other popular features.

Relative accuracy of computerized intrapartum fetal heart rate pattern recognition by ultrasound and abdominal electrocardiogram detection

INTRODUCTION

Noninvasive fetal heart rate monitoring using transabdominal fetal electrocardiographic detection is now commercially available and has been demonstrated to be an effective alternative to traditional Doppler ultrasonographic techniques. Our objective in this study was to compare the results of computerized identification of fetal heart rate patterns generated by ultrasound-based and transabdominal fetal electrocardiogram-based techniques with simultaneously obtained fetal scalp electrode-derived heart rate information.

MATERIAL AND METHODS

We applied an objective computer-based analysis for recognition of fetal heart rate patterns (Monica Decision Support) to data obtained simultaneously from a direct fetal scalp electrode, Doppler ultrasound, and the abdominal-fetal electrocardiogram techniques. This allowed us to compare over 145 hours of fetal heart rate patterns generated by the external devices with those derived from the scalp electrode in 30 term singleton uncomplicated pregnancies during labor. The direct fetal scalp electrode is considered to be the most accurate and reliable technique used in current clinical practice, and was, therefore, used as the standard for comparison. The program quantified the baseline heart rate, long- and short-term variability. It indicated when an acceleration or deceleration was present and whether it was large or small.

RESULTS

Ultrasound was associated with significantly greater deviations from the fetal scalp electrode results than the abdominal fetal electrocardiogram technique in recognizing the correct baseline heart rate, its variability, and the presence of small and large accelerations and small decelerations. For large decelerations the two external methods were each not significantly different from the scalp electrode results.

CONCLUSIONS

Noninvasive fetal heart rate monitoring using maternal abdominal wall electrodes to detect fetal cardiac activity more reliably reproduced the computerized analysis of heart rate patterns derived from a direct fetal scalp electrode than did traditional ultrasound-based monitoring. Abdominal-fetal electrocardiogram should, therefore, be considered a primary option for externally monitored patients.

Use of automated fetal heart rate analysis to identify risk factors for umbilical cord acidosis at birth

OBJECTIVE

To identify clinical parameters and intrapartum fetal heart rate parameters associated with a risk of umbilical cord acidosis at birth, using an automated analysis method based on empirical mode decomposition.

METHODS

Our single-center study included 381 cases (arterial cord blood pH at birth pHa ≤7.15) and 1860 controls (pHa ≥7.25) extracted from a database comprising 8,383 full datasets for over-18 mothers after vaginal or caesarean non-twin, non-breech deliveries at term (>37 weeks of amenorrhea). The analysis of a 120-min period of the FHR recording (before maternal pushing or the decision to perform a caesarean section during labor) led to the extraction of morphological, frequency-related, and long- and short-term heart rate variability variables. After univariate analyses, sparse partial least square selection and logistic regression were applied.

RESULTS

Several clinical factors were predictive of fetal acidosis in a multivariate analysis: nulliparity (odds ratio (OR) 95% confidence interval (CI)]: 1.769 [1.362-2.300]), a male fetus (1.408 [1.097-1.811]), and the term of the pregnancy (1.333 [1.189-1.497]). The risk of acidosis increased with the time interval between the end of the FHR recording and the delivery (OR [95%CI] for a 1-min increment: 1.022 [1.012-1.031]). The risk factors related to the FHR signal were mainly the difference between the mean baseline and the mean FHR (OR [95%CI]: 1.292 [1.174-1.424]), the baseline range (1.027 [1.014-1.040]), fetal bradycardia (1.038 [1.003-1.075]) and the late deceleration area (1.002 [1.000-1.005]). The area under the curve for the multivariate model was 0.79 [0.76; 0.81].

CONCLUSION

In addition to clinical predictors, the automated FHR analysis highlighted other significant predictors, such as the baseline range, the instability of the FHR signal and the late deceleration area. This study further extends the routine application of automated FHR analysis during labor and, ultimately, contributes to the development of predictive scores for fetal acidosis.