Fractal Analysis and Hurst Parameter for Intrapartum Fetal Heart Rate Variability Analysis: A Versatile Alternative to Frequency Bands and LF/HF Ratio

A multimodal deep learning-based algorithm for specific fetal heart rate events detection

OBJECTIVES

This study aims to develop a multimodal deep learning-based algorithm for detecting specific fetal heart rate (FHR) events, to enhance automatic monitoring and intelligent assessment of fetal well-being.

METHODS

We analyzed FHR and uterine contraction signals by combining various feature extraction techniques, including morphological features, heart rate variability features, and nonlinear domain features, with deep learning algorithms. This approach enabled us to classify four specific FHR events (bradycardia, tachycardia, acceleration, and deceleration) as well as four distinct deceleration patterns (early, late, variable, and prolonged deceleration). We proposed a multi-model deep neural network and a pre-fusion deep learning model to accurately classify the multimodal parameters derived from Cardiotocography signals.

RESULTS

These accuracy metrics were calculated based on expert-labeled data. The algorithm achieved a classification accuracy of 96.2 % for acceleration, 94.4 % for deceleration, 90.9 % for tachycardia, and 85.8 % for bradycardia. Additionally, it achieved 67.0 % accuracy in classifying the four distinct deceleration patterns, with 80.9 % accuracy for late deceleration and 98.9 % for prolonged deceleration.

CONCLUSIONS

The proposed multimodal deep learning algorithm serves as a reliable decision support tool for clinicians, significantly improving the detection and assessment of specific FHR events, which are crucial for fetal health monitoring.

Metabolic flexibility and resting autonomic function in active menopausal women

PURPOSE

The present study aims to analyze the relationship between cardiac autonomic control at rest-i.e., baseline Heart Rate Variability (HRV)-and metabolic flexibility assessed by means of the FATox and CHOox oxidation rates at the intensities of maximum fat and carbohydrate oxidation (MFO and MCO, respectively).

METHODS

Twenty-four active over-60 women (66.8 ± 4.4 years) had their HRV assessed with 10 min recordings under resting conditions, and this was analyzed with Kubios Scientific software. After this, an incremental submaximal cycling test, starting at 30 watts, with increments of 10 watts every 3 min 15 s was performed. FATox and CHOox were calculated in the last 60 s at each step, using Frayn's equation. MFO and MCO were further obtained.

RESULTS

Nonlinear SampEn and 1-DFAα1 (Detrending Fluctuation Analysis score) at rest were both moderate and significantly (p < 0.05) related to FATox (r = 0.43, r = -0.40) and CHOox (r = -0.59, r = 0.41), as well as RER (r = -0.43, r = 0.43) at FATmax intensity. At the MCO intensity, no association was observed between HRV and oxidation rates. However, DFAα1 (r = -0.63, p < 0.05), the frequency ratio LF/HF (r = -0.63, p < 0.05), and the Poincaré ratio SD1/SD2 (r = 0.48, p < 0.05) were correlated with blood lactate concentration.

CONCLUSION

These results support the autonomic resources hypothesis, suggesting that better autonomic function at rest is related to enhanced metabolic flexibility in postmenopausal women. They also underpin a comprehensive analysis of cardiovascular-autonomic health with aging. The results imply that non-linear DFAα1 and SampEn are appropriate to analyze this association in health of the aging cardiovascular-autonomic system.

A Unified Framework for Investigating Aperiodic and Periodic Components in the Hearbeat Dynamics Spectrum: a Feasibility Study

Heart Rate Variability (HRV) series is a widely used, non-invasive, and easy-to-acquire time-resolved signal for evaluating autonomic control on cardiovascular activity. Despite the recognition that heartbeat dynamics contains both periodic and aperiodic components, the majority of HRV modeling studies concentrate on only one component. On the one hand, there are models based on self-similarity and 1/f behavior that focus on the aperiodic component; on the other hand, there is the conventional division of the spectral domain into narrow-band oscillations, which considers HRV as a combination of periodic components. Taking inspiration from a recent parametrization of EEG power spectra, here we evaluate the applicability of a unified modeling framework to quantitatively assess heartbeat dynamics spectra as a mixture of aperiodic and periodic components. The proposed model is applied on publicly-available, real HRV series collected during postural changes from 10 healthy subjects. Results show that the proposed modeling effectively characterizes different experimental conditions and may complement HRV standard analysis defined in the frequency domain.

Comprehensive evaluation of machine learning algorithms for predicting sleep-wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability

Introduction

Perinatal women tend to have difficulties with sleep along with autonomic characteristics. This study aimed to identify a machine learning algorithm capable of achieving high accuracy in predicting sleep-wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability (HRV).

Methods

Nine HRV indicators (features) and sleep-wake conditions of 154 pregnant women were measured for 1 week, from the 23rd to the 32nd weeks of pregnancy. Ten machine learning and three deep learning methods were applied to predict three types of sleep-wake conditions (wake, shallow sleep, and deep sleep). In addition, the prediction of four conditions, in which the wake conditions before and after sleep were differentiated-shallow sleep, deep sleep, and the two types of wake conditions-was also tested.

Results and Discussion

In the test for predicting three types of sleep-wake conditions, most of the algorithms, except for Naïve Bayes, showed higher areas under the curve (AUCs; 0.82-0.88) and accuracy (0.78-0.81). The test using four types of sleep-wake conditions with differentiation between the wake conditions before and after sleep also resulted in successful prediction by the gated recurrent unit with the highest AUC (0.86) and accuracy (0.79). Among the nine features, seven made major contributions to predicting sleep-wake conditions. Among the seven features, "the number of interval differences of successive RR intervals greater than 50 ms (NN50)" and "the proportion dividing NN50 by the total number of RR intervals (pNN50)" were useful to predict sleep-wake conditions unique to pregnancy. These findings suggest alterations in the vagal tone system specific to pregnancy.

Fetal Health Classification from Cardiotocograph for Both Stages of Labor-A Soft-Computing-Based Approach

To date, cardiotocography (CTG) is the only non-invasive and cost-effective tool available for continuous monitoring of the fetal health. In spite of a marked growth in the automation of the CTG analysis, it still remains a challenging signal processing task. Complex and dynamic patterns of fetal heart are poorly interpreted. Particularly, the precise interpretation of the suspected cases is fairly low by both visual and automated methods. Also, the first and second stage of labor produce very different fetal heart rate (FHR) dynamics. Thus, a robust classification model takes both stages into consideration separately. In this work, the authors propose a machine-learning-based model, which was applied separately to both the stages of labor, using standard classifiers such as SVM, random forest (RF), multi-layer perceptron (MLP), and bagging to classify the CTG. The outcome was validated using the model performance measure, combined performance measure, and the ROC-AUC. Though AUC-ROC was sufficiently high for all the classifiers, the other parameters established a better performance by SVM and RF. For suspicious cases the accuracies of SVM and RF were 97.4% and 98%, respectively, whereas sensitivity was 96.4% and specificity was 98% approximately. In the second stage of labor the accuracies were 90.6% and 89.3% for SVM and RF, respectively. Limits of agreement for 95% between the manual annotation and the outcome of SVM and RF were (-0.05 to 0.01) and (-0.03 to 0.02). Henceforth, the proposed classification model is efficient and can be integrated into the automated decision support system.

Drowsiness detection from polysomnographic data using multivariate selfsimilarity and eigen-wavelet analysis

Because drowsiness is a major cause in vehicle accidents, its automated detection is critical. Scale-free temporal dynamics is known to be typical of physiological and body rhythms. The present work quantifies the benefits of applying a recent and original multivariate selfsimilarity analysis to several modalities of polysomnographic measurements (heart rate, blood pressure, electroencephalogram and respiration), from the MIT-BIH Polysomnographic Database, to better classify drowsiness-related sleep stages. Clinical relevance- This study shows that probing jointly temporal dynamics amongst polysomnographic measurements, with a proposed original multivariate multiscale approach, yields a gain of above 5% in the Area-under-Curve quanti-fying drowsiness-related sleep stage classification performance compared to univariate analysis.

Machine Learning Algorithm to Predict Acidemia Using Electronic Fetal Monitoring Recording Parameters

Background: Electronic fetal monitoring (EFM) is the universal method for the surveillance of fetal well-being in intrapartum. Our objective was to predict acidemia from fetal heart signal features using machine learning algorithms. Methods: A case–control 1:2 study was carried out compromising 378 infants, born in the Miguel Servet University Hospital, Spain. Neonatal acidemia was defined as pH < 7.10. Using EFM recording logistic regression, random forest and neural networks models were built to predict acidemia. Validation of models was performed by means of discrimination, calibration, and clinical utility. Results: Best performance was attained using a random forest model built with 100 trees. The discrimination ability was good, with an area under the Receiver Operating Characteristic curve (AUC) of 0.865. The calibration showed a slight overestimation of acidemia occurrence for probabilities above 0.4. The clinical utility showed that for 33% cutoff point, missing 5% of acidotic cases, 46% of unnecessary cesarean sections could be prevented. Logistic regression and neural networks showed similar discrimination ability but with worse calibration and clinical utility. Conclusions: The combination of the variables extracted from EFM recording provided a predictive model of acidemia that showed good accuracy and provides a practical tool to prevent unnecessary cesarean sections.

Non-linear Methods Predominant in Fetal Heart Rate Analysis: A Systematic Review

The analysis of fetal heart rate variability has served as a scientific and diagnostic tool to quantify cardiac activity fluctuations, being good indicators of fetal well-being. Many mathematical analyses were proposed to evaluate fetal heart rate variability. We focused on non-linear analysis based on concepts of chaos, fractality, and complexity: entropies, compression, fractal analysis, and wavelets. These methods have been successfully applied in the signal processing phase and increase knowledge about cardiovascular dynamics in healthy and pathological fetuses. This review summarizes those methods and investigates how non-linear measures are related to each paper's research objectives. Of the 388 articles obtained in the PubMed/Medline database and of the 421 articles in the Web of Science database, 270 articles were included in the review after all exclusion criteria were applied. While approximate entropy is the most used method in classification papers, in signal processing, the most used non-linear method was Daubechies wavelets. The top five primary research objectives covered by the selected papers were detection of signal processing, hypoxia, maturation or gestational age, intrauterine growth restriction, and fetal distress. This review shows that non-linear indices can be used to assess numerous prenatal conditions. However, they are not yet applied in clinical practice due to some critical concerns. Some studies show that the combination of several linear and non-linear indices would be ideal for improving the analysis of the fetus's well-being. Future studies should narrow the research question so a meta-analysis could be performed, probing the indices' performance.

Challenges of Developing Robust AI for Intrapartum Fetal Heart Rate Monitoring

Background: CTG remains the only non-invasive tool available to the maternity team for continuous monitoring of fetal well-being during labour. Despite widespread use and investment in staff training, difficulty with CTG interpretation continues to be identified as a problem in cases of fetal hypoxia, which often results in permanent brain injury. Given the recent advances in AI, it is hoped that its application to CTG will offer a better, less subjective and more reliable method of CTG interpretation. Objectives: This mini-review examines the literature and discusses the impediments to the success of AI application to CTG thus far. Prior randomised control trials (RCTs) of CTG decision support systems are reviewed from technical and clinical perspectives. A selection of novel engineering approaches, not yet validated in RCTs, are also reviewed. The review presents the key challenges that need to be addressed in order to develop a robust AI tool to identify fetal distress in a timely manner so that appropriate intervention can be made. Results: The decision support systems used in three RCTs were reviewed, summarising the algorithms, the outcomes of the trials and the limitations. Preliminary work suggests that the inclusion of clinical data can improve the performance of AI-assisted CTG. Combined with newer approaches to the classification of traces, this offers promise for rewarding future development.

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.

Autonomous nervous system regulation of pain in children with cerebral palsy

Aim: Children with cerebral palsy (CP) have increased pain sensitivity and recurrent pain episodes; however, pain is underreported in children with intellectual impairment. Cardiac autonomic regulation is imbalanced in chronic pain conditions and neurological disorders. This study aims at exploring the autonomous nervous system regulation of pain in children with CP compared with typically developing peers (TDP).Method: Heart rate variability (HRV) was recorded during 24 hours in 26 children with CP and 26 TDP, and examined offline at baseline (sleeping, seated rest) and during spontaneous pain events. Pain and fatigue, HRV indices (linear indices on time - IBI, SDNN, RMSSD - and frequency domains - high, low, and very low frequency - and non-linear indices - Hurst coefficient and multiscale entropy) were computed.Results: Children with CP showed comparable HRV during daily conditions and similar reductions after pain events than their TDP, regardless of their level of intellectual impairment. Interpretation: Children with CP have an intact autonomic regulation in acute pain events. HRV could be an accurate pain biomarker in children with CP and intellectual disability.What this paper adds: Autonomic regulation in acute pain is efficient in children with cerebral palsy.Heart rate variability indices can be reliable pain biomarkers in intellectual impairment.

Cardiotocography signal abnormality classification using time-frequency features and Ensemble Cost-sensitive SVM classifier

BACKGROUND

Cardiotocography (CTG) signal abnormality classification plays an important role in the diagnosis of abnormal fetuses. This classification problem is made difficult by the non-stationary nature of CTG and the dataset imbalance. This paper introduces a novel application of Time-frequency (TF) features and Ensemble Cost-sensitive Support Vector Machine (ECSVM) classifier to tackle these problems.

METHODS

Firstly, CTG signals are converted into TF-domain representations by Continuous Wavelet Transform (CWT), Wavelet Coherence (WTC), and Cross-wavelet Transform (XWT). From these representations, a novel image descriptor is used to extract the TF features. Then, the linear feature is derived from the time-domain representation of the CTG signal. The linear and TF features are fed to the ECSVM classifier for prediction and classification of fetal outcome.

RESULTS

The TF features show the significant difference (p-value<0.05) in distinguishing abnormal CTG signals, but not for traditional nonlinear features. In ECSVM abnormality classification, using only linear features, the sensitivity, specificity, and quality index are 59.3%, 78.3%, and 68.1%, respectively, whereas more effective results (sensitivity: 85.2%, specificity: 66.1%, and quality index: 75.0%) are obtained using a combination of linear and TF features, with a performance improvement index of 10.1%. Especially, the area under the receiver operating characteristic curve (0.77 vs. 0.64) is significantly increased with the ECSVM vs. SVM.

CONCLUSION

Our method can greatly improve the classification results, especially for sensitivity. It improves the true positive rate of CTG abnormality classification and reduces the false positive rate, which may help detect and treat abnormal fetuses during labor.

Maturation of the Autonomic Nervous System in Premature Infants: Estimating Development Based on Heart-Rate Variability Analysis

This study aims at investigating the development of premature infants' autonomic nervous system (ANS) based on a quantitative analysis of the heart-rate variability (HRV) with a variety of novel features. Additionally, the role of heart-rate drops, known as bradycardias, has been studied in relation to both clinical and novel sympathovagal indices. ECG data were measured for at least 3 h in 25 preterm infants (gestational age ≤32 weeks) for a total number of 74 recordings. The post-menstrual age (PMA) of each patient was estimated from the RR interval time-series by means of multivariate linear-mixed effects regression. The tachograms were segmented based on bradycardias in periods after, between and during bradycardias. For each of those epochs, a set of temporal, spectral and fractal indices were included in the regression model. The best performing model has R 2 = 0.75 and mean absolute error MAE = 1.56 weeks. Three main novelties can be reported. First, the obtained maturation models based on HRV have comparable performance to other development models. Second, the selected features for age estimation show a predominance of power and fractal features in the very-low- and low-frequency bands in explaining the infants' sympathovagal development from 27 PMA weeks until 40 PMA weeks. Third, bradycardias might disrupt the relationship between common temporal indices of the tachogram and the age of the infant and the interpretation of sympathovagal indices. This approach might provide a novel overview of post-natal autonomic maturation and an alternative development index to other electrophysiological data analysis.

Heart Rate Information-Based Machine Learning Prediction of Emotions Among Pregnant Women

In this study, the extent to which different emotions of pregnant women can be predicted based on heart rate-relevant information as indicators of autonomic nervous system functioning was explored using various machine learning algorithms. Nine heart rate-relevant autonomic system indicators, including the coefficient of variation R-R interval (CVRR), standard deviation of all NN intervals (SDNN), and square root of the mean squared differences of successive NN intervals (RMSSD), were measured using a heart rate monitor (MyBeat) and four different emotions including "happy," as a positive emotion and "anxiety," "sad," "frustrated," as negative emotions were self-recorded on a smartphone application, during 1 week starting from 23rd to 32nd weeks of pregnancy from 85 pregnant women. The k-nearest neighbor (k-NN), support vector machine (SVM), logistic regression (LR), random forest (RF), naïve bayes (NB), decision tree (DT), gradient boosting trees (GBT), stochastic gradient descent (SGD), extreme gradient boosting (XGBoost), and artificial neural network (ANN) machine learning methods were applied to predict the four different emotions based on the heart rate-relevant information. To predict four different emotions, RF also showed a modest area under the receiver operating characteristic curve (AUC-ROC) of 0.70. CVRR, RMSSD, SDNN, high frequency (HF), and low frequency (LF) mostly contributed to the predictions. GBT displayed the second highest AUC (0.69). Comprehensive analyses revealed the benefits of the prediction accuracy of the RF and GBT methods and were beneficial to establish models to predict emotions based on autonomic nervous system indicators. The results implicated SDNN, RMSSD, CVRR, LF, and HF as important parameters for the predictions.

Systematic Review of Intrapartum Fetal Heart Rate Spectral Analysis and an Application in the Detection of Fetal Acidemia

It is fundamental to diagnose fetal acidemia as early as possible, allowing adequate obstetrical interventions to prevent brain damage or perinatal death. The visual analysis of cardiotocography traces has been complemented by computerized methods in order to overcome some of its limitations in the screening of fetal hypoxia/acidemia. Spectral analysis has been proposed by several studies exploring fetal heart rate recordings while referring to a great variety of frequency bands for integrating the power spectrum. In this paper, the main goal was to systematically review the spectral bands reported in intrapartum fetal heart rate studies and to evaluate their performance in detecting fetal acidemia/hypoxia. A total of 176 articles were reviewed, from MEDLINE, and 26 were included for the extraction of frequency bands and other relevant methodological information. An open-access fetal heart rate database was used, with recordings of the last half an hour of labor of 246 fetuses. Four different umbilical artery pH cutoffs were considered for fetuses' classification into acidemic or non-acidemic: 7.05, 7.10, 7.15, and 7.20. The area under the receiver operating characteristic curve (AUROC) was used to quantify the frequency bands' ability to distinguish acidemic fetuses. Bands referring to low frequencies, mainly associated with neural sympathetic activity, were the best at detecting acidemic fetuses, with the more severe definition (pH ≤ 7.05) attaining the highest values for the AUROC. This study shows that the power spectrum analysis of the fetal heart rate is a simple and powerful tool that may become an adjunctive method to CTG, helping healthcare professionals to accurately identify fetuses at risk of intrapartum hypoxia and to implement timely obstetrical interventions to reduce the incidence of related adverse perinatal outcomes.

A perinatal stress calculator for the neonatal intensive care unit: an unobtrusive approach

OBJECTIVE

Early experience of pain and stress in the neonatal intensive care unit is known to have an effect on the neurodevelopment of the infant. However, an automated method to quantify the procedural pain or perinatal stress in premature patients does not exist.

APPROACH

In the current study, EEG and ECG data were collected for more than 3 hours from 136 patients in order to quantify stress exposure. Specifically, features extracted from the EEG and heart-rate variability in both quiet and non-quiet sleep segments were used to develop a subspace linear-discriminant analysis stress classifier.

MAIN RESULTS

The main novelty of the study lies in the absence of intrusive methods or pain elicitation protocols to develop the stress classifier. Three main findings can be reported. First, we developed different stress classifiers for the different age groups and stress intensities, obtaining an area under the curve in the range [0.78-0.93] for non-quiet sleep and [0.77-0.96] for quiet sleep. Second, a dysmature EEG was found in patients under stress. Third, an enhanced cortical connectivity and increased brain-heart communication was correlated with a higher stress load, while the autonomic activity did not seem to be associated to stress exposure.

SIGNIFICANCE

The results shed a light on the pain and stress processing in preterm neonates, suggesting that software tools to investigate dysmature EEG might be helpful to assess stress load in premature patients. These results could be the foundation to assess the impact of stress on infants' development and to tune preventive care.

A Bradycardia-Based Stress Calculator for the Neonatal Intensive Care Unit: A Multisystem Approach

Early life stress in the neonatal intensive care unit (NICU) can predispose premature infants to adverse health outcomes and neurodevelopment delays. Hands-on-care and procedural pain might induce apneas, hypoxic events, and sleep-wake disturbances, which can ultimately impact maturation, but a data-driven method based on physiological fingerprints to quantify early-life stress does not exist. This study aims to provide an automatic stress detector by investigating the relationship between bradycardias, hypoxic events and perinatal stress in NICU patients. EEG, ECG, and SpO 2 were recorded from 136 patients for at least 3 h in three different monitoring groups. In these subjects, the stress burden was assessed using the Leuven Pain Scale. Different subspace linear discriminant analysis models were designed to detect the presence or the absence of stress based on information in each bradycardic spell. The classification shows an area under the curve in the range [0.80-0.96] and a kappa score in the range [0.41-0.80]. The results suggest that stress seems to increase SpO 2 desaturations and EEG regularity as well as the interaction between the cardiovascular and neurological system. It might be possible that stress load enhances the reaction to respiratory abnormalities, which could ultimately impact the neurological and behavioral development.

Doppler Ultrasound Technology for Fetal Heart Rate Monitoring: A Review

Fetal well-being is commonly assessed by monitoring the fetal heart rate (fHR). In clinical practice, the de facto standard technology for fHR monitoring is based on the Doppler ultrasound (US). Continuous monitoring of the fHR before and during labor is performed using a US transducer fixed on the maternal abdomen. The continuous fHR monitoring, together with simultaneous monitoring of the uterine activity, is referred to as cardiotocography (CTG). In contrast, for intermittent measurements of the fHR, a handheld Doppler US transducer is typically used. In this article, the technology of Doppler US for continuous fHR monitoring and intermittent fHR measurements is described, with emphasis on fHR monitoring for CTG. Special attention is dedicated to the measurement environment, which includes the clinical setting in which fHR monitoring is commonly performed. In addition, to understand the signal content of acquired Doppler US signals, the anatomy and physiology of the fetal heart and the surrounding maternal abdomen are described. The challenges encountered in these measurements have led to different technological strategies, which are presented and critically discussed, with a focus on the US transducer geometry, Doppler signal processing, and fHR extraction methods.

DeepFHR: intelligent prediction of fetal Acidemia using fetal heart rate signals based on convolutional neural network

Background

Fetal heart rate (FHR) monitoring is a screening tool used by obstetricians to evaluate the fetal state. Because of the complexity and non-linearity, a visual interpretation of FHR signals using common guidelines usually results in significant subjective inter-observer and intra-observer variability. Objective: Therefore, computer aided diagnosis (CAD) systems based on advanced artificial intelligence (AI) technology have recently been developed to assist obstetricians in making objective medical decisions.

Methods

In this work, we present an 8-layer deep convolutional neural network (CNN) framework to automatically predict fetal acidemia. After signal preprocessing, the input 2-dimensional (2D) images are obtained using the continuous wavelet transform (CWT), which provides a better way to observe and capture the hidden characteristic information of the FHR signals in both the time and frequency domains. Unlike the conventional machine learning (ML) approaches, this work does not require the execution of complex feature engineering, i.e., feature extraction and selection. In fact, 2D CNN model can self-learn useful features from the input data with the prerequisite of not losing informative features, representing the tremendous advantage of deep learning (DL) over ML.

Results

Based on the test open-access database (CTU-UHB), after comprehensive experimentation, we achieved better classification performance using the optimal CNN configuration compared to other state-of-the-art methods: the averaged ten-fold cross-validation of the accuracy, sensitivity, specificity, quality index defined as the geometric mean of the sensitivity and specificity, and the area under the curve yielded results of 98.34, 98.22, 94.87, 96.53 and 97.82%, respectively

Conclusions

Once the proposed CNN model is successfully trained, the corresponding CAD system can be served as an effective tool to predict fetal asphyxia objectively and accurately.

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.

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

The second Signal Processing and Monitoring in Labor workshop gathered researchers who utilize promising new research strategies and initiatives to tackle the challenges of intrapartum fetal monitoring. The workshop included a series of lectures and discussions focusing on: new algorithms and techniques for cardiotocogoraphy (CTG) and electrocardiogram acquisition and analyses; the results of a CTG evaluation challenge comparing state-of-the-art computerized methods and visual interpretation for the detection of arterial cord pH <7.05 at birth; the lack of consensus about the role of intrapartum acidemia in the etiology of fetal brain injury; the differences between methods for CTG analysis "mimicking" expert clinicians and those derived from "data-driven" analyses; a critical review of the results from two randomized controlled trials testing the former in clinical practice; and relevant insights from modern physiology-based studies. We concluded that the automated algorithms performed comparably to each other and to clinical assessment of the CTG. However, the sensitivity and specificity urgently need to be improved (both computerized and visual assessment). Data-driven CTG evaluation requires further work with large multicenter datasets based on well-defined labor outcomes. And before first tests in the clinic, there are important lessons to be learnt from clinical trials that tested automated algorithms mimicking expert CTG interpretation. In addition, transabdominal fetal electrocardiogram monitoring provides reliable CTG traces and variability estimates; and fetal electrocardiogram waveform analysis is subject to promising new research. There is a clear need for close collaboration between computing and clinical experts. We believe that progress will be possible with multidisciplinary collaborative research.

A Strategy for Classification of "Vaginal vs. Cesarean Section" Delivery: Bivariate Empirical Mode Decomposition of Cardiotocographic Recordings

We propose objective and robust measures for the purpose of classification of "vaginal vs. cesarean section" delivery by investigating temporal dynamics and complex interactions between fetal heart rate (FHR) and maternal uterine contraction (UC) recordings from cardiotocographic (CTG) traces. Multivariate extension of empirical mode decomposition (EMD) yields intrinsic scales embedded in UC-FHR recordings while also retaining inter-channel (UC-FHR) coupling at multiple scales. The mode alignment property of EMD results in the matched signal decomposition, in terms of frequency content, which paves the way for the selection of robust and objective time-frequency features for the problem at hand. Specifically, instantaneous amplitude and instantaneous frequency of multivariate intrinsic mode functions are utilized to construct a class of features which capture nonlinear and nonstationary interactions from UC-FHR recordings. The proposed features are fed to a variety of modern machine learning classifiers (decision tree, support vector machine, AdaBoost) to delineate vaginal and cesarean dynamics. We evaluate the performance of different classifiers on a real world dataset by investigating the following classifying measures: sensitivity, specificity, area under the ROC curve (AUC) and mean squared error (MSE). It is observed that under the application of all proposed 40 features AdaBoost classifier provides the best accuracy of 91.8% sensitivity, 95.5% specificity, 98% AUC, and 5% MSE. To conclude, the utilization of all proposed time-frequency features as input to machine learning classifiers can benefit clinical obstetric practitioners through a robust and automatic approach for the classification of fetus dynamics.

Computer-Aided Diagnosis System of Fetal Hypoxia Incorporating Recurrence Plot With Convolutional Neural Network

Background: Electronic fetal monitoring (EFM) is widely applied as a routine diagnostic tool by clinicians using fetal heart rate (FHR) signals to prevent fetal hypoxia. However, visual interpretation of the FHR usually leads to significant inter-observer and intra-observer variability, and false positives become the main cause of unnecessary cesarean sections. Goal: The main aim of this study was to ensure a novel, consistent, robust, and effective model for fetal hypoxia detection. Methods: In this work, we proposed a novel computer-aided diagnosis (CAD) system integrated with an advanced deep learning (DL) algorithm. For a 1-dimensional preprocessed FHR signal, the 2-dimensional image was transformed using recurrence plot (RP), which is considered to greatly capture the non-linear characteristics. The ultimate image dataset was enriched by changing several parameters of the RP and was then used to feed the convolutional neural network (CNN). Compared to conventional machine learning (ML) methods, a CNN can self-learn useful features from the input data and does not perform complex manual feature engineering (i.e., feature extraction and selection). Results: Finally, according to the optimization experiment, the CNN model obtained the average performance using optimal configuration across 10-fold: accuracy = 98.69%, sensitivity = 99.29%, specificity = 98.10%, and area under the curve = 98.70%. Conclusion: To the best of our knowledge, this approached achieved better classification performance in predicting fetal hypoxia using FHR signals compared to the other state-of-the-art works. Significance: In summary, the satisfied result proved the effectiveness of our proposed CAD system for assisting obstetricians making objective and accurate medical decisions based on RP and powerful CNN algorithm.

Fetal Heart Rate Monitoring Implemented by Dynamic Adaptation of Transmission Power of a Flexible Ultrasound Transducer Array

Fetal heart rate (fHR) monitoring using Doppler Ultrasound (US) is a standard method to assess fetal health before and during labor. Typically, an US transducer is positioned on the maternal abdomen and directed towards the fetal heart. Due to fetal movement or displacement of the transducer, the relative fetal heart location (fHL) with respect to the US transducer can change, leading to frequent periods of signal loss. Consequently, frequent repositioning of the US transducer is required, which is a cumbersome task affecting clinical workflow. In this research, a new flexible US transducer array is proposed which allows for measuring the fHR independently of the fHL. In addition, a method for dynamic adaptation of the transmission power of this array is introduced with the aim of reducing the total acoustic dose transmitted to the fetus and the associated power consumption, which is an important requirement for application in an ambulatory setting. The method is evaluated using an in-vitro setup of a beating chicken heart. We demonstrate that the signal quality of the Doppler signal acquired with the proposed method is comparable to that of a standard, clinical US transducer. At the same time, our transducer array is able to measure the fHR for varying fHL while only using 50% of the total transmission power of standard, clinical US transducers.

Stress assessment by means of heart rate derived from functional near-infrared spectroscopy

Many studies have been carried out in order to detect and quantify the level of mental stress by means of different physiological signals. From the physiological point of view, stress promptly affects brain and cardiac function; therefore, stress can be assessed by analyzing the brain- and heart-related signals more efficiently. Signals produced by functional near-infrared spectroscopy (fNIRS) of the brain together with the heart rate (HR) are employed to assess the stress induced by the Montreal Imaging Stress Task. Two different versions of the HR are used in this study. The first one is the commonly used HR derived from the electrocardiogram (ECG) and is considered as the reference HR (RHR). The other is the HR computed from the fNIRS signal (EHR) by means of an effective combinational algorithm. fNIRS and ECG signals were simultaneously recorded from 10 volunteers, and EHR and RHR are derived from them, respectively. Our results showed a high degree of agreement [r  >  0.9, BAR (Bland Altman ratio) <5  %  ] between the two HR. A principal component analysis/support vector machine-based algorithm for stress classification is developed and applied to the three measurements of fNIRS, EHR, and RHR and a classification accuracy of 78.8%, 94.6%, and 62.2% were obtained for the three measurements, respectively. From these observations, it can be concluded that the EHR carries more useful information with regards to the mental stress than the RHR and fNIRS signals. Therefore, EHR can be used alone or in combination with the fNIRS signal for a more accurate and real-time stress detection and classification.

A Comprehensive Feature Analysis of the Fetal Heart Rate Signal for the Intelligent Assessment of Fetal State

Continuous monitoring of the fetal heart rate (FHR) signal has been widely used to allow obstetricians to obtain detailed physiological information about newborns. However, visual interpretation of FHR traces causes inter-observer and intra-observer variability. Therefore, this study proposed a novel computerized analysis software of the FHR signal (CAS-FHR), aimed at providing medical decision support. First, to the best of our knowledge, the software extracted the most comprehensive features (47) from different domains, including morphological, time, and frequency and nonlinear domains. Then, for the intelligent assessment of fetal state, three representative machine learning algorithms (decision tree (DT), support vector machine (SVM), and adaptive boosting (AdaBoost)) were chosen to execute the classification stage. To improve the performance, feature selection/dimensionality reduction methods (statistical test (ST), area under the curve (AUC), and principal component analysis (PCA)) were designed to determine informative features. Finally, the experimental results showed that AdaBoost had stronger classification ability, and the performance of the selected feature set using ST was better than that of the original dataset with accuracies of 92% and 89%, sensitivities of 92% and 89%, specificities of 90% and 88%, and F-measures of 95% and 92%, respectively. In summary, the results proved the effectiveness of our proposed approach involving the comprehensive analysis of the FHR signal for the intelligent prediction of fetal asphyxia accurately in clinical practice.

Wavelet p-Leader Non Gaussian Multiscale Expansions for Heart Rate Variability Analysis in Congestive Heart Failure Patients

OBJECTIVE

Numerous indices were devised for the statistical characterization of temporal dynamics of heart rate variability (HRV) with the aim to discriminate between healthy subjects and nonhealthy patients. Elaborating on the concepts of (multi)fractal and nonlinear analyses, the present contribution defines and studies formally novel non Gaussian multiscale representations.

METHODS

A methodological framework for non Gaussian multiscale representations constructed on wavelet p-leaders is developed, relying a priori neither on exact scale-free dynamics nor on predefined forms of departure from Gaussianity. Its versatility in quantifying the strength and nature of departure from Gaussian is analyzed theoretically and numerically. The ability of the representations to discriminate between healthy subjects and congestive heart failure (CHF) patients, and between survivors and nonsurvivor CHF patients, is assessed on a large cohort of 198 subjects.

RESULTS

The analysis leads to conclude that i) scale-free and multifractal dynamics are observed, both for healthy subjects and CHF patients, for time scales shorter than [Formula: see text]; ii) a circadian evolution of multifractal and non Gaussian properties of HRV is evidenced for healthy subjects, but not for CHF patients; iii) non Gaussian multiscale indices possess high discriminative abilities between survivor and nonsurvivor CHF patients, at specific time scales ([Formula: see text] and [Formula: see text]).

CONCLUSIONS

The non Gaussian multiscale representations provide evidence for the existence of short-term cascade-type multifractal mechanisms underlying HRV for both healthy and CHF subjects. A circadian evolution of this mechanism is only evidenced for the healthy group, suggesting an alteration of the sympathetic-parasympathetic balance for CHF patients.

SIGNIFICANCE

Results obtained for a large cohort of subjects suggest that the novel non Gaussian indices might robustly quantify crucial information for clinical risk stratification in CHF patients.

Correlation Analysis between Obstructive Sleep Apnea Syndrome (OSAS) and Heart Rate Variability

BACKGROUND

Heart rate variability (HRV) represents the sympathetic nervous system activity induced by apnea or hypopnea events among OSAS patients. However, few studies have been conducted to clarify the association between HRV parameters and polysomnography (PSG) diagnostic indices. In our study, we postulate that the prevalence of cardiac arrhythmias is associated with OSAS, and HRV parameters may be an effective method for OSAS screening.

METHODS

Overall, 168 participants had been collected from 2011 to 2016 in the Second Affiliated Hospital of Soochow University. By apnea-hypopnea index (AHI), patients were separated into three subsets: AHI < 5 as control group, 5≤AHI<30 as mild-moderate OSAS group and AHI≥30as severe OSAS group. HRV and PSG parameters were collected based on electrocardiography and polysomnography system. Correlation analyses between standard deviation of R-R intervals (SDNN), SDNN index, RMSSD, PNN50, low frequency (LF), high frequency (HF) and LF/HF ratio and the AHI, ODI and MI were performed by Spearman's correlation analysis.

RESULTS

Compared with control group (64.5%) or mild-moderate OSAS group (67.3%), the prevalence of arrhythmias was considerably greater in severe OSAS group (P<0.05). Moreover, we demonstrated that LF/HF was greater in two OSAS groups than the normal group.

CONCLUSION

Correlation analyses revealed a significant and positive relation between the LF/HF and AHI, ODI and MI in OSAS patients. Severe OSAS could be attributed to enhanced danger of incident arrhythmia. LF/HF ratio as a relevant feature may be an effective parameter for detecting OSAS.

Mutual information for intrapartum fetal heart rate analysis

The analysis of the temporal dynamics in intrapartum fetal heart rate (FHR), aiming at early detection of fetal acidosis, constitutes an intricate signal processing task, that continuously receives significant research efforts. Entropy and entropy rates, envisaged as measures of complexity, often computed via popular implementations referred to as Approximate Entropy (ApEn) or Sample Entropy (SampEn), have regularly been reported as significant features for intrapartum FHR analysis. The present contribution aims to show how mutual information enhances characterization of FHR temporal dynamics and improves fetal acidosis detection performance. To that end, mutual information is first connected to ApEn and SampEn both conceptually and with respect to estimation procedure. Second, mutual information, ApEn and SampEn are computed on a large (≃ 1000 subjects) and documented database of FHR data, collected in a French academic hospital. Reported results show that the use of mutual information permits to significantly outperform ApEn and SampEn for acidosis detection, during any stage of labor.

Advantages and problems of nonlinear methods applied to analyze physiological time signals: human balance control as an example

Physiological processes are regulated by nonlinear dynamical systems. Various nonlinear measures have frequently been used for characterizing the complexity of fractal time signals to detect system features that cannot be derived from linear analyses. We analysed human balance dynamics ranging from simple standing to balancing on one foot with closed eyes to study the inherent methodological problems when applying fractal dimension analysis to real-world signals. Higuchi dimension was used as an example. Choice of measurement and analysis parameters has a distinct influence on the computed dimension. Noise increases the fractional dimension which may be misinterpreted as a higher complexity of the signal. Publications without specifying the parameter setting, or without analysing the noise-sensitivity are not comparable to findings of others and therefore of limited scientific value.

The fractal heart - embracing mathematics in the cardiology clinic

For clinicians grappling with quantifying the complex spatial and temporal patterns of cardiac structure and function (such as myocardial trabeculae, coronary microvascular anatomy, tissue perfusion, myocyte histology, electrical conduction, heart rate, and blood-pressure variability), fractal analysis is a powerful, but still underused, mathematical tool. In this Perspectives article, we explain some fundamental principles of fractal geometry and place it in a familiar medical setting. We summarize studies in the cardiovascular sciences in which fractal methods have successfully been used to investigate disease mechanisms, and suggest potential future clinical roles in cardiac imaging and time series measurements. We believe that clinical researchers can deploy innovative fractal solutions to common cardiac problems that might ultimately translate into advancements for patient care.

Short-term pulse rate variability is better characterized by functional near-infrared spectroscopy than by photoplethysmography

Pulse rate variability (PRV) can be extracted from functional near-infrared spectroscopy (fNIRS) (PRV(NIRS)) and photoplethysmography (PPG) (PRV(PPG)) signals. The present study compared the accuracy of simultaneously acquired PRV(NIRS) and PRV(PPG), and evaluated their different characterizations of the sympathetic (SNS) and parasympathetic (PSNS) autonomous nervous system activity. Ten healthy subjects were recorded during resting-state (RS) and respiratory challenges in two temperature conditions, i.e., room temperature (23°C) and cold temperature (4°C). PRV(NIRS) was recorded based on fNIRS measurement on the head, whereas PRV(PPG) was determined based on PPG measured at the finger. Accuracy between PRV(NIRS) and PRV(PPG), as assessed by cross-covariance and cross-sample entropy, demonstrated a high degree of correlation (r > 0.9), which was significantly reduced by respiration and cold temperature. Characterization of SNS and PSNS using frequency-domain, time-domain, and nonlinear methods showed that PRV(NIRS) provided significantly better information on increasing PSNS activity in response to respiration and cold temperature than PRV(PPG). The findings show that PRV(NIRS) may outperform PRV(PPG) under conditions in which respiration and temperature changes are present, and may, therefore, be advantageous in research and clinical settings, especially if characterization of the autonomous nervous system is desired.

Sparse Support Vector Machine for Intrapartum Fetal Heart Rate Classification

Fetal heart rate (FHR) monitoring is routinely used in clinical practice to help obstetricians assess fetal health status during delivery. However, early detection of fetal acidosis that allows relevant decisions for operative delivery remains a challenging task, receiving considerable attention. This contribution promotes sparse support vector machine classification that permits to select a small number of relevant features and to achieve efficient fetal acidosis detection. A comprehensive set of features is used for FHR description, including enhanced and computerized clinical features, frequency domain, and scaling and multifractal features, all computed on a large (1288 subjects) and well-documented database. The individual performance obtained for each feature independently is discussed first. Then, it is shown that the automatic selection of a sparse subset of features achieves satisfactory classification performance (sensitivity 0.73 and specificity 0.75, outperforming clinical practice). The subset of selected features (average depth of decelerations MAD_dtrd, baseline level β₀ , and variability H) receives simple interpretation in clinical practice. Intrapartum fetal acidosis detection is improved in several respects: A comprehensive set of features combining clinical, spectral, and scale-free dynamics is used; an original multivariate classification targeting both sparse feature selection and high performance is devised; state-of-the-art performance is obtained on a much larger database than that generally studied with description of common pitfalls in supervised classification performance assessments.