Predicting term and preterm delivery with transabdominal uterine electromyography

Uterine slow wave: directionality and changes with imminent delivery

OBJECTIVE

The slow wave (SW) of the electrohysterogram (EHG) may contain relevant information on the electrophysiological condition of the uterus throughout pregnancy and labor. Our aim was to assess differences in the SW as regards the imminence of labor and the directionality of uterine myoelectrical activity.

APPROACH

The SW of the EHG was extracted from the signals of the Icelandic 16-electrode EHG database in the bandwidth [5, 30] mHz and its power, spectral content, complexity and synchronization between the horizontal (X) and vertical (Y) directions were characterized by the root mean square (RMS), dominant frequency (domF), sample entropy (SampEn) and maximum cross-correlation (CCmax) of the signals, respectively. Significant differences between parameters at time-to-delivery (TTD) ≤7 vs. >7 days and between the horizontal vs. vertical directions were assessed.

MAIN RESULTS

The SW power significantly increased in both directions as labor approached (TTD≤7d vs. >7d (mean±SD): x= 0.12±0.10 vs. 0.08±0.06mV; y= 0.12±0.09 vs. 0.08±0.05mV), as well as the dominant frequency in the horizontal direction (= 9.1±1.3 vs. 8.5±1.2mHz) and the synchronization between both directions (= 0.44±0.16 vs. 0.36±0.14). Furthermore, its complexity decreased in the vertical direction (= 6.13·10-2±8.7·10-3 vs. 6.50·10-2±8.3·10-3), suggesting a higher cell-to-cell electrical coupling. Whereas there were no differences between the SW features in both directions in the general population, statistically significant differences were obtained between them in individuals in many cases.

SIGNIFICANCE

Our results suggest that the SW of the EHG is related to bioelectrical events in the uterus and could provide objective information to clinicians in challenging obstetric scenarios.

Assessing Velocity and Directionality of Uterine Electrical Activity for Preterm Birth Prediction Using EHG Surface Records

The aim of the present study was to assess the capability of conduction velocity amplitudes and directions of propagation of electrohysterogram (EHG) waves to better distinguish between preterm and term EHG surface records. Using short-time cross-correlation between pairs of bipolar EHG signals (upper and lower, left and right), the conduction velocities and their directions were estimated using preterm and term EHG records of the publicly available Term–Preterm EHG DataSet with Tocogram (TPEHGT DS) and for different frequency bands below and above 1.0 Hz, where contractions and the influence of the maternal heart rate on the uterus, respectively, are expected. No significant or preferred continuous direction of propagation was found in any of the non-contraction (dummy) or contraction intervals; however, on average, a significantly lower percentage of velocity vectors was found in the vertical direction, and significantly higher in the horizontal direction, for preterm dummy intervals above 1.0 Hz. The newly defined features—the percentages of velocities in the vertical and horizontal directions, in combination with the sample entropy of the EHG signal recorded in the vertical direction, obtained from dummy intervals above 1.0 Hz—showed the highest classification accuracy of 86.8% (AUC=90.3%) in distinguishing between preterm and term EHG records of the TPEHGT DS.

Review and Study of Uterine Bioelectrical Waveforms and Vector Analysis to Identify Electrical and Mechanosensitive Transduction Control Mechanisms During Labor in Pregnant Patients

The bioelectrical signals that produce uterine contractions during parturition are not completely understood. The objectives are as follows: (1) to review the literature and information concerning uterine biopotential waveforms generated by the uterus, known to produce contractions, and evaluate mechanotransduction in pregnant patients using electromyographic (EMG) recording methods and (2) to study a new approach, uterine vector analysis, commonly used for the heart: vectorcardiography analysis. The patients used in this study were as follows: (1) patients at term not in labor (n = 3); (2) patients during the 1st stage of labor at cervical dilations from 2 to 10 cm (n = 30); and (3) patients in the 2nd stage of labor and during delivery (n = 3). We used DC-coupled electrodes and PowerLab hardware (model no. PL2604, ADInstruments, Castle Hill, Australia), with software (LabChart, ADInstruments) for storage and analysis of biopotentials. Uterine and abdominal EMG recordings were made from the surface of each patient using 3 electrode pairs with 1 pair (+ and -, with a 31-cm spacing distance) placed in the right/left position (X position) and with 1 pair placed in an up/down position (Y position, also 31 cm apart) and with the third pair at the front/back (Z position). Using signals from the three X, Y, and Z electrodes, slow (0.03 to 0.1 Hz, high amplitude) and fast wave (0.3 to 1 Hz, low amplitude) biopotentials were recorded. The amplitudes of the slow waves and fast waves were significantly higher during the 2nd stage of labor compared to the 1st stage (respectively, p = 9.54 × e^-3 and p = 3.94 × e^-7). When 2 channels were used, for example, the X vs. Y, for 2-D vector analysis or 3 channels, X vs. Y vs. Z, for 3-D analysis, are plotted against each other on their axes, this produces a vector electromyometriogram (EMMG) that shows no directionality for fast waves and a downward direction for slow waves. Similarly, during the 2nd stage of labor during abdominal contractions ("pushing"), the slow and fast waves were enlarged. Manual applied pressure was used to evoke bioelectrical activity to examine the mechanosensitivity of the uterus. Conclusions: (1) Phasic contractility of the uterus is a product of slow waves and groups of fast waves (bursts of spikes) to produce myometrial contractile responses. (2) 2-D and 3-D uterine vector analyses (uterine vector electromyometriogram) demonstrate no directionality of small fast waves while the larger slow waves represent the downward direction of biopotentials towards the cervical opening. (3) Myometrial cell action event excitability and subsequent contractility likely amplify slow wave activity input and uterine muscle contractility via mechanotransduction systems. (4) Models illustrate the possible relationships of slow to fast waves and the association of a mechanotransduction system and pacemaker activity as observed for slow waves and pacemakers in gastrointestinal muscle. (5) The interaction of these systems is thought to regulate uterine contractility. (6) This study suggests a potential indicator of delivery time. Such vector approaches might help us predict the progress of gestation and better estimate the timing of delivery, gestational pathologies reflected in bioelectric events, and perhaps the potential for premature delivery drug and mechanical interventions.

Analysis of Electrohysterographic Signal Propagation Direction during Uterine Contraction: the Application of Directed Information

The potential of using the information of uterine contractions (UCs) derived from electrohysterogram (EHG) has been recognized in early detection of preterm delivery. A better understanding of the conduction property of EHG is clinically useful for developing advanced methods to achieve a reliable prediction of preterm delivery. In this paper, a method to analyze the destination of EHG propagation has been proposed via the estimation of directed information (DI) between each pair of neighboring channels with a novel propagation terminal zone (PTZ) identification algorithm. The proposed method was applied to experimental data from the Icelandic 16-electrode EHG database. The results demonstrated that for more than 81.8% participants, the PTZ was identified along the medial axis of uterus, among which more than half have their PTZ determined in the center between the uterine fundus and public symphysis, which indicated a great probability of propagation of EHG signals towards the center of uterus plane.Clinical relevance- This study makes a fundamental contribution for predicting preterm delivery, which can provide improvement in obstetric care towards pregnancy monitoring.

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.

Robust Characterization of the Uterine Myoelectrical Activity in Different Obstetric Scenarios

Electrohysterography (EHG) has been shown to provide relevant information on uterine activity and could be used for predicting preterm labor and identifying other maternal fetal risks. The extraction of high-quality robust features is a key factor in achieving satisfactory prediction systems from EHG. Temporal, spectral, and non-linear EHG parameters have been computed to characterize EHG signals, sometimes obtaining controversial results, especially for non-linear parameters. The goal of this work was to assess the performance of EHG parameters in identifying those robust enough for uterine electrophysiological characterization. EHG signals were picked up in different obstetric scenarios: antepartum, including women who delivered on term, labor, and post-partum. The results revealed that the 10th and 90th percentiles, for parameters with falling and rising trends as labor approaches, respectively, differentiate between these obstetric scenarios better than median analysis window values. Root-mean-square amplitude, spectral decile 3, and spectral moment ratio showed consistent tendencies for the different obstetric scenarios as well as non-linear parameters: Lempel–Ziv, sample entropy, spectral entropy, and SD1/SD2 when computed in the fast wave high bandwidth. These findings would make it possible to extract high quality and robust EHG features to improve computer-aided assessment tools for pregnancy, labor, and postpartum progress and identify maternal fetal risks.

An Integrated Review of Uterine Activity Monitoring for Evaluating Labor Dystocia

Introduction:

Labor dystocia is the most common cause of cesarean birth in the United States, yet how dystocia develops during labor remains elusive. Uterine activity monitoring has significant potential for advancing our understanding of labor dystocia. While evaluating contraction frequency and amplitude is a common component of labor dystocia management, the literature describing the relationship between measures of uterine activity and labor dystocia is heterogeneous and has not been synthesized to identify the best methods for use in clinical investigation.

Methods:

We conducted a literature search for original research exploring the relationship between uterine activity and labor dystocia published between 2000 and 2019. Included articles were critically reviewed and synthesized.

Results:

Across 11 identified studies, investigators employed 3 different techniques for monitoring uterine activity and 9 different measures were employed. Uterine activity measures, including Montevideo units, uterine electromyography power density spectrum and sample entropy, and the fall-to-rise ratio of contraction shape, detected patterns associated with labor dystocia or cesarean birth.

Discussion:

The use of multiple regression with clinical covariates and a uterine activity measure increased the accuracy of predicting cesarean delivery. Uterine electromyography may be especially useful to evaluate labor dystocia phenotypes to differentiate uterine muscle fatigue from understimulation and lead to algorithms for increased precision in the diagnosis of labor dystocia and innovative approaches to treatment.

Electrohysterogram for ANN-Based Prediction of Imminent Labor in Women with Threatened Preterm Labor Undergoing Tocolytic Therapy

Threatened preterm labor (TPL) is the most common cause of hospitalization in the second half of pregnancy and entails high costs for health systems. Currently, no reliable labor proximity prediction techniques are available for clinical use. Regular checks by uterine electrohysterogram (EHG) for predicting preterm labor have been widely studied. The aim of the present study was to assess the feasibility of predicting labor with a 7- and 14-day time horizon in TPL women, who may be under tocolytic treatment, using EHG and/or obstetric data. Based on 140 EHG recordings, artificial neural networks were used to develop prediction models. Non-linear EHG parameters were found to be more reliable than linear for differentiating labor in under and over 7/14 days. Using EHG and obstetric data, the <7- and <14-day labor prediction models achieved an AUC in the test group of 87.1 ± 4.3% and 76.2 ± 5.8%, respectively. These results suggest that EHG can be reliable for predicting imminent labor in TPL women, regardless of the tocolytic therapy stage. This paves the way for the development of diagnostic tools to help obstetricians make better decisions on treatments, hospital stays and admitting TPL women, and can therefore reduce costs and improve maternal and fetal wellbeing.

New electrohysterogram-based estimators of intrauterine pressure signal, tonus and contraction peak for non-invasive labor monitoring

BACKGROUND

Uterine activity monitoring is an essential part of managing the progress of pregnancy and labor. Although intrauterine pressure (IUP) is the only reliable method of estimating uterine mechanical activity, it is highly invasive. Since there is a direct relationship between the electrical and mechanical activity of uterine cells, surface electrohysterography (EHG) has become a noninvasive monitoring alternative. The Teager energy (TE) operator of the EHG signal has been used for IUP continuous pressure estimation, although its accuracy could be improved. We aimed to develop new optimized IUP estimation models for clinical application.

APPROACH

We first considered enhancing the optimal estimation of IUP clinical features (maximum pressure and tonus) rather than optimizing the signal only (continuous pressure). An adaptive algorithm was also developed to deal with inter-patient variability. For each optimizing signal feature (continuous pressure, maximum pressure and tonus), individual (single patient), global (full database) and adaptive models were built to estimate the recorded IUP signal. The results were evaluated by computing the root mean square errors (RMSe): continuous pressure error (CPe), maximum pressure error (MPe) and tonus error (TOe).

MAIN RESULTS

The continuous pressure global model yielded IUP estimates with Cpe  =  14.61 mm Hg, MPe  =  29.17 mm Hg and Toe  =  7.8 mm Hg. The adaptive models significantly reduced errors to CPe  =  11.88, MPe  =  16.02 and Toe  =  5.61 mm Hg. The EHG-based IUP estimates outperformed those from traditional tocographic recordings, which had significantly higher errors (CPe  =  21.93, MPe  =  26.97, and TOe  =  13.96).

SIGNIFICANCE

Our results show that adaptive models yield better IUP estimates than the traditional approaches and provide the best balance of the different errors computed for a better assessment of the labor progress and maternal and fetal well-being.

Detection of preterm birth in electrohysterogram signals based on wavelet transform and stacked sparse autoencoder

Based on electrohysterogram, this paper designed a new method using wavelet-based nonlinear features and stacked sparse autoencoder for preterm birth detection. For each sample, three level wavelet decomposition of a time series was performed. Approximation coefficients at level 3 and detail coefficients at levels 1, 2 and 3 were extracted. Sample entropy of the detail coefficients at levels 1, 2, 3 and approximation coefficients at level 3 were computed as features. The classifier was constructed based on stacked sparse autoencoder. In addition, stacked sparse autoencoder was further compared with extreme learning machine and support vector machine in relation to their classification performance of electrohysterogram. The experiment results reveal that classifier based on stacked sparse autoencoder showed better performance than the other two classifiers with an accuracy of 90%, a sensitivity of 92%, a specificity of 88%. The results indicate that the method proposed in this paper could be effective for detecting preterm birth in electrohysterogram and the framework designed in this work presents higher discriminability than other techniques.

Uterine electromyography for discrimination of labor imminence in women with threatened preterm labor under tocolytic treatment

As one of the main aims of obstetrics is to be able to detect imminent delivery in patients with threatened preterm labor, the techniques currently used in clinical practice have serious limitations in this respect. The electrohysterogram (EHG) has now emerged as an alternative technique, providing relevant information about labor onset when recorded in controlled checkups without administration of tocolytic drugs. The studies published to date mainly focus on EHG-burst analysis and, to a lesser extent, on whole EHG window analysis. The study described here assessed the ability of EHG signals to discriminate imminent labor (< 7 days) in women with threatened preterm labor undergoing tocolytic therapy, using both EHG-burst and whole EHG window analyses, by calculating temporal, spectral, and non-linear parameters. Only two non-linear EHG-burst parameters and four whole EHG window analysis parameters were able to distinguish the women who delivered < 7 days from the others, showing that EHG can provide relevant information on the approach of labor, even in women with threatened preterm labor under the effects of tocolytic therapy. The whole EHG window outperformed the EHG-burst analysis and is seen as a step forward in the development of real-time EHG systems able to predict imminent labor in clinical praxis. Graphical abstract The ability of EHG recordings to predict imminent labor (< 7 days) was analyzed in preterm threatened patients undergoing tocolytic therapies by means of EHG-burst and whole EHG window analysis. The non-linear features were found to have better performance than the temporal and spectral parameters in separating women who delivered in less than 7 days from those who did not.

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.

Infection-induced thrombin production: a potential novel mechanism for preterm premature rupture of membranes (PPROM)

BACKGROUND

Preterm premature rupture of membranes is a leading contributor to maternal and neonatal morbidity and death. Epidemiologic and experimental studies have demonstrated that thrombin causes fetal membrane weakening and subsequently preterm premature rupture of membranes. Although blood is suspected to be the likely source of thrombin in fetal membranes and amniotic fluid of patients with preterm premature rupture of membranes, this has not been proved. Ureaplasma parvum is emerging as a pathogen involved in prematurity, which includes preterm premature rupture of membranes; however, until now, prothrombin production that has been induced directly by bacteria in fetal membranes has not been described.

OBJECTIVE

This study was designed to investigate whether Ureaplasma parvum exposure can induce prothrombin production in fetal membranes cells.

STUDY DESIGN

Primary fetal membrane cells (amnion epithelial, chorion trophoblast, and decidua stromal) or full-thickness fetal membrane tissue explants from elective, term, uncomplicated cesarean deliveries were harvested. Cells or tissue explants were infected with live Ureaplasma parvum (1×10⁵, 1×10⁶ or 1×10⁷ colony-forming units per milliliter) or lipopolysaccharide (Escherichia coli J5, L-5014; Sigma Chemical Company, St. Louis, MO; 100 ng/mL or 1000 ng/mL) for 24 hours. Tissue explants were fixed for immunohistochemistry staining of thrombin/prothrombin. Fetal membrane cells were fixed for confocal immunofluorescent staining of the biomarkers of fetal membrane cell types and thrombin/prothrombin. Protein and messenger RNA were harvested from the cells and tissue explants for Western blot or quantitative reverse transcription polymerase chain reaction to quantify thrombin/prothrombin protein or messenger RNA production, respectively. Data are presented as mean values ± standard errors of mean. Data were analyzed using 1-way analysis of variance with post hoc Dunnett's test.

RESULTS

Prothrombin production and localization were confirmed by Western blot and immunostainings in all primary fetal membrane cells and tissue explants. Immunofluorescence observations revealed a perinuclear localization of prothrombin in amnion epithelial cells. Localization of prothrombin in chorion and decidua cells was perinuclear and cytoplasmic. Prothrombin messenger RNA and protein expression in fetal membranes were increased significantly by Ureaplasma parvum, but not lipopolysaccharide, treatments in a dose-dependent manner. Specifically, Ureaplasma parvum at a dose of 1×10⁷ colony-forming units/mL significantly increased both prothrombin messenger RNA (fold changes in amnion: 4.1±1.9; chorion: 5.7±4.2; decidua: 10.0±5.4; fetal membrane: 9.2±3.0) and protein expression (fold changes in amnion: 138.0±44.0; chorion: 139.6±15.1; decidua: 56.9±29.1; fetal membrane: 133.1±40.0) compared with untreated control subjects. Ureaplasma parvum at a dose of 1×10⁶ colony-forming units/mL significantly up-regulated prothrombin protein expression in chorion cells (fold change: 54.9±5.3) and prothrombin messenger RNA expression in decidua cells (fold change: 4.4±1.9).

CONCLUSION

Our results demonstrate that prothrombin can be produced directly by fetal membrane amnion, chorion, and decidua cells. Further, prothrombin production can be stimulated by Ureaplasma parvum exposure in fetal membranes. These findings represent a potential novel underlying mechanism of Ureaplasma parvum-induced rupture of fetal membranes.

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.

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.

Feature Extraction and Classification of EHG between Pregnancy and Labour Group Using Hilbert-Huang Transform and Extreme Learning Machine

Preterm birth (PTB) is the leading cause of perinatal mortality and long-term morbidity, which results in significant health and economic problems. The early detection of PTB has great significance for its prevention. The electrohysterogram (EHG) related to uterine contraction is a noninvasive, real-time, and automatic novel technology which can be used to detect, diagnose, or predict PTB. This paper presents a method for feature extraction and classification of EHG between pregnancy and labour group, based on Hilbert-Huang transform (HHT) and extreme learning machine (ELM). For each sample, each channel was decomposed into a set of intrinsic mode functions (IMFs) using empirical mode decomposition (EMD). Then, the Hilbert transform was applied to IMF to obtain analytic function. The maximum amplitude of analytic function was extracted as feature. The identification model was constructed based on ELM. Experimental results reveal that the best classification performance of the proposed method can reach an accuracy of 88.00%, a sensitivity of 91.30%, and a specificity of 85.19%. The area under receiver operating characteristic (ROC) curve is 0.88. Finally, experimental results indicate that the method developed in this work could be effective in the classification of EHG between pregnancy and labour group.

Characterizing the Propagation of Uterine Electrophysiological Signals Recorded with a Multi-Sensor Abdominal Array in Term Pregnancies

The objective of this study was to quantify the number of segments that have contractile activity and determine the propagation speed from uterine electrophysiological signals recorded over the abdomen. The uterine magnetomyographic (MMG) signals were recorded with a 151 channel SARA (SQUID Array for Reproductive Assessment) system from 36 pregnant women between 37 and 40 weeks of gestational age. The MMG signals were scored and segments were classified based on presence of uterine contractile burst activity. The sensor space was then split into four quadrants and in each quadrant signal strength at each sample was calculated using center-of-gravity (COG). To this end, the cross-correlation analysis of the COG was performed to calculate the delay between pairwise combinations of quadrants. The relationship in propagation across the quadrants was quantified and propagation speeds were calculated from the delays. MMG recordings were successfully processed from 25 subjects and the average values of propagation speeds ranged from 1.3-9.5 cm/s, which was within the physiological range. The propagation was observed between both vertical and horizontal quadrants confirming multidirectional propagation. After the multiple pairwise test (99% CI), significant differences in speeds can be observed between certain vertical or horizontal combinations and the crossed pair combinations. The number of segments containing contractile activity in any given quadrant pair with a detectable delay was significantly higher in the lower abdominal pairwise combination as compared to all others. The quadrant-based approach using MMG signals provided us with high spatial-temporal information of the uterine contractile activity and will help us in the future to optimize abdominal electromyographic (EMG) recordings that are practical in a clinical setting.

The association between myometrial electrical activity and time to delivery in threatened preterm labor

OBJECTIVE

To assess the association between myometrial electrical activity and time-to-delivery in preterm labor using uterine electromyography.

METHODS

Myometrial electrical activity was measured via the electrical uterine monitor (EUM) device. Data was prospectively collected among women admitted due to suspected preterm labor, prior to 34 weeks of gestation. EUM-Index was defined as the mean electrical activity of the uterine muscle over a period of 10 minutes measured in units of microjoule (μJ, microwatt second). The association between the EUM-Index at admission to time-to-delivery and delivery prior to 34 weeks of gestation was calculated.

RESULTS

Overall, 45 women were included in the study. EUM-Index combined with cervical dilatation, demonstrated significant correlation to time-to-delivery (R(2 )= 0.49, p = 0.005), which was strengthened for women presenting prior to 28 weeks of gestation. EUM-Index above the median (>3.05 MJ) was significantly associated with a shorter latency period for delivery (36.0 ± 19.4 vs. 50.2 ± 25.9 days, p = 0.04). For delivery prior to 34 weeks, the EUM-Index showed an AUC = 0.65 (95% CI 0.48-0.82), and a cutoff of 2.5 MJ provided 91.7% sensitivity and 93.3% negative predictive value.

CONCLUSION

EUM-Index at time of admission due to suspected preterm labor is inversely correlated with time-to-delivery and may effectively rule out preterm delivery prior to 34 weeks.

Vaginal electrohysterography: the design and preliminary evaluation of a novel device for uterine contraction monitoring in an ovine model (.)

OBJECTIVE

Tocodynamometry is the most common method of labor evaluation but most clinicians would agree it has limited utility before 26 weeks of gestation. The obesity epidemic has further reduced our ability to accurately detect uterine contractions using the tocodynamometer at any gestational age. We sought to design and test a novel contraction monitor that bypasses the maternal abdomen.

METHODS

An optimized version of an intravaginal electrohysterographic ring device was tested in an ovine model. The device and its methodology as well as the tocodynamometer were validated against the current gold standard uterine activity monitor, the intrauterine pressure catheter in six sheep at varying gestational ages.

RESULTS

Both the intravaginal ring device and the tocodynamometer correlated well with IUPC, r = 0.69 and 0.73, respectively (p < 0.001). The number of contractions detected by each monitor remained similar even after accounting for confounders.

CONCLUSIONS

These results suggest that uterine activity can be monitored from the vaginal interface in an ovine model and offers an alternative clinical tool for the detection of contractions in situations, in which tocodynamometry would be ineffective or intrauterine monitoring inappropