Multicentric intelligent cardiotocography signal interpretation using deep semi-supervised domain adaptation via minimax entropy and domain invariance.

BACKGROUND AND OBJECTIVE: Obstetricians use Cardiotocography (CTG), which is the continuous recording of fetal heart rate and uterine contraction, to assess fetal health status. Deep learning models for intelligent fetal monitoring trained on extensively labeled and identically distributed CTG records have achieved excellent performance. However, creation of these training sets requires excessive time and specialist labor for the collection and annotation of CTG signals. Previous research has demonstrated that multicenter studies can improve model performance. However, models trained on cross-domain data may not generalize well to target domains due to variance in distribution among datasets. Hence, this paper conducted a multicenter study with Deep Semi-Supervised Domain Adaptation (DSSDA) for intelligent interpretation of antenatal CTG signals. This approach helps to align cross-domain distribution and transfer knowledge from a label-rich source domain to a label-scarce target domain. METHODS: We proposed a DSSDA framework that integrated Minimax Entropy and Domain Invariance (DSSDA-MMEDI) to reduce inter-domain gaps and thus achieve domain invariance. The networks were developed using GoogLeNet to extract features from CTG signals, with fully connected, softmax layers for classification. We designed a Dynamic Gradient-driven strategy based on Mutual Information (DGMI) to unify the losses from Minimax Entropy (MME), Domain Invariance (DI), and supervised cross-entropy during iterative learning. RESULTS: We validated our DSSDA model on two datasets collected from collaborating healthcare institutions and mobile terminals as the source and target domains, which contained 16,355 and 3,351 CTG signals, respectively. Compared to the results achieved with deep learning networks without DSSDA, DSSDA-MMEDI significantly improved sensitivity and F1-score by over 6%. DSSDA-MMEDI also outperformed other state-of-the-art DSSDA approaches for CTG signal interpretation. Ablation studies were performed to determine the unique contribution of each component in our DSSDA mechanism. CONCLUSIONS: The proposed DSSDA-MMEDI is feasible and effective for alignment of cross-domain data and automated interpretation of multicentric antenatal CTG signals with minimal annotation cost.

Implementation barriers and facilitators of Moyo foetal heart rate monitor during labour in public hospitals in Nepal.

BACKGROUND: Globally, every year, approximately 1 million foetal deaths take place during the intrapartum period, fetal heart monitoring (FHRM) and timely intervention can reduce these deaths. OBJECTIVE: This study evaluates the implementation barriers and facilitators of a device, Moyo for FHRM. METHODS: The study adopted a qualitative study design in four hospitals in Nepal where Moyo was implemented for HRM. The study participants were labour room nurses and convenience sampling was used to select them. A total of 20 interviews were done to reach the data saturation. The interview transcripts were translated to English, and qualitative content analysis using deductive approach was applied. RESULTS: Using the deductive approach, the data were organised into three categories i) changes in practice of FHRM, ii) barriers to implementing Moyo and iii) facilitators of implementing Moyo. Moyo improved adherence to intermittent FHRM as the device could handle higher caseloads compared to the previous devices. The implementation of Moyo was hindered by difficulty to organise training ondevice during non-working hours, technical issue of the device, nurse mistrust towards the device and previous experience of poor implementation to similar innovations. Facilitators for implementation included effective training on how to use Moyo, improvement in intrapartum foetal monitoring and improvement in staff morale, ease of using the device, Plan Do Study Act (PDSA) meetings to improve use of Moyo and supportive leadership. CONCLUSION: The change in FHRM practice suggests that the implementation of innovative solution such as Moyo was successful with adequate facilitation, supportive staff attitude and leadership.

Main findings: Before the Moyo implementation, foetal heart rate monitoring was sub-optimal in the hospitals, which changed after introduction of the device, as it helped early display of foetal heart rate in the monitor and supported communication with women during the labour and delivery.Added knowledge: Implementation of Moyo in low-resource setting requires an interdisciplinary approach with continuous support to health care providers on how to correctly read Moyo, maintenance of device and management of false reading.Global health impact for policy and action: The global efforts to accelerate reduce preventable intrapartum related neonatal death requires contextual understanding of clinical context for effective implementation of Moyo.

Machine learning on cardiotocography data to classify fetal outcomes: A scoping review.

INTRODUCTION: Uterine contractions during labour constrict maternal blood flow and oxygen delivery to the developing baby, causing transient hypoxia. While most babies are physiologically adapted to withstand such intrapartum hypoxia, those exposed to severe hypoxia or with poor physiological reserves may experience neurological injury or death during labour. Cardiotocography (CTG) monitoring was developed to identify babies at risk of hypoxia by detecting changes in fetal heart rate (FHR) patterns. CTG monitoring is in widespread use in intrapartum care for the detection of fetal hypoxia, but the clinical utility is limited by a relatively poor positive predictive value (PPV) of an abnormal CTG and significant inter and intra observer variability in CTG interpretation. Clinical risk and human factors may impact the quality of CTG interpretation. Misclassification of CTG traces may lead to both under-treatment (with the risk of fetal injury or death) or over-treatment (which may include unnecessary operative interventions that put both mother and baby at risk of complications). Machine learning (ML) has been applied to this problem since early 2000 and has shown potential to predict fetal hypoxia more accurately than visual interpretation of CTG alone. To consider how these tools might be translated for clinical practice, we conducted a review of ML techniques already applied to CTG classification and identified research gaps requiring investigation in order to progress towards clinical implementation. MATERIALS AND METHOD: We used identified keywords to search databases for relevant publications on PubMed, EMBASE and IEEE Xplore. We used Preferred Reporting Items for Systematic Review and Meta-Analysis for Scoping Reviews (PRISMA-ScR). Title, abstract and full text were screened according to the inclusion criteria. RESULTS: We included 36 studies that used signal processing and ML techniques to classify CTG. Most studies used an open-access CTG database and predominantly used fetal metabolic acidosis as the benchmark for hypoxia with varying pH levels. Various methods were used to process and extract CTG signals and several ML algorithms were used to classify CTG. We identified significant concerns over the practicality of using varying pH levels as the CTG classification benchmark. Furthermore, studies needed to be more generalised as most used the same database with a low number of subjects for an ML study. CONCLUSION: ML studies demonstrate potential in predicting fetal hypoxia from CTG. However, more diverse datasets, standardisation of hypoxia benchmarks and enhancement of algorithms and features are needed for future clinical implementation.

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.

Intrapartum cardiotocography with simultaneous maternal heart rate registration improves neonatal outcome.

BACKGROUND: Intrapartum cardiotocographic monitoring of fetal heart rate by abdominal external ultrasound transducer without simultaneous maternal heart rate recording has been associated with increased risk of early neonatal death and other asphyxia-related neonatal outcomes. It is unclear, however, whether this increase in risk is independently associated with fetal surveillance method or is attributable to other factors. OBJECTIVE: This study aimed to compare different fetal surveillance methods and their association with adverse short- and long-term fetal and neonatal outcomes in a large retrospective cohort of spontaneous term deliveries. STUDY DESIGN: Fetal heart rate and maternal heart rate patterns were recorded by cardiotocography during labor in spontaneous term singleton cephalic vaginal deliveries in the Hospital District of Helsinki and Uusimaa, Finland between October 1, 2005, and September 30, 2023. According to the method of cardiotocography monitoring at birth, the cohort was divided into the following 3 groups: women with ultrasound transducer, women with both ultrasound transducer and maternal heart rate transducer, and women with internal fetal scalp electrode. Umbilical artery pH and base excess values, low 1- and 5-minute Apgar scores, need for intubation and resuscitation, neonatal intensive care unit admission for asphyxia, neonatal encephalopathy, and early neonatal death were used as outcome variables. RESULTS: Among the 213,798 deliveries that met the inclusion criteria, the monitoring type was external ultrasound transducer in 81,559 (38.1%), both external ultrasound transducer and maternal heart rate recording in 62,268 (29.1%), and fetal scalp electrode in 69,971 (32.7%) cases, respectively. The rates of both neonatal encephalopathy (odds ratio, 1.48; 95% confidence interval, 1.08-2.02) and severe acidemia (umbilical artery pH <7.00 and/or umbilical artery base excess ≤-12.0 mmol/L) (odds ratio, 2.03; 95% confidence interval, 1.65-2.50) were higher in fetuses of women with ultrasound transducer alone compared with those of women with concurrent external fetal and maternal heart rate recording. Monitoring with ultrasound transducer alone was also associated with increased risk of neonatal intubation for resuscitation (odds ratio, 1.22; 95% confidence interval, 1.03-1.44). A greater risk of severe neonatal acidemia was observed both in the ultrasound transducer (odds ratio, 2.78; 95% confidence interval, 2.23-3.48) and concurrent ultrasound transducer and maternal heart rate recording (odds ratio, 1.37; 95% confidence interval, 1.05-1.78) groups compared with those monitored with fetal scalp electrodes. No difference in risk of neonatal encephalopathy was found between newborns monitored with concurrent ultrasound transducer and maternal heart rate recording and those monitored with fetal scalp electrodes. CONCLUSION: The use of external ultrasound transducer monitoring of fetal heart rate without simultaneous maternal heart rate recording is associated with higher rates of neonatal encephalopathy and severe neonatal acidemia. We suggest that either external fetal heart rate monitoring with concurrent maternal heart rate recording or internal fetal scalp electrode be used routinely as a fetal surveillance tool in term deliveries.

Evaluation and patient experience of wireless noninvasive fetal heart rate monitoring devices.

INTRODUCTION: In clinical practice, fetal heart rate monitoring is performed intermittently using Doppler ultrasound, typically for 30 minutes. In case of a non-reassuring heart rate pattern, monitoring is usually prolonged. Noninvasive fetal electrocardiography may be more suitable for prolonged monitoring due to improved patient comfort and signal quality. This study evaluates the performance and patient experience of four noninvasive electrocardiography devices to assess candidate devices for prolonged noninvasive fetal heart rate monitoring. MATERIAL AND METHODS: Non-critically sick women with a singleton pregnancy from 24 weeks of gestation were eligible for inclusion. Fetal heart rate monitoring was performed during standard care with a Doppler ultrasound device (Philips Avalon-FM30) alone or with this Doppler ultrasound device simultaneously with one of four noninvasive electrocardiography devices (Nemo Fetal Monitoring System, Philips Avalon-Beltless, Demcon Dipha-16 and Dräger Infinity-M300). Performance was evaluated by: success rate, positive percent agreement, bias, 95% limits of agreement, regression line, root mean square error and visual agreement using FIGO guidelines. Patient experience was captured using a self-made questionnaire. RESULTS: A total of 10 women were included per device. For fetal heart rate, Nemo performed best (success rate: 99.4%, positive percent agreement: 94.2%, root mean square error 5.1 BPM, bias: 0.5 BPM, 95% limits of agreement: -9.7 - 10.7 BPM, regression line: y = -0.1x + 11.1) and the cardiotocography tracings obtained simultaneously by Nemo and Avalon-FM30 received the same FIGO classification. Comparable results were found with the Avalon-Beltless from 36 weeks of gestation, whereas the Dipha-16 and Infinity-M300 performed significantly worse. The Avalon-Beltless, Nemo and Infinity-M300 closely matched the performance of the Avalon-FM30 for maternal heart rate, whereas the performance of the Dipha-16 deviated more. Patient experience scores were higher for the noninvasive electrocardiography devices. CONCLUSIONS: Both Nemo and Avalon-Beltless are suitable devices for (prolonged) noninvasive fetal heart rate monitoring, taking their intended use into account. But outside its intended use limit of 36 weeks' gestation, the Avalon-Beltless performs less well, comparable to the Dipha-16 and Infinity-M300, making them currently unsuitable for (prolonged) noninvasive fetal heart rate monitoring. Noninvasive electrocardiography devices appear to be preferred due to greater comfort and mobility.

Exploring the Influence of Fetal Sex on Heart Rate Dynamics Using Fetal Magnetocardiographic Recordings.

Fetal sex has been associated with different development trajectories that cause structural and functional differences between the sexes throughout gestation. Fetal magnetocardiography (fMCG) recordings from 123 participants (64 females and 59 males; one recording/participant) from a database consisting of low-risk pregnant women were analyzed to explore and compare fetal development trajectories of both sexes. The gestational age of the recordings ranged from 28 to 38 weeks. Linear metrics in both the time and frequency domains were applied to study fetal heart rate variability (fHRV) measures that reveal the dynamics of short- and long-term variability. Rates of linear change with GA in these metrics were analyzed using general linear model regressions with assessments for significantly different variances and GA regression slopes between the sexes. The fetal sexes were well balanced for GA and sleep state. None of the fHRV measures analyzed exhibited significant variance heterogeneity between the sexes, and none of them exhibited a significant sex-by-GA interaction. The absence of a statistically significant sex-by-GA interaction on all parameters resulted in none of the regression slope estimates being significantly different between the sexes. With high-precision fMCG recordings, we were able to explore the variation in fHRV parameters as it relates to fetal sex. The fMCG-based fHRV parameters did not show any significant difference in rates of change with gestational age between sexes. This study provides a framework for understanding normal development of the fetal autonomic nervous system, especially in the context of fetal sex.

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.

Is the fetus fit for labor? Introducing fast-and-frugal trees (FFTrees) to simplify triage of women for STAN monitoring: An interobserver agreement comparison with traditional classification.

INTRODUCTION: It is a shortcoming of traditional cardiotocography (CTG) classification table formats that CTG traces are frequently classified differently by different users, resulting in poor interobserver agreements. A fast-and-frugal tree (FFTree) flow chart may help provide better concordance because it is straightforward and has clearly structured binary questions with understandable "yes" or "no" responses. The initial triage to determine whether a fetus is suitable for labor when utilizing fetal ECG ST analysis (STAN) is very important, since a fetus with restricted capacity to respond to hypoxic stress may not generate STAN events and therefore may become falsely negative. This study aimed to compare physiology-focused FFTree CTG interpretation with FIGO classification for assessing the suitability for STAN monitoring. MATERIAL AND METHODS: A retrospective study of 36 CTG traces with a high proportion of adverse outcomes (17/36) selected from a European multicenter study database. Eight experienced European obstetricians evaluated the initial 40 minutes of the CTG recordings and judged whether STAN was a suitable fetal surveillance method and whether intervention was indicated. The experts rated the CTGs using the FFTree and FIGO classifications at least 6 weeks apart. Interobserver agreements were calculated using proportions of agreement and Fleiss' kappa (κ). RESULTS: The proportions of agreement for "not suitable for STAN" were for FIGO 47% (95% confidence interval [CI] 42%-52%) and for FFTree 60% (95% CI 56-64), ie a significant difference; the corresponding figures for "yes, suitable" were 74% (95% CI 71-77) and 70% (95% CI 67-74). For "intervention needed" the figures were 52% (95% CI 47-56) vs 58% (95% CI 54-62) and for "expectant management" 74% (95% CI 71-77) vs 72% (95% CI 69-75). Fleiss' κ agreement on "suitability for STAN" was 0.50 (95% CI 0.44-0.56) for the FIGO classification and 0.57 (95% CI 0.51-0.63) for the FFTree classification; the corresponding figures for "intervention or expectancy" were 0.53 (95% CI 0.47-0.59) and 0.57 (95% CI 0.51-0.63). CONCLUSIONS: The proportion of agreement among expert obstetricians using the FFTree physiological approach was significantly higher compared with the traditional FIGO classification system in rejecting cases not suitable for STAN monitoring. That might be of importance to avoid false negative STAN recordings. Other agreement figures were similar. It remains to be shown whether the FFTree simplicity will benefit less experienced users and how it will work in real-world clinical scenarios.

Re-evaluating fetal scalp pH thresholds: An examination of fetal pH variations during labor.

INTRODUCTION: Since the 1970s, fetal scalp blood sampling (FSBS) has been used as a second-line test of the acid-base status of the fetus to evaluate fetal well-being during labor. The commonly employed thresholds that delineate normal pH (>7.25), subnormal (7.20-7.25), and pathological pH (<7.20) guide clinical decisions. However, these experienced-based thresholds, based on observations and common sense, have yet to be confirmed. The aim of the study was to investigate if pH drop rate accelerates at the common thresholds (7.25 and 7.20) and to explore the possibility of identifying more accurate thresholds. MATERIAL AND METHODS: A retrospective study was conducted at a tertiary maternity hospital between June 2017 and July 2021. Patients with at least one FSBS during labor for category II fetal heart rate and delivery of a singleton cephalic infant were included. The rate of change in pH value between consecutive samples for each patient was calculated and plotted as a function of pH value. Linear regression models were used to model the evolution of the pH drop rate estimating slope and standard errors across predefined pH intervals. Exploration of alternative pH action thresholds was conducted. To explore the independence of the association between pH value and pH drop rate, multiple linear regression adjusted on age, body mass index, parity, oxytocin stimulation and suspected small for gestational age was performed. RESULTS: We included 2047 patients with at least one FSBS (total FSBS 3467); with 2047 umbilical cord blood pH, and a total of 5514 pH samples. Median pH values were 7.29 1 h before delivery, 7.26 30 min before delivery. The pH drop was slow between 7.40 and 7.30, then became more pronounced, with median rates of 0.0005 units/min at 7.25 and 0.0013 units/min at 7.20. Out of the alternative pH thresholds, 7.26 and 7.20 demonstrated the best alignment with our dataset. Multiple linear regression revealed that only pH value was significantly associated to the rate of pH change. CONCLUSIONS: Our study confirms the validity and reliability of current guideline thresholds for fetal scalp pH in category II fetal heart rate.

A wearable system to track vital signs communicated from the mother to the fetus.

BACKGROUND: The monitoring of fetal heart rate (FHR) before intrapartum has been crucial in modern obstetrics. FHR has been used for about 300 years to determine fetal status, leading to the development of monitoring devices to prevent fetal death during gestation. While medical devices like fetal electrocardiograms exist for disease detection, their size and cost limit individual use. OBJECTIVE: To address cardiovascular issues during pregnancy, a mobile system is developed to display heart rates and blood pressure on mobile devices. The system is generated from a medical device with Bluetooth communication, supplementing traditional monitoring. METHOD: The study focuses on creating a mobile system that connects to mobile operating systems, enhancing treatment, diagnosis, and patient monitoring. The mobile system displays cardiovascular data obtained from the medical device. RESULTS: The results are expected to have an immediate impact on cases where abnormal measurement parameters of the monitoring system occur during pregnancy. The use of mobile systems or applications on smartphones is seen as beneficial in distributing processing and census of embedded health systems. CONCLUSION: The study highlights the potential benefits of mobile systems in distributing processing for health systems, particularly in addressing cardiovascular problems during pregnancy. The creation of a mobile system for displaying cardiovascular data could significantly improve monitoring and early detection.

The significance of meeting Dawes-Redman criteria in computerised antenatal fetal heart rate assessment.

OBJECTIVE: To investigate the significance of not meeting Dawes-Redman criteria on computerised cardiotocography in high-risk pregnancies. DESIGN: Retrospective observational study. SETTING: UK university hospital. POPULATION: High-risk pregnancies undergoing antenatal assessment. METHODS: We interrogated the database for records of computerised fetal heart rate assessment and pregnancy outcomes. MAIN OUTCOME MEASURES: Neonatal outcome and stillbirths. RESULTS: Excluding duplicate assessment in the same pregnancy, 14 025 records with complete information on the criteria of normality having been met and the outcome of the pregnancy were available. Criteria were not met for 907 records (6.46%). The gestational age of assessment was lower in the group not meeting criteria of normality. Overall, 32 stillbirths occurred in normally formed fetuses (2.28/1000). Stillbirths were more frequent in the group not meeting criteria (odds ratio [OR] 8.78, 95% CI 4.28-18.02). This finding persisted even after records with abnormally low short-term variation (STV) were excluded. The confidence intervals around the rate of stillbirth in the two groups overlapped beyond an STV of 8 ms. CONCLUSIONS: Approximately 1:16 pregnancies do not meet the criteria of normality. The criteria are not met more often at preterm gestation than at term. The risk of stillbirth was higher in the group not meeting criteria of normality, even if cases with low STV are excluded. Cases not meeting criteria should be followed up closely, unless the STV is ≥8 ms. Stillbirths still occurred in the group meeting criteria, but the rate was lower than in the general population.

Evaluation of The Fetal Heart Rate Monitoring with The Non-Invasive Electrocardiography Signals.

Fetal heart rate monitoring is a crucial element in determining the health of the fetus during pregnancy. In this paper, we evaluate the fetal heart rate (FHR) and maternal heart rate (MHR) between our non-invasive fetal monitoring system, Femom, developed by a Biorithm and the Huntleigh computerized cardiotocography (cCTG) together with the Sonicaid FetalCare3 software by comparing the accuracy, sensitivity, and reliability through using Bland-Altman analysis, Positive Percent Agreement (PPA) and Intraclass Correlation Coefficient (ICC) respectively. Femom device is a part of the Femom system which collects abdominal electrocardiogram (aECG) signals. Femom sever then processes the collected signals to generate FHR and MHR using novel algorithms. We collected data from 285 pregnant participants who were at least of 28 weeks of gestational age. FHR accuracy consists of mean bias and limit-of-agreement (LoA). The FHR bias is 0.05 beat per minute (BPM) and LoA is [-8.7 8.8] with 95% confidence interval (95% CI) measured using Bland Altman analysis. The PPA of 90.9% reflects FHR sensitivity. Reliability is measured with absolute ICC and consistency ICC. The absolute ICC is of 88% and consistency ICC of 94%. For MHR evaluation, accuracy is measured using Bland Altman analysis which provided a bias of 0.35 BPM and LoA of [-7 6.2] with 95% CI. The MHR sensitivity calculated using PPA is 98% while the MHR reliability is with the absolute value of 99% and consistency ICC of 99%.

The Effect of Fetal Heart Rate Segment Selection on Deep Learning Models for Fetal Compromise Detection.

Monitoring the fetal heart rate (FHR) is common practice in obstetric care to assess the risk of fetal compromise. Unfortunately, human interpretation of FHR recordings is subject to inter-observer variability with high false positive rates. To improve the performance of fetal compromise detection, deep learning methods have been proposed to automatically interpret FHR recordings. However, existing deep learning methods typically analyse a fixed-length segment of the FHR recording after removing signal gaps, where the influence of this segment selection process has not been comprehensively assessed. In this work, we develop a novel input length invariant deep learning model to determine the effect of FHR segment selection for detecting fetal compromise. Using this model, we perform five times repeated five-fold cross-validation on an open-access database of 552 FHR recordings and assess model performance for FHR segment lengths between 15 and 60 minutes. We show that the performance after removing signal gaps improves with increasing segment length from 15 minutes (AUC = 0.50) to 60 minutes (AUC = 0.74). Additionally, we demonstrate that using FHR segments without removing signal gaps achieves superior performance across signal lengths from 15 minutes (AUC = 0.68) to 60 minutes (AUC = 0.76). These results show that future works should carefully consider FHR segment selection and that removing signal gaps might contribute to the loss of valuable information.

Prediction of fetal RR intervals from maternal factors using machine learning models.

Previous literature has highlighted the importance of maternal behavior during the prenatal period for the upbringing of healthy adults. During pregnancy, fetal health assessments are mainly carried out non-invasively by monitoring fetal growth and heart rate (HR) or RR interval (RRI). Despite this, research entailing prediction of fHRs from mHRs is scarce mainly due to the difficulty in non-invasive measurements of fetal electrocardiogram (fECG). Also, so far, it is unknown how mHRs are associated with fHR over the short term. In this study, we used two machine learning models, support vector regression (SVR) and random forest (RF), for predicting average fetal RRI (fRRI). The predicted fRRI values were compared with actual fRRI values calculated from non-invasive fECG. fRRI was predicted from 13 maternal features that consisted of age, weight, and non-invasive ECG-derived parameters that included HR variability (HRV) and R wave amplitude variability. 156 records were used for training the models and the results showed that the SVR model outperformed the RF model with a root mean square error (RMSE) of 29 ms and an average error percentage (< 5%). Correlation analysis between predicted and actual fRRI values showed that the Spearman coefficient for the SVR and RF models were 0.31 (P < 0.001) and 0.19 (P < 0.05), respectively. The SVR model was further used to predict fRRI of 14 subjects who were not included in the training. The latter prediction results showed that individual error percentages were (≤ 5%) except in 3 subjects. The results of this study show that maternal factors can be potentially used for the assessment of fetal well-being based on fetal HR or RRI.

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.

An Update of Our Understanding of Fetal Heart Rate Patterns in Health and Disease.

UNDERSTANDING FETAL HEART RATE PATTERNS THAT MAY PREDICT ANTENATAL AND INTRAPARTUM NEURAL INJURY: Christopher A. Lear, Jenny A. Westgate, Austin Ugwumadu, Jan G. Nijhuis, Peter R. Stone, Antoniya Georgieva, Tomoaki Ikeda, Guido Wassink , Laura Bennet , Alistair J. Gunn Seminars in Pediatric Neurology Volume 28, December 2018, Pages 3-16 Electronic fetal heart rate (FHR) monitoring is widely used to assess fetal well-being throughout pregnancy and labor. Both antenatal and intrapartum FHR monitoring are associated with a high negative predictive value and a very poor positive predictive value. This in part reflects the physiological resilience of the healthy fetus and the remarkable effectiveness of fetal adaptations to even severe challenges. In this way, the majority of "abnormal" FHR patterns in fact reflect a fetus' appropriate adaptive responses to adverse in utero conditions. Understanding the physiology of these adaptations, how they are reflected in the FHR trace and in what conditions they can fail is therefore critical to appreciating both the potential uses and limitations of electronic FHR monitoring.

Clinical efficacy and acceptability of remote fetal heart rate self-monitoring in Southern China.

BACKGROUND: Compared to traditional fetal heart rate monitoring (FHR) for the outpatients in clinic, remote FHR monitoring shows real-time assessment of fetal wellbeing at home. The clinical function of remote FHR monitoring in pregnant wome in outpatient is still unclear. OBJECTIVE: To explore the feasibility of remote FHR self-monitoring in singleton pregnant women from southern China. STUDY DESIGN: This prospective cohort study was conducted at one tertiary center in southern China. Pregnant women used a mobile cardiotocogram device to measure the FHR at least once a week until delivery in the remote group. For the control group, pregnant women underwent traditional FHR monitoring once a week in the outpatient clinic. The rate of cesarean section, risk of postpartum hemorrhage and adverse neonatal outcomes were compared between the two groups. All the pregnant women completed a questionnaire survey to evaluate their acquisition of remote FHR self-monitoring. RESULTS: Approximately 500 women were recruited in the remote FHR self-monitoring group (remote group), and 567 women were recruited in the traditional FHR monitoring group (control group). The women in the remote FHR monitoring group were more likely to be nulliparous (P < 0.001), more likely to have a higher education level (P < 0.001) and more likely to be at high risk (P = 0.003). There was no significant difference in the risk of cesarean section (P = 0.068) or postpartum hemorrhage (P = 0.836) between the two groups. No difference in fetal complications was observed across groups, with the exception of the incidence of NICU stays, which was higher in the remote group (12.0% vs. 8.3%, P = 0.044). The questionnaire survey showed that the interval time (P = 0.001) and cost (P = 0.010) of fetal heart rate monitoring were lower in the remote group. Regarding age, prepregnancy BMI, risk factors, education level, maternal risk and household income, senior high school (OR 2.86, 95% CI 1.67-4.90, P < 0.001), undergraduate (OR 2.96, 95% CI 1.73-5.06, P < 0.001), advanced maternal age (OR 1.42, 95% CI 1.07-1.89, P = 0.015) and high-risk pregnancy (OR 1.61, 95% CI 1.11-2.35, P = 0.013) were independent factors for pregnant women to choose remote fetal monitoring. Multiparty (OR 0.33, 95% CI 0.21-0.51, P < 0.001), full-time motherhood (OR 0.47, 95% CI 0.33-0.678, P < 0.001) and high household income (OR 0.67, 95% CI 0.50-0.88, P = 0.004) were negatively correlated with the choice of remote FHR self-monitoring. CONCLUSION: Remote FHR self-monitoring technology has a lower cost and shows potential clinical efficacy for the outpatient setting in southern China. This approach does not increase the risk of cesarean section or adverse neonatal outcomes. It is acceptable among nulliparous pregnant women with a high education level, high household income or high risk. Further research is needed to assess the impact of this technology on obstetric outcomes in different health settings.

Prevention of fetal brain injury in category II tracings.

INTRODUCTION: With category II fetal heart rate tracings, the preferred timing of interventions to prevent fetal hypoxic brain damage while limiting operative interventions remains unclear. We aimed to estimate fetal extracellular base deficit (BDecf ) during labor with category II tracings to quantify the timing of potential interventions to prevent severe fetal metabolic acidemia. MATERIAL AND METHODS: A longitudinal study was conducted using the database of the Recurrence Prevention Committee, Japan Obstetric Compensation System for Cerebral Palsy, including infants with severe cerebral palsy born at ≥34 weeks' gestation between 2009 and 2014. Cases included those presumed to have an intrapartum onset of hypoxic-ischemic insult based on the fetal heart rate pattern evolution from reassuring to an abnormal pattern during delivery, in association with category II tracings marked by recurrent decelerations and an umbilical arterial BDecf ≥ 12 mEq/L. BDecf changes during labor were estimated based on stages of labor and the frequency/severity of fetal heart rate decelerations using the algorithm of Ross and Gala. The times from the onset of recurrent decelerations to BDecf 8 and 12 mEq/L (Decels-to-BD8, Decels-to-BD12) and to delivery were determined. Cases were divided into two groups (rapid and slow progression) based upon the rate of progression of acidosis from onset of decelerations to BDecf 12 mEq/L, determined by a finite-mixture model. RESULTS: The median Decels-to-BD8 (28 vs. 144 min, p < 0.01) and Decels-to-BD12 (46 vs. 177 min, p < 0.01) times were significantly shorter in the rapid vs slow progression. In rapid progression cases, physicians' decisions to deliver the fetus occurred at ~BDecf 8 mEq/L, whereas the "decisions" did not occur until BDecf reached 12 mEq/L in slow progression cases. CONCLUSIONS: Fetal BDecf reached 12 mEq/L within 1 h of recurrent fetal heart rate decelerations in the rapid progression group and within 3 h in the slow progression group. These findings suggest that cases with category II tracings marked by recurrent decelerations (i.e., slow progression) may benefit from operative intervention if persisting for longer than 2 h. In contrast, cases with sudden bradycardia (i.e., rapid progression) represent a challenge to prevent severe acidosis and hypoxic brain injury due to the limited time opportunity for emergent delivery.

Double-sided asymmetric method for automated fetal heart rate baseline calculation.

The fetal heart rate (FHR) signal is used to assess the well-being of a fetus during labor. Manual interpretation of the FHR is subject to high inter- and intra-observer variability, leading to inconsistent clinical decision-making. The baseline of the FHR signal is crucial for its interpretation. An automated method for baseline determination may reduce interpretation variability. Based on this claim, we present the Auto-Regressed Double-Sided Improved Asymmetric Least Squares (ARDSIAsLS) method as a baseline calculation algorithm designed to imitate expert obstetrician baseline determination. As the FHR signal is prone to a high rate of missing data, a step of gap interpolation in a physiological manner was implemented in the algorithm. The baseline of the interpolated signal was determined using a weighted algorithm of two improved asymmetric least squares smoothing models and an improved symmetric least squares smoothing model. The algorithm was validated against a ground truth determined from annotations of six expert obstetricians. FHR baseline calculation performance of the ARDSIAsLS method yielded a mean absolute error of 2.54 bpm, a max absolute error of 5.22 bpm, and a root mean square error of 2.89 bpm. In a comparison between the algorithm and 11 previously published methods, the algorithm outperformed them all. Notably, the algorithm was non-inferior to expert annotations. Automating the baseline FHR determination process may help reduce practitioner discordance and aid decision-making in the delivery room.