Fetal heart rate spectral analysis in raw signals and PRSA-derived curve: normal and pathological fetuses discrimination.

Cardiotocography (CTG) is the most common technique for electronic fetal monitoring and consists of the simultaneous recording of fetal heart rate (FHR) and uterine contractions. In analogy with the adult case, spectral analysis of the FHR signal can be used to assess the functionality of the autonomic nervous system. To do so, several methods can be employed, each of which has its strengths and limitations. This paper aims at performing a methodological investigation on FHR spectral analysis adopting 4 different spectrum estimators and a novel PRSA-based spectral method. The performances have been evaluated in terms of the ability of the various methods to detect changes in the FHR in two common pregnancy complications: intrauterine growth restriction (IUGR) and gestational diabetes. A balanced dataset containing 2178 recordings distributed between the 32nd and 38th week of gestation was used. The results show that the spectral method derived from the PRSA better differentiates high-risk pregnancies vs. controls compared to the others. Specifically, it more robustly detects an increase in power percentage within the movement frequency band and a decrease in high frequency between pregnancies at high risk in comparison to those at low risk.

Fetal states identification in cardiotocographic tracings through discrete emissions multivariate hidden Markov models.

BACKGROUND AND OBJECTIVES: Computerized Cardiotocography (cCTG) allows to analyze the Fetal Heart Rate (FHR) objectively and thoroughly, providing valuable insights on fetal condition. A challenging but crucial task in this context is the automatic identification of fetal activity and quiet periods within the tracings. Different neural mechanisms are involved in the regulation of the fetal heart, depending on the behavioral states. Thereby, their correct identification has the potential to increase the interpretability and diagnostic capabilities of FHR quantitative analysis. Moreover, the most common pathologies in pregnancy have been associated with variations in the alternation between quiet and activity states. METHODS: We address the problem of fetal states clustering by means of an unsupervised approach, resorting to the use of a multivariate Hidden Markov Models (HMM) with discrete emissions. A fixed length sliding window is shifted on the CTG traces and a small set of features is extracted at each slide. After an encoding procedure, these features become the emissions of a multivariate HMM in which quiet and activity are the hidden states. After an unsupervised training procedure, the model is used to automatically segment signals. RESULTS: The achieved results indicate that our developed model exhibits a high degree of reliability in identifying quiet and activity states within FHR signals. A set of 35 CTG signals belonging to different pregnancies were independently annotated by an expert gynecologist and segmented using the proposed HMM. To avoid any bias, the physician was blinded to the results provided by the algorithm. The overall agreement between the HMM's predictions and the clinician's interpretations was 90%. CONCLUSIONS: The proposed method reliably identified fetal behavioral states, the alternance of which is an important factor in the fetal development. One key strength of our approach lies in the ease of interpreting the obtained results. By utilizing a small set of parameters that are already used in cCTG and possess clear intrinsic meanings, our method provides a high level of explainability. Another significant advantage of our approach is its fully unsupervised learning process. The states identified by our model using the Baum-Welch algorithm are associated with the "Active" and "Quiet" states only after the clustering process, removing the reliance on expert annotations. By autonomously identifying the clusters based solely on the intrinsic characteristics of the signal, our method achieves a more objective evaluation that overcomes the limitations of subjective interpretations. Indeed, we believe it could be integrated in cCTG systems to obtain a more complete signal analysis.

A Novel Large Structured Cardiotocographic Database.

In this work we present the creation of a large, structured database of CardioTocoGraphic (CTG) recordings, starting from a raw dataset containing tracings collected between 2013 and 2021 by the medical team of the University Hospital Federico II of Naples. The aim of the work is to provide a big, structured database of real clinical cardiotocographic data, useful for subsequent processing and analysis through state-of-the-art methods, in particular Deep Learning Methods. This organized dataset could lead to an increase of the diagnostic accuracy of CTG analysis in the discrimination of healthy and unhealthy fetuses.

A Machine Learning Approach to Monitor the Emergence of Late Intrauterine Growth Restriction.

