Development and evaluation of an algorithm for computer analysis of maternal heart rate during labor

The Approach to Sensing the True Fetal Heart Rate for CTG Monitoring: An Evaluation of Effectiveness of Deep Learning with Doppler Ultrasound Signals

Cardiotocography (CTG) is widely used to assess fetal well-being. CTG is typically obtained using ultrasound and autocorrelation methods, which extract periodicity from the signal to calculate the heart rate. However, during labor, maternal vessel pulsations can be measured, resulting in the output of the maternal heart rate (MHR). Since the autocorrelation output is displayed as fetal heart rate (FHR), there is a risk that obstetricians may mistakenly evaluate the fetal condition based on MHR, potentially overlooking the necessity for medical intervention. This study proposes a method that utilizes Doppler ultrasound (DUS) signals and artificial intelligence (AI) to determine whether the heart rate obtained by autocorrelation is of fetal origin. We developed a system to simultaneously record DUS signals and CTG and obtained data from 425 cases. The midwife annotated the DUS signals by auditory differentiation, providing data for AI, which included 30,160 data points from the fetal heart and 2160 data points from the maternal vessel. Comparing the classification accuracy of the AI model and a simple mathematical method, the AI model achieved the best performance, with an area under the curve (AUC) of 0.98. Integrating this system into fetal monitoring could provide a new indicator for evaluating CTG quality.

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

Background

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

Material and methods

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

Results

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

Conclusion

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

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

OBJECTIVES

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

CONTENT

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

SUMMARY AND OUTLOOK

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

Prognostic model based on image-based time-frequency features and genetic algorithm for fetal hypoxia assessment

Cardiotocography (CTG) is applied routinely for fetal monitoring during the perinatal period to decrease the rates of neonatal mortality and morbidity as well as unnecessary interventions. The analysis of CTG traces has become an indispensable part of present clinical practices; however, it also has serious drawbacks, such as poor specificity and variability in its interpretation. The automated CTG analysis is seen as the most promising way to overcome these disadvantages. In this study, a novel prognostic model is proposed for predicting fetal hypoxia from CTG traces based on an innovative approach called image-based time-frequency (IBTF) analysis comprised of a combination of short time Fourier transform (STFT) and gray level co-occurrence matrix (GLCM). More specifically, from a graphical representation of the fetal heart rate (FHR) signal, the spectrogram is obtained by using STFT. The spectrogram images are converted into 8-bit grayscale images, and IBTF features such as contrast, correlation, energy, and homogeneity are utilized for identifying FHR signals. At the final stage of the analysis, different subsets of the feature space are applied as the input to the least square support vector machine (LS-SVM) classifier to determine the most informative subset. For this particular purpose, the genetic algorithm is employed. The prognostic model was performed on the open-access intrapartum CTU-UHB CTG database. The sensitivity and specificity obtained using only conventional features were 57.33% and 67.24%, respectively, whereas the most effective results were achieved using a combination of conventional and IBTF features, with a sensitivity of 63.45% and a specificity of 65.88%. Conclusively, this study provides a new promising approach for feature extraction of FHR signals. In addition, the experimental outcomes showed that IBTF features provided an increase in the classification accuracy.

Simultaneous monitoring of maternal and fetal heart rate variability during labor in relation with fetal gender

Male gender is considered a risk factor for several adverse perinatal outcomes. Fetal gender effect on fetal heart rate (FHR) has been subject of several studies with contradictory results. The importance of maternal heart rate (MHR) monitoring during labor has also been investigated, but less is known about the effect of fetal gender on MHR. The aim of this study is to simultaneously assess maternal and FHR variability during labor in relation with fetal gender. Simultaneous MHR and FHR recordings were obtained from 44 singleton term pregnancies during the last 2 hr of labor (H_1, H₂ ). Heart rate tracings were analyzed using linear (time- and frequency-domain) and nonlinear indices. Both linear and nonlinear components were considered in assessing FHR and MHR interaction, including cross-sample entropy (cross-SampEn). Mothers carrying male fetuses (n = 22) had significantly higher values for linear indices related with MHR average and variability and sympatho-vagal balance, while the opposite occurred in the high-frequency component and most nonlinear indices. Significant differences in FHR were only observed in H₁ with higher entropy values in female fetuses. Assessing the differences between FHR and MHR, statistically significant differences were obtained in most nonlinear indices between genders. A significantly higher cross-SampEn was observed in mothers carrying female fetuses (n = 22), denoting lower synchrony or similarity between MHR and FHR. The variability of MHR and the synchrony/similarity between MHR and FHR vary with respect to fetal gender during labor. These findings suggest that fetal gender needs to be taken into account when simultaneously monitoring MHR and FHR.

Classification of caesarean section and normal vaginal deliveries using foetal heart rate signals and advanced machine learning algorithms

BACKGROUND

Visual inspection of cardiotocography traces by obstetricians and midwives is the gold standard for monitoring the wellbeing of the foetus during antenatal care. However, inter- and intra-observer variability is high with only a 30% positive predictive value for the classification of pathological outcomes. This has a significant negative impact on the perinatal foetus and often results in cardio-pulmonary arrest, brain and vital organ damage, cerebral palsy, hearing, visual and cognitive defects and in severe cases, death. This paper shows that using machine learning and foetal heart rate signals provides direct information about the foetal state and helps to filter the subjective opinions of medical practitioners when used as a decision support tool. The primary aim is to provide a proof-of-concept that demonstrates how machine learning can be used to objectively determine when medical intervention, such as caesarean section, is required and help avoid preventable perinatal deaths.

METHODS

This is evidenced using an open dataset that comprises 506 controls (normal virginal deliveries) and 46 cases (caesarean due to pH ≤ 7.20-acidosis, n = 18; pH > 7.20 and pH < 7.25-foetal deterioration, n = 4; or clinical decision without evidence of pathological outcome measures, n = 24). Several machine-learning algorithms are trained, and validated, using binary classifier performance measures.

RESULTS

The findings show that deep learning classification achieves sensitivity = 94%, specificity = 91%, Area under the curve = 99%, F-score = 100%, and mean square error = 1%.

CONCLUSIONS

The results demonstrate that machine learning significantly improves the efficiency for the detection of caesarean section and normal vaginal deliveries using foetal heart rate signals compared with obstetrician and midwife predictions and systems reported in previous studies.

Electrocardiography versus photoplethysmography in assessment of maternal heart rate variability during labor

Purpose

Evaluation of maternal heart rate (MHR) variability provides useful information on the maternal-fetal clinical state. Electrocardiography (ECG) is the most accurate method to monitor MHR but it may not always be available, and pulse oximetry using photoplethysmography (PPG) can be an alternative. In this study we compared ECG and PPG signals, obtained with conventional fetal monitors, to evaluate signal loss, MHR variability indices, and the ability of the latter to predict fetal acidemia and operative delivery.

Methods

Both signals were simultaneously acquired in 51 term pregnancies during the last 2 h of labor (H₁ and H₂). Linear time- and frequency-domain, and nonlinear MHR variability indices were estimated, and the dataset was divided into normal and acidemic cases, as well as into normal and operative deliveries. Differences between ECG and PPG signals were assessed using non-parametric confidence intervals, hypothesis testing, correlation coefficient and a measure of disagreement. Prediction of fetal acidemia and operative delivery was assessed using areas under the receiver operating characteristic curve (auROC).

Results

Signal loss was higher with ECG during the first segments of H₁, and higher with PPG in the last segment of H₂, and it increased in both signals with labour progression. MHR variability indices were significantly different when acquired with ECG and PPG signals, with low correlation coefficients and high disagreement for entropy and fast oscillation-based indices, and low disagreement for the mean MHR and slow oscillation-based indices. However, both acquisition modes evidenced significant differences between H₁ and H₂ and comparable auROC values were obtained in the detection of fetal acidemia and operative vaginal delivery.

Conclusion

Although PPG captures the faster oscillations of the MHR signal less well than ECG and is prone to have higher signal loss in the last 10-min preceding delivery, it can be considered an alternative for MHR monitoring during labor, with adaptation of cut-off values for MHR variability indices.

Computerized analysis of fetal heart rate variability signal during the stages of labor

AIM

To analyze computerized cardiotocographic (cCTG) parameters (baseline fetal heart rate, baseline FHR; short term variability, STV; approximate entropy, ApEn; low frequency, LF; movement frequency, MF; high frequency, HF) in physiological pregnancy in order to correlate them with the stages of labor. This could provide more information for understanding the mechanisms of nervous system control of FHR during labor progression.

METHODS

A total of 534 pregnant women were monitored on cCTG from the 37th week before the onset of spontaneous labor and during the first and the second stage of labor. Statistical analysis was performed using Kruskal-Wallis test and Wilcoxon rank-sum test with the Bonferroni adjusted α (< 0.05).

RESULTS

Statistically significant differences were seen between baseline FHR, MF and HF (P < 0.001), in which the first two were reduced and the third was increased when compared between pre-labor, and the first and second stages of labor. Differences between some of the stages were found for ApEn, LF and for LF/(HF + MF), where the first and the third were reduced and the second was increased.

CONCLUSIONS

cCTG modifications during labor may reflect the physiologic increased activation of the autonomous nervous system. Using computerized fetal heart rate analysis during labor it may be possible to obtain more information from the fetal cardiac signal, in comparison with the traditional tracing.

Improvements in fetal heart rate analysis by the removal of maternal-fetal heart rate ambiguities

Background

Misinterpretation of the maternal heart rate (MHR) as fetal may lead to significant errors in fetal heart rate (FHR) interpretation. In this study we hypothesized that the removal of these MHR-FHR ambiguities would improve FHR analysis during the final hour of labor.

Methods

Sixty-one MHR and FHR recordings were simultaneously acquired in the final hour of labor. Removal of MHR-FHR ambiguities was performed by subtracting MHR signals from their FHR counterparts when the absolute difference between the two was less or equal to 5 beats per minute. Major MHR-FHR ambiguities were defined when they exceeded 1 % of the tracing. Maternal, fetal and neonatal characteristics were evaluated in cases where major MHR-FHR ambiguities occurred and computer analysis of FHR recordings was compared, before and after removal of the ambiguities.

Results

Seventy-two percent of tracings (44/61) exhibited episodes of major MHR-FHR ambiguities, which were not significantly associated with any maternal, fetal or neonatal characteristics, but were associated with MHR accelerations, FHR signal loss and decelerations. Removal of MHR-FHR ambiguities resulted in a significant decrease in FHR decelerations, and improvement in FHR tracing classification.

Conclusions

FHR interpretation during the final hour of labor can be significantly improved by the removal of MHR-FHR ambiguities.

Toward the improvement in fetal monitoring during labor with the inclusion of maternal heart rate analysis

Fetal heart rate (FHR) monitoring is used routinely in labor, but conventional methods have a limited capacity to detect fetal hypoxia/acidosis. An exploratory study was performed on the simultaneous assessment of maternal heart rate (MHR) and FHR variability, to evaluate their evolution during labor and their capacity to detect newborn acidemia. MHR and FHR were simultaneously recorded in 51 singleton term pregnancies during the last two hours of labor and compared with newborn umbilical artery blood (UAB) pH. Linear/nonlinear indices were computed separately for MHR and FHR. Interaction between MHR and FHR was quantified through the same indices on FHR-MHR and through their correlation and cross-entropy. Univariate and bivariate statistical analysis included nonparametric confidence intervals and statistical tests, receiver operating characteristic curves and linear discriminant analysis. Progression of labor was associated with a significant increase in most MHR and FHR linear indices, whereas entropy indices decreased. FHR alone and in combination with MHR as FHR-MHR evidenced the highest auROC values for prediction of fetal acidemia, with 0.76 and 0.88 for the UAB pH thresholds 7.20 and 7.15, respectively. The inclusion of MHR on bivariate analysis achieved sensitivity and specificity values of nearly 100 and 89.1%, respectively. These results suggest that simultaneous analysis of MHR and FHR may improve the identification of fetal acidemia compared with FHR alone, namely during the last hour of labor.

Computer analysis of maternal-fetal heart rate recordings during labor in relation with maternal-fetal attachment and prediction of newborn acidemia

OBJECTIVE

To assess combined maternal (MHR) and fetal heart rate (FHR) recordings during labor, in relation with maternal-fetal attachment and prediction of newborn acidemia.

STUDY DESIGN

Fifty-nine simultaneous MHR and FHR recordings were acquired in the final minutes of labor. Computer analysis followed the FIGO guidelines with estimation of MHR and FHR baselines, accelerations, decelerations, short- (STV) and long-term variabilities. MHR and FHR characteristics, their differences and correlations were assessed in relation to labor progression and to newborn umbilical artery blood (UAB) pH lower than 7.15 and 7.20. To assess prediction of acidemia, areas under ROC curves (auROC) were calculated.

RESULTS

Progression of labor was associated with a significant increase in MHR accelerations and FHR decelerations both in the non-acidemic and acidemic fetuses (p < 0.01). At the same time there was an increase in MHR-FHR correlations and differences in accelerations and decelerations in acidemic fetuses. The auROC ranged between 0.50 for FHR accelerations and 0.77 for MHR baseline plus FHR STV.

CONCLUSIONS

MHR and FHR respond differently during labor with signs of increased maternal-fetal attachment during labor progression in acidemic fetuses. Combined MHR-FHR analysis may help to improve prediction of newborn acidemia compared with FHR analysis alone.

Continuous cardiotocography during labour: Analysis, classification and management

The use of continuous intrapartum electronic fetal heart rate monitoring (EFM) using a cardiotocograph (CTG) was developed to enable obstetricians and midwives to analyse the changes of fetal heart rate during labour so as to institute timely intervention to avoid intrapartum hypoxic-ischaemic injury. Although CTG was initially developed as a screening tool to predict fetal hypoxia, its positive predictive value for intrapartum fetal hypoxia is approximately only 30%. Even though different international classifications have been developed with the aim of defining combinations of features that help predict intrapartum fetal hypoxia, the false-positive rate of the CTG is high (60%). Moreover, there has not been a demonstrable improvement in the rate of cerebral palsy or perinatal deaths since the introduction of CTG into clinical practice approximately 45 years ago. However, there has been a significant increase in intrapartum caesarean section and operative vaginal delivery rates. Unfortunately, existing guidelines employ the visual interpretation of CTG based on 'pattern recognition', which is fraught with inter- and intra-observer variability. Therefore, clinicians need to understand the physiology behind fetal heart rate changes and to respond to them accordingly, instead of purely relying on guidelines for management. It is very likely that such a 'physiology-based' approach would reduce unnecessary operative interventions and improve perinatal outcomes whilst reducing the need for 'additional tests' of fetal well-being.