Study protocol: PoPE-Prediction of Preterm delivery by Electrohysterography

Assessment of uterine contractions in labor and delivery

Normal labor and delivery are dependent on the presence of regular and effective contractions of the uterine myometrium. The mechanisms responsible for the initiation and maintenance of adequate and synchronized uterine activity that are necessary for labor and delivery result from a complex interplay of hormonal, mechanical, and electrical factors that have not yet been fully elucidated. Monitoring uterine activity during term labor and in suspected preterm labor is an important component of obstetrical care because cases of inadequate and excessive uterine activity can be associated with substantial maternal and neonatal morbidity and mortality. Inadequate labor progress is a common challenge encountered in intrapartum care, with labor dystocia being the most common indication for cesarean deliveries performed during labor. Hereafter, an accurate assessment of uterine activity during labor can assist in the management of protracted labor by diagnosing inadequate uterine activity and facilitating the titration of uterotonic medications before a trial of labor is prematurely terminated. Conversely, the ability to diagnose unwanted or excessive uterine activity is also critical in cases of threatened preterm labor, tachysystole, or patients undergoing a trial of labor after cesarean delivery. Knowledge of uterine activity in these cases may guide the use of tocolytic medications or raise suspicion of uterine rupture. Current diagnostic capabilities are less than optimal, hindering the medical management of term and preterm labor. Currently, different methods exist for evaluating uterine activity during labor, including manual palpation, external tocodynamometry, intrauterine pressure monitoring, and electrical uterine myometrial activity tracing. Legacy uterine monitoring techniques have advantages and limitations. External tocodynamometry is the most widespread tool in clinical use owing to its noninvasive nature and its ability to time contractions against the fetal heart rate monitor. However, it does not provide information regarding the strength of uterine contractions and is limited by signal loss with maternal movements. Conversely, the intrauterine pressure catheter quantifies the strength of uterine contractions; however, its use is limited by its invasiveness, risk for complications, and limited additive value in all but few clinical scenarios. New monitoring methods are being used, such as electrical uterine monitoring, which is noninvasive and does not require ruptured membranes. Electrical uterine monitoring has yet to be incorporated into common clinical practice because of lack of access to this technology, its high cost, and the need for appropriate training of clinical staff. Further work needs to be done to increase the accessibility and implementation of this technique by experts, and further research is needed to implement new practical and useful methods. This review describes current clinical tools for uterine activity assessment during labor and discusses their advantages and shortcomings. The review also summarizes current knowledge regarding novel technologies for monitoring uterine contractions that are not yet in widespread use, but are promising and could help improve our understanding of the physiology of labor, delivery, and preterm labor, and ultimately enhance patient care.

Alvarez waves in pregnancy: a comprehensive review

Alvarez waves are local rhythmic contractions of the myometrium with high frequency and low intensity. They can be detected using internal or external tocography and electrohysterography. Some researchers correlate these small contractions with the initiation of labor, since they have been described as a pattern representing the uterine response to prostaglandin production. Other authors either do not validate a causality relation between Alvarez waves and labor or suggest that they have low predictive value for preterm labor. Alvarez waves' research has become a multidisciplinary subject with inputs ranging from medical science, biomedical engineering, and related areas. A comprehensive review is herein conducted to summarize the state of the art regarding Alvarez waves and their role in the initiation of labor, namely in preterm birth. The results show that a large number of studies have analyzed and characterized Alvarez waves without necessarily digging into their relationship with labor. Publications were categorized in three groups: (A) reports about morphology and characterization of Alvarez waves; (B) publications reporting a positive causality relation between Alvarez waves and labor; and (C) publications reporting an absence of causality regarding the previous hypothesis. Studies in group B outnumbered those in group C. A critical analysis is presented.

Propagation of spontaneous electrical activity in the ex vivo human uterus

Contractions of the non-pregnant uterus play a key role in fertility. Yet, the electrophysiology underlying these contractions is poorly understood. In this paper, we investigate the presence of uterine electrical activity and characterize its propagation in unstimulated ex vivo human uteri. Multichannel electrohysterographic measurements were performed in five freshly resected human uteri starting immediately after hysterectomy. Using an electrode grid externally and an electrode array internally, measurements were performed up to 24 h after hysterectomy and compared with control. Up to 2 h after hysterectomy, we measured biopotentials in all included uteri. The median root mean squared (RMS) values of the external measurements ranged between 3.95 μV (interquartile range (IQR) 2.41–14.18 μV) and 39.4 μV (interquartile range (IQR) 10.84–105.64 μV) and were all significantly higher than control (median RMS of 1.69 μV, IQR 1.13–3.11 μV), consisting of chicken breast meat. The RMS values decreased significantly over time. After 24 h, the median RMS (1.27 μV, IQR 0.86–3.04 μV) was comparable with the control (1.69 μV, IQR 1.13–3.11 μV, p = 0.125). The internal measurements showed a comparable pattern over time, but overall lower amplitude. The measured biopotentials propagated over the uterine surface, following both a plane-wave as well as an erratic pattern. No clear pacemaker location nor a preferred propagation direction could be identified. These results show that ex vivo uteri can spontaneously generate propagating biopotentials and provide novel insight contributing to improving our understanding of the electrophysiology of the human non-pregnant uterus.

Estimation of 8-Electrode Configuration for Recognition of Uterine Contraction with Electrohysterogram

As the representative of electrical activity from uterine muscle, electrohysterogram (EHG) is recorded non-invasively by multiple electrodes positioned on the abdominal surface. The purpose of our paper is to estimate different electrode configurations for recognizing uterine contractions (UCs) with EHG signals. 8-electrode configuration was taken as an example to show our novel method with convolutional neural network (CNN) classification and score. The open accessed Icelandic 16-electrode EHG database was adopted in our study. With 8-electrode configuration, EHG signals corresponding to UCs and non-UCs were segmented and saved as image patches. The CNN was established and trained by thousands of EHG segments. The performance of CNN was evaluated by the area under curve (AUC) and accuracy of recognizing UCs and non-UCs. Seven different 8-electrode configurations were scored and ranked. It was found the 8-electrode configuration with 4 on the uterine fundus, 2 on the body and 2 on the cervix achieved the AUC of 0.766 and the highest score of 2.197. Among the configurations we have tried, it is concluded that the 8 electrodes in 4-2-2 configuration placed along the uterus as an upside-down pear could provide the most important information for recognition of UC based on our experiments.

Evaluation of electrohysterogram measured from different gestational weeks for recognizing preterm delivery: a preliminary study using random Forest

Developing a computational method for recognizing preterm delivery is important for timely diagnosis and treatment of preterm delivery. The main aim of this study was to evaluate electrohysterogram (EHG) signals recorded at different gestational weeks for recognizing the preterm delivery using random forest (RF). EHG signals from 300 pregnant women were divided into two groups depending on when the signals were recorded: i) preterm and term delivery with EHG recorded before the 26^th week of gestation (denoted by PE and TE group), and ii) preterm and term delivery with EHG recorded during or after the 26^th week of gestation (denoted by PL and TL group). 31 linear features and nonlinear features were derived from each EHG signal, and then compared comprehensively within PE and TE group, and PL and TL group. After employing the adaptive synthetic sampling approach and six-fold cross-validation, the accuracy (ACC), sensitivity, specificity and area under the curve (AUC) were applied to evaluate RF classification. For PL and TL group, RF achieved the ACC of 0.93, sensitivity of 0.89, specificity of 0.97, and AUC of 0.80. Similarly, their corresponding values were 0.92, 0.88, 0.96 and 0.88 for PE and TE group, indicating that RF could be used to recognize preterm delivery effectively with EHG signals recorded before the 26^th week of gestation.

Development of Electrohysterogram Recording System for Monitoring Uterine Contraction

Uterine contraction (UC) is an important clinical indictor for monitoring uterine activity. The purpose of this study is to develop a portable electrohysterogram (EHG) recording system (called PregCare) for monitoring UCs with EHG signals. The PregCare consisted of sensors, a signal acquisition device, and a computer with application software. Eight-channel EHG signals, the tocodynamometry (TOCO) signal, and maternal perception were recorded simultaneously by the signal acquisition device controlled by the computer via Bluetooth. PregCare was firstly evaluated by a signal simulator. Its relative error (RE) and coefficient of variation (CV) were calculated, and its agreement with the commercial instrument PowerLab was assessed by Bland-Altman plots. After that, PregCare was applied to 20 pregnant women in a hospital to record their EHG signals. These EHG signals were preprocessed and segmented into UCs and non-UCs. Then, the EHG features corresponding to UCs and non-UCs were extracted, respectively, including power spectral density (PSD), root mean square (RMS), peak frequency (PF), median frequency (MDF), and sample entropy (SamEn). One-way ANOVA was employed to assess the difference between UCs and non-UCs. The results show that RE and CV were less than 8% and 0.03%, respectively, which indicated the high accuracy and repeatability of PregCare. The small differences of mean and standard deviation indicated the high agreement between PregCare and PowerLab. Besides, the PSD of UCs was much larger than non-UCs between 0 and 0.7 Hz. RMS of UCs was significantly larger than non-UCs (p < 0.05). PF and SamEn of UCs were significantly smaller than non-UCs (p < 0.05). In conclusion, the developed EHG recording system was able to record EHG signals reliably. It has the advantages of portability, low power consumption, and wireless transmission, which can be used for long-term monitoring of UCs and prediction of the preterm delivery.