Late intrauterine growth restriction (IUGR) is a fetal pathological condition characterized by chronic hypoxia secondary to placental insufficiency, resulting in an abnormal rate of fetal growth. This pathology has been associated with increased fetal and neonatal morbidity and mortality. In standard clinical practice, late IUGR diagnosis can only be suspected in the third trimester and ultimately confirmed at birth. This study presents a radial basis function support vector machine (RBF-SVM) classification based on quantitative features extracted from fetal heart rate (FHR) signals acquired using routine cardiotocography (CTG) in a population of 160 healthy and 102 late IUGR fetuses. First, the individual performance of each time, frequency, and nonlinear feature was tested. To improve the unsatisfactory results of univariate analysis we firstly adopted a Recursive Feature Elimination approach to select the best subset of FHR-based parameters contributing to the discrimination of healthy vs. late IUGR fetuses. A fine tuning of the RBF-SVM model parameters resulted in a satisfactory classification performance in the training set (accuracy 0.93, sensitivity 0.93, specificity 0.84). Comparable results were obtained when applying the model on a totally independent testing set. This investigation supports the use of a multivariate approach for the in utero identification of late IUGR condition based on quantitative FHR features encompassing different domains. The proposed model allows describing the relationships among features beyond the traditional linear approaches, thus improving the classification performance. This framework has the potential to be proposed as a screening tool for the identification of late IUGR fetuses.

Transfer Entropy Modeling of Newborn Cardiorespiratory Regulation.

This study investigates the complex interplay between the cardiac and respiratory systems in 268 healthy neonates born between 35 and 40 weeks of gestation. The aim is to provide a comprehensive description of the developing cardiorespiratory information transfer mechanisms as a function of gestational age (GA). This report proposes an extension of the traditional Transfer Entropy measure (TE), which employs multiple lagged versions of the time series of the intervals between two successive R waves of the QRS signal on the electrocardiogram (RR series) and respiration time series (RESP). The method aims to quantify the instantaneous and delayed effects between the two processes within a fine-grained time scale. Firstly, lagged TE was validated on a simulated dataset. Subsequently, lagged TE was employed on newborn cardiorespiratory data. Results indicate a progressive increase in information transfer as a function of gestational age, as well as significant differences in terms of instantaneous and delayed interactions between the cardiac and the respiratory system when comparing the two TE directionalities (RR→RESP vs. RESP→RR). The proposed investigation addresses the role of the different autonomic nervous system (ANS) branches involved in the cardiorespiratory system, since the sympathetic and parasympathetic branches operate at different time scales. Our results allow to infer that the two TE directionalities are uniquely and differently modulated by both branches of the ANS. TE adds an original quantitative tool to understanding cardiorespiratory imbalance in early infancy.

Dataset on linear and non-linear indices for discriminating healthy and IUGR fetuses.

The presented collection of data comprises of a set of 12 linear and nonlinear indices computed at different time scales and extracted from Fetal Heart Rate (FHR) traces acquired through Hewlett Packard CTG fetal monitors (series 1351A), connected to a PC. The sampling frequency of the recorded FHR signal is equal 2 Hz. The recorded populations consist of two groups of fetuses: 60 healthy and 60 Intra Uterine Growth Restricted (IUGR) fetuses. IUGR condition is a fetal condition defined as the abnormal rate of fetal growth. In clinical practice, diagnosis is confirmed at birth and may only be suspected during pregnancy. The pathology is a documented cause of fetal and neonatal morbidity and mortality. The described database was employed in a set of machine learning approaches for the early detection of the IUGR condition: "Integrating machine learning techniques and physiology based heart rate features for antepartum fetal monitoring" [1]. The added value of the proposed indices is their interpretability and close connection to physiological and pathological aspect of FHR regulation. Additional information on data acquisition, feature extraction and potential relevance in clinical practice are discussed in [1].

Integrating machine learning techniques and physiology based heart rate features for antepartum fetal monitoring.

BACKGROUND AND OBJECTIVES: Intrauterine Growth Restriction (IUGR) is a fetal condition defined as the abnormal rate of fetal growth. The pathology is a documented cause of fetal and neonatal morbidity and mortality. In clinical practice, diagnosis is confirmed at birth and may only be suspected during pregnancy. Therefore, designing an accurate model for the early and prompt identification of pathology in the antepartum period is crucial in view of pregnancy management. METHODS: We tested the performance of 15 machine learning techniques in discriminating healthy versus IUGR fetuses. The various models were trained with a set of 12 physiology based heart rate features extracted from a single antepartum CardioTocographic (CTG) recording. The reason for the utilization of time, frequency, and nonlinear indices is based on their standalone documented ability to describe several physiological and pathological fetal conditions. RESULTS: We validated our approach on a database of 60 healthy and 60 IUGR fetuses. The machine learning methodology achieving the best performance was Random Forests. Specifically, we obtained a mean classification accuracy of 0.911 [0.860, 0.961 (0.95 confidence interval)] averaged over 10 test sets (10 Fold Cross Validation). Similar results were provided by Classification Trees, Logistic Regression, and Support Vector Machines. A features ranking procedure highlighted that nonlinear indices showed the highest capability to discriminate between the considered fetal conditions. Nevertheless, is the combination of features investigating CTG signal in different domains, that contributes to an increase in classification accuracy. CONCLUSIONS: We provided validation of an accurate artificially intelligence framework for the diagnosis of IUGR condition in the antepartum period. The employed physiology based heart rate features constitute an interpretable link between the machine learning results and the quantitative estimators of fetal wellbeing.

Fetal heart rate monitoring and neonatal outcome in a population of early- and late-onset intrauterine growth restriction.

AIM: The early-onset intrauterine growth restriction (IUGR) is associated with severe placental insufficiency and Doppler abnormalities. The late-onset IUGR is associated with mild placental insufficiency and normal Doppler velocimetry. The computerized cardiotocographic (cCTG) monitoring is used to evaluate the fetal well-being in pregnancies complicated by IUGR. Our aim was to investigate the cardiotocographic characteristics of IUGR fetuses and to identify every cCTG difference between Healthy and IUGR fetuses. METHODS: Four hundred thirty pregnant women were enrolled starting from the 28th week of gestation until the time of delivery: 200 healthy and 230 IUGR fetuses. Fetal heart rate (FHR) baseline (FHR), short-term variability (STV), long-term irregularity (LTI), delta, interval index (II), approximate entropy (ApEn), high frequency (HF), low frequency (LF), movement frequency (MF), LF/(HF + MF) ratio (LF/(HF + MF)) and number of decelerations were examined. Newborn baby data were also collected. RESULTS: The parameters of short- and medium-term variability discriminate between IUGR and healthy fetuses before 36 weeks including FHR, STV, LTI and delta discriminate between each subgroup of IUGR were compared to each one of the other two (P < 0.05). CONCLUSION: cCTG is a useful tool for the evaluation of chronic hypoxemia, which causes a delay in the maturation of all components of the autonomic and central nervous system. However, cCTG requires integration with fetal ultrasound and Doppler vessels evaluation to improve the ability to predict the neonatal outcome.

A Point Process Framework for the Characterization of Sleep States in Early Infancy.

It is well known that the coordination among several subsystems in newborns is effectively changing as a function of behavioral states. For this reason, sleep state characterization is an essential procedure in neonatal monitoring. Despite its importance, methodologies assessing sleep states are discrete in time and usually based on visual inspection. In this work, we validate a point process framework on a population of 113 full-term infants with the aim of providing continuous sleep state characterization over time. After determining a suitable probability density distribution to best fit the neonatal RR series, we compare traditional heart rate variability (HRV) parameters with the point process-extracted sets of time and frequency domain instantaneous measures in order to validate the proposed framework. Our results provide insights into the point process ability to capture HRV dynamics with a high degree of reliability, thus providing evidence that our framework might be employed for an instantaneous estimate of behavioral states.

An Efficient Algorithm for the Extraction of Fetal ECG from Standard and Non-Standard Multi Abdominal Maternal Leads.

The importance of fetal surveillance during pregnancy is worldwide accepted since its peculiar ability to anticipate fetal distress under a variety of conditions. The novel frontier in the field of remote fetal monitoring relies on a continuous and everyday-monitoring of fetal wellbeing. As a consequence, fECG monitoring systems have seen a net increase in popularity in the recent years. In this paper, we propose a novel algorithm for the detection of fECG and we validated its performances by testing it on an open source collection of 75 annotated fECG traces. Our results show the reliability of the proposed methodology in extracting fECG and deriving an estimate of fHR.

Multi-parametric cardiorespiratory analysis in late-preterm, early-term, and full-term infants at birth.

Infants born at 35-37 weeks' gestational age (GA) are at higher risk for a range of pathological conditions and poorer neurodevelopmental outcomes. However, mechanisms responsible are not fully understood. The purpose of this paper is to use traditional and novel techniques to assess newborn autonomic development as a function of GA at birth, focusing on cardiorespiratory regulation. ECG and respiration were acquired during sleep on 329 healthy newborns. Infants were divided into GA groups: 35-36 weeks (late preterm (LPT)), 37-38 weeks (early term (ET)), and 39-40 weeks (full term (FT)). Time domain, frequency domain, and non-linear measures were calculated. Increased heart rate short-term variability and complexity as a function of GA were observed in time domain and non-linear measures. Decreasing inter-breath interval variability was found as a function of GA, with increasing linear cardiorespiratory coupling. A complexity parameter (quadratic sample entropy) was less affected by arrhythmias and artifacts when compared to traditional measures. Results suggest lower maturation in LPT, with less developed cardiorespiratory regulation. This may confer risk for altered outcome, convergent with epidemiological findings. Reported examples show that a combination of methodological approaches can be beneficial to characterize autonomic maturation. Graphical abstract ᅟ.

Influence of prenatal alcohol and smoke exposure on neonatal vagal tone in response to head-up tilt.

This paper investigates differences in the parasympathetically mediated heart rate response to head-up tilt in two populations of newborns. One group was unexposed to any drug during pregnancy, the other was exposed to both alcohol and smoking in utero. Four different estimates of vagal tone were calculated. These indexes quantify vagal tone magnitude in four different domains: time, frequency, complexity and phase. Control group (CG) results across all parameters show a consistent physiological response to an orthostatic tilt consistent with vagal withdrawal. On the other hand, infants in the exposed group (EG) did not express a decrease in vagal measures following tilt.

Characterization of cardiorespiratory phase synchronization and directionality in late premature and full term infants.

OBJECTIVE: Though the mutual influence of cardiovascular and respiratory rhythms in healthy newborns has been documented, its full characterization is still pending. In general, the activity of many physiological subsystems has a well-expressed rhythmic character, and often an interdependency between physiological rhythms emerges early in development. Traditional methods of data analysis only address the quantification of the strength of subsystem interactions. In this work, we will investigate system interrelationships in terms of the possible presence of causal or directional interplays. APPROACH: In this paper, we propose a methodological application that quantifies phase coupling and its directionality in a population of newborn infants born between 35 and 40 weeks of gestational age (GA). The aim is to assess whether GA at birth significantly influences the development of phase synchronization and the directionality of the coupling between the cardiovascular and respiratory system activity. Several studies indicating irregular cardiorespiratory coupling as a leading cause of several pathologies underscore the need to investigate this phenomenon in this at-risk population. MAIN RESULTS: Results from our investigation show a different directionality profile as a function of GA and sleep state. SIGNIFICANCE: These findings are a contribution to the understanding of higher risk for the documented negative outcomes in the late preterm population. Moreover, these parameters could provide a tool for the development of early markers of cardiorespiratory dysregulation in infants.

Entropy Information of Cardiorespiratory Dynamics in Neonates during Sleep.

Sleep is a central activity in human adults and characterizes most of the newborn infant life. During sleep, autonomic control acts to modulate heart rate variability (HRV) and respiration. Mechanisms underlying cardiorespiratory interactions in different sleep states have been studied but are not yet fully understood. Signal processing approaches have focused on cardiorespiratory analysis to elucidate this co-regulation. This manuscript proposes to analyze heart rate (HR), respiratory variability and their interrelationship in newborn infants to characterize cardiorespiratory interactions in different sleep states (active vs. quiet). We are searching for indices that could detect regulation alteration or malfunction, potentially leading to infant distress. We have analyzed inter-beat (RR) interval series and respiration in a population of 151 newborns, and followed up with 33 at 1 month of age. RR interval series were obtained by recognizing peaks of the QRS complex in the electrocardiogram (ECG), corresponding to the ventricles depolarization. Univariate time domain, frequency domain and entropy measures were applied. In addition, Transfer Entropy was considered as a bivariate approach able to quantify the bidirectional information flow from one signal (respiration) to another (RR series). Results confirm the validity of the proposed approach. Overall, HRV is higher in active sleep, while high frequency (HF) power characterizes more quiet sleep. Entropy analysis provides higher indices for SampEn and Quadratic Sample entropy (QSE) in quiet sleep. Transfer Entropy values were higher in quiet sleep and point to a major influence of respiration on the RR series. At 1 month of age, time domain parameters show an increase in HR and a decrease in variability. No entropy differences were found across ages. The parameters employed in this study help to quantify the potential for infants to adapt their cardiorespiratory responses as they mature. Thus, they could be useful as early markers of risk for infant cardiorespiratory vulnerabilities.

Monitoring fetal maturation-objectives, techniques and indices of autonomic function.

Monitoring the fetal behavior does not only have implications for acute care but also for identifying developmental disturbances that burden the entire later life. The concept, of 'fetal programming', also known as 'developmental origins of adult disease hypothesis', e.g. applies for cardiovascular, metabolic, hyperkinetic, cognitive disorders. Since the autonomic nervous system is involved in all of those systems, cardiac autonomic control may provide relevant functional diagnostic and prognostic information. The fetal heart rate patterns (HRP) are one of the few functional signals in the prenatal period that relate to autonomic control and, therefore, is predestinated for its evaluation. The development of sensitive markers of fetal maturation and its disturbances requires the consideration of physiological fundamentals, recording technology and HRP parameters of autonomic control. Based on the ESGCO2016 special session on monitoring the fetal maturation we herein report the most recent results on: (i) functional fetal autonomic brain age score (fABAS), Recurrence Quantitative Analysis and Binary Symbolic Dynamics of complex HRP resolve specific maturation periods, (ii) magnetocardiography (MCG) based fABAS was validated for cardiotocography (CTG), (iii) 30 min recordings are sufficient for obtaining episodes of high variability, important for intrauterine growth restriction (IUGR) detection in handheld Doppler, (iv) novel parameters from PRSA to identify Intra IUGR fetuses, (v) evaluation of fetal electrocardiographic (ECG) recordings, (vi) correlation between maternal and fetal HRV is disturbed in pre-eclampsia. The reported novel developments significantly extend the possibilities for the established CTG methodology. Novel HRP indices improve the accuracy of assessment due to their more appropriate consideration of complex autonomic processes across the recording technologies (CTG, handheld Doppler, MCG, ECG). The ultimate objective is their dissemination into routine practice and studies of fetal developmental disturbances with implications for programming of adult diseases.

Feasibility study for the assessment of cardio-respiratory coupling in newborn infants.

Cardio Respiratory Coupling (CRC) plays a key role during infant development. Nonetheless, mechanisms underlying it are still mostly unexplained and tools to assess it are often inadequate to understand its functioning. This study aims to evaluate the feasibility of CRC activity detection and quantification analyzing ECG and respiration of newborn healthy subjects. Cross-spectral analysis (coherence) and a novel application of a nonlinear method (Bivariate Phase Rectified Signal Averaging) were applied on 10 minutes recording from 4 subjects. Our preliminary results show that these methods can provide significant information about the occurrence and the strength of CRC, opening interesting perspectives in the evaluation of cardiorespiratory pathologies in newborn infants. In particular, the observed dynamic behavior appears stable and centered around one single frequency in Quiet Sleep, while being more variable and less consistent in Active Sleep.

A pre-docking source for the power-law behavior of spontaneous quantal release: application to the analysis of LTP.

In neurons, power-law behavior with different scaling exponents has been reported at many different levels, including fluctuations in membrane potentials, synaptic transmission up to neuronal network dynamics. Unfortunately in most cases the source of this non-linear feature remains controversial. Here we have analyzed the dynamics of spontaneous quantal release at hippocampal synapses and characterized their power-law behavior. While in control conditions a fractal exponent greater than zero was rarely observed, its value was greatly increased by α-latrotoxin (α-LTX), a potent stimulator of spontaneous release, known to act at the very last step of vesicle fusion. Based on computer modeling, we confirmed that at an increase in fusion probability would unmask a pre-docking phenomenon with 1/f structure, where α estimated from the release series appears to sense the increase in release probability independently from the number of active sites. In the simplest scenario the pre-docking 1/f process could coincide with the Brownian diffusion of synaptic vesicles. Interestingly, when the effect of long-term potentiation (LTP) was tested, a ~200% long-lasting increase in quantal frequency was accompanied by a significant increase in the scaling exponent. The similarity between the action of LTP and of α-LTX suggests an increased contribution of high release probability sites following the induction of LTP. In conclusion, our results indicate that the source of the synaptic power-law behavior arises before synaptic vesicles dock to the active zone and that the fractal exponent α is capable of sensing a change in release probability independently from the number of active sites or synapses.

The forgotten role of central volume in low frequency oscillations of heart rate variability.

The hypothesis that central volume plays a key role in the source of low frequency (LF) oscillations of heart rate variability (HRV) was tested in a population of end stage renal disease patients undergoing conventional hemodialysis (HD) treatment, and thus subject to large fluid shifts and sympathetic activation. Fluid overload (FO) in 58 chronic HD patients was assessed by whole body bioimpedance measurements before the midweek HD session. Heart Rate Variability (HRV) was measured using 24-hour Holter electrocardiogram recordings starting before the same HD treatment. Time domain and frequency domain analyses were performed on HRV signals. Patients were retrospectively classified in three groups according to tertiles of FO normalized to the extracellular water (FO/ECW%). These groups were also compared after stratification by diabetes mellitus. Patients with the low to medium hydration status before the treatment (i.e. 1st and 2nd FO/ECW% tertiles) showed a significant increase in LF power during last 30 min of HD compared to dialysis begin, while no significant change in LF power was seen in the third group (i.e. those with high pre-treatment hydration values). In conclusion, several mechanisms can generate LF oscillations in the cardiovascular system, including baroreflex feedback loops and central oscillators. However, the current results emphasize the role played by the central volume in determining the power of LF oscillations.

Influence of sleep state and position on cardio-respiratory regulation in newborn babies.

The paper presents results of a sleep study on 60 newborn infants and 22 one-month infants, in quiet and active sleep and in prone and supine position. During the study, HRV and respiration were acquired and then analyzed with a multi-parametric approach. Time, Frequency Domain and Non-Linear parameters were calculated, also encompassing indices from the adult and fetal field. The novelty of this study is the introduction of innovative measurements in a thorough investigation to characterize the effect of sleep state and position on the cardio-respiratory control in newborns. Results show that most parameters succeed in classifying different sleep states, while differences between positions were found in the one-month population only. This study comes as a continuation of previous analysis with the addition of respiratory signal. These results are encouraging for the aim of defining a set of parameters that could help characterizing the autonomic control of infants and early detect the onset of distress or particular pathologies.