Characterization and automatic classification of preterm and term uterine records

Predicting preterm birth is uncertain, and numerous scientists are searching for non-invasive methods to improve its predictability. Current researches are based on the analysis of ElectroHysteroGram (EHG) records, which contain information about the electrophysiological properties of the uterine muscle and uterine contractions. Since pregnancy is a long process, we decided to also characterize, for the first time, non-contraction intervals (dummy intervals) of the uterine records, i.e., EHG signals accompanied by a simultaneously recorded external tocogram measuring mechanical uterine activity (TOCO signal). For this purpose, we developed a new set of uterine records, TPEHGT DS, containing preterm and term uterine records of pregnant women, and uterine records of non-pregnant women. We quantitatively characterized contraction intervals (contractions) and dummy intervals of the uterine records of the TPEHGT DS in terms of the normalized power spectra of the EHG and TOCO signals, and developed a new method for predicting preterm birth. The results on the characterization revealed that the peak amplitudes of the normalized power spectra of the EHG and TOCO signals of the contraction and dummy intervals in the frequency band 1.0-2.2 Hz, describing the electrical and mechanical activity of the uterus due to the maternal heart (maternal heart rate), are high only during term pregnancies, when the delivery is still far away; and they are low when the delivery is close. However, these peak amplitudes are also low during preterm pregnancies, when the delivery is still supposed to be far away (thus suggesting the danger of preterm birth); and they are also low or barely present for non-pregnant women. We propose the values of the peak amplitudes of the normalized power spectra due to the influence of the maternal heart, in an electro-mechanical sense, in the frequency band 1.0-2.2 Hz as a new biophysical marker for the preliminary, or early, assessment of the danger of preterm birth. The classification of preterm and term, contraction and dummy intervals of the TPEHGT DS, for the task of the automatic prediction of preterm birth, using sample entropy, the median frequency of the power spectra, and the peak amplitude of the normalized power spectra, revealed that the dummy intervals provide quite comparable and slightly higher classification performances than these features obtained from the contraction intervals. This result suggests a novel and simple clinical technique, not necessarily to seek contraction intervals but using the dummy intervals, for the early assessment of the danger of preterm birth. Using the publicly available TPEHG DB database to predict preterm birth in terms of classifying between preterm and term EHG records, the proposed method outperformed all currently existing methods. The achieved classification accuracy was 100% for early records, recorded around the 23rd week of pregnancy; and 96.33%, the area under the curve of 99.44%, for all records of the database. Since the proposed method is capable of using the dummy intervals with high classification accuracy, it is also suitable for clinical use very early during pregnancy, around the 23rd week of pregnancy, when contractions may or may not be present.

Automated electrohysterographic detection of uterine contractions for monitoring of pregnancy: feasibility and prospects

Background

Preterm birth is a major public health problem in developed countries. In this context, we have conducted research into outpatient monitoring of uterine electrical activity in women at risk of preterm delivery. The objective of this preliminary study was to perform automated detection of uterine contractions (without human intervention or tocographic signal, TOCO) by processing the EHG recorded on the abdomen of pregnant women. The feasibility and accuracy of uterine contraction detection based on EHG processing were tested and compared to expert decision using external tocodynamometry (TOCO) .

Methods

The study protocol was approved by local Ethics Committees under numbers ID-RCB 2016-A00663-48 for France and VSN 02-0006-V2 for Iceland.

Two populations of women were included (threatened preterm birth and labour) in order to test our system of recognition of the various types of uterine contractions.

EHG signal acquisition was performed according to a standardized protocol to ensure optimal reproducibility of EHG recordings. A system of 18 Ag/AgCl surface electrodes was used by placing 16 recording electrodes between the woman’s pubis and umbilicus according to a 4 × 4 matrix. TOCO was recorded simultaneously with EHG recording.

EHG signals were analysed in real-time by calculation of the nonlinear correlation coefficient H². A curve representing the number of correlated pairs of signals according to the value of H² calculated between bipolar signals was then plotted. High values of H² indicated the presence of an event that may correspond to a contraction.

Two tests were performed after detection of an event (fusion and elimination of certain events) in order to increase the contraction detection rate.

Results

The EHG database contained 51 recordings from pregnant women, with a total of 501 contractions previously labelled by analysis of the corresponding tocographic recording. The percentage recognitions obtained by application of the method based on coefficient H² was 100% with 782% of false alarms. Addition of fusion and elimination tests to the previously obtained detections allowed the false alarm rate to be divided by 8.5, while maintaining an excellent detection rate (96%).

Conclusion

These preliminary results appear to be encouraging for monitoring of uterine contractions by algorithm-based automated detection to process the electrohysterographic signal (EHG). This compact recording system, based on the use of surface electrodes attached to the skin, appears to be particularly suitable for outpatient monitoring of uterine contractions, possibly at home, allowing telemonitoring of pregnancies. One of the advantages of EHG processing is that useful information concerning contraction efficiency can be extracted from this signal, which is not possible with the TOCO signal.

NEW AR/ARMA MODEL SELECTION METHOD FOR FINITE LENGTH TIME SERIES WITH APPLICATION TO PREDICTION OF PRETERM DELIVERIES

In this paper, we proposed a new method able to select, simultaneously, from finite length time-series sequence, the suitable model type; pure Autoregressive (AR) or Autoregressive Moving Average (ARMA), which best describes the process that generated data. This is also a new way for estimating ARMA model order. The proposed method is different in its concept from all other methods found in the literature, direct and far simpler to implement. We proposed new empirical criteria basing on specific AR order selection criteria for finite length time series. We tested the proposed criteria on 10000 realizations of different broadband and narrow band processes. We also studied effects of additive noise and data length on their performance. The best mean recognition rate of model type was 92%. [Formula: see text]-value of Fisher’s exact test was always strictly under [Formula: see text]. Power spectral densities of selected models managed to recover the true Power spectral density (PSDs) shapes by resolving close spectral peaks and by finding their positions and their bandwidths with negligible spectral biases. Efficiency of our method was proved by its application in automatic segmentation of electrohysterographic signals (EHG) in the aim of predicting preterm deliveries with a mean rate of 90%.

Dedicated Entropy Measures for Early Assessment of Pregnancy Progression From Single-Channel Electrohysterography

OBJECTIVE

Preterm birth is a large-scale clinical problem involving over 10% of infants. Diagnostic means for timely risk assessment are lacking and the underlying physiological mechanisms unclear. To improve the evaluation of pregnancy before term, we introduce dedicated entropy measures derived from a single-channel electrohysterogram (EHG).

METHODS

The estimation of approximate entropy (ApEn) and sample entropy (SampEn) is adjusted to monitor variations in the regularity of single-channel EHG recordings, reflecting myoelectrical changes due to pregnancy progression. In particular, modifications in the tolerance metrics are introduced for improving robustness to EHG amplitude fluctuations. An extensive database of 58 EHG recordings with 4 monopolar channels in women presenting with preterm contractions was manually annotated and used for validation. The methods were tested for their ability to recognize the onset of labor and the risk of preterm birth. Comparison with the best single-channel methods according to the literature was performed.

RESULTS

The reference methods were outperformed. SampEn and ApEn produced the best prediction of delivery, although only one channel showed a significant difference () between labor and nonlabor. The modified ApEn produced the best prediction of preterm delivery, showing statistical significance () in three channels. These results were also confirmed by the area under the receiver operating characteristic curve and fivefold cross validation.

CONCLUSION

The use of dedicated entropy estimators improves the diagnostic value of EHG analysis earlier in pregnancy.

SIGNIFICANCE

Our results suggest that changes in the EHG might manifest early in pregnancy, providing relevant prognostic opportunities for pregnancy monitoring by a practical single-channel solution.

Prediction of labor onset type: Spontaneous vs induced; role of electrohysterography?

BACKGROUND AND OBJECTIVE

Induction of labor (IOL) is a medical procedure used to initiate uterine contractions to achieve delivery. IOL entails medical risks and has a significant impact on both the mother's and newborn's well-being. The assistance provided by an automatic system to help distinguish patients that will achieve labor spontaneously from those that will need late-term IOL would help clinicians and mothers to take an informed decision about prolonging pregnancy. With this aim, we developed and evaluated predictive models using not only traditional obstetrical data but also electrophysiological parameters derived from the electrohysterogram (EHG).

METHODS

EHG recordings were made on singleton term pregnancies. A set of 10 temporal and spectral parameters was calculated to characterize EHG bursts and a further set of 6 common obstetrical parameters was also considered in the predictive models design. Different models were implemented based on single layer Support Vector Machines (SVM) and with aggregation of majority voting of SVM (double layer), to distinguish between the two groups: term spontaneous labor (≤41 weeks of gestation) and IOL late-term labor. The areas under the curve (AUC) of the models were compared.

RESULTS

The obstetrical and EHG parameters of the two groups did not show statistically significant differences. The best results of non-contextualized single input parameter SVM models were achieved by the Bishop Score (AUC= 0.65) and GA at recording time (AUC= 0.68) obstetrical parameters. The EHG parameter median frequency, when contextualized with the two obstetrical parameters improved these results, reaching AUC= 0.76. Multiple input SVM obtained AUC= 0.70 for all EHG parameters. Aggregation of majority voting of SVM models using contextualized EHG parameters achieved the best result AUC= 0.93.

CONCLUSIONS

Measuring the electrophysiological uterine condition by means of electrohysterographic recordings yielded a promising clinical decision support system for distinguishing patients that will spontaneously achieve active labor before the end of full term from those who will require late term IOL. The importance of considering these EHG measurements in the patient's individual context was also shown by combining EHG parameters with obstetrical parameters. Clinicians considering elective labor induction would benefit from this technique.

Improved Prediction of Preterm Delivery Using Empirical Mode Decomposition Analysis of Uterine Electromyography Signals

Preterm delivery increases the risk of infant mortality and morbidity, and therefore developing reliable methods for predicting its likelihood are of great importance. Previous work using uterine electromyography (EMG) recordings has shown that they may provide a promising and objective way for predicting risk of preterm delivery. However, to date attempts at utilizing computational approaches to achieve sufficient predictive confidence, in terms of area under the curve (AUC) values, have not achieved the high discrimination accuracy that a clinical application requires. In our study, we propose a new analytical approach for assessing the risk of preterm delivery using EMG recordings which firstly employs Empirical Mode Decomposition (EMD) to obtain their Intrinsic Mode Functions (IMF). Next, the entropy values of both instantaneous amplitude and instantaneous frequency of the first ten IMF components are computed in order to derive ratios of these two distinct components as features. Discrimination accuracy of this approach compared to those proposed previously was then calculated using six differently representative classifiers. Finally, three different electrode positions were analyzed for their prediction accuracy of preterm delivery in order to establish which uterine EMG recording location was optimal signal data. Overall, our results show a clear improvement in prediction accuracy of preterm delivery risk compared with previous approaches, achieving an impressive maximum AUC value of 0.986 when using signals from an electrode positioned below the navel. In sum, this provides a promising new method for analyzing uterine EMG signals to permit accurate clinical assessment of preterm delivery risk.

Propagation of electrical activity in uterine muscle during pregnancy: a review

The uterine muscle (the myometrium) plays its most evident role during pregnancy, when quiescence is required for adequate nourishment and development of the foetus, and during labour, when forceful contractions are needed to expel the foetus and the other products of conception. The myometrium is composed of smooth muscle cells. Contraction is initiated by the spontaneous generation of electrical activity at the cell level in the form of action potentials. The mechanisms underlying uterine quiescence during pregnancy and electrical activation during labour remain largely unknown; as a consequence, the clinical management of preterm contractions during pregnancy and inefficient uterine contractility during labour remains suboptimal. In an effort to improve clinical management of uterine contractions, research has focused on understanding the propagation properties of the electrical activity of the uterus. Different perspectives have been undertaken, from animal and in vitro experiments up to clinical studies and dedicated methods for non-invasive parameter estimation. A comparison of the results is not straightforward due to the wide range of different approaches reported in the literature. However, previous studies unanimously reveal a unique complexity as compared to other organs in the pattern of uterine electrical activity propagation, which necessarily needs to be taken into consideration for future studies to be conclusive. The aim of this review is to structure current variegated knowledge on the properties of the uterus in terms of pacemaker position, pattern, direction and speed of the electrical activity during pregnancy and labour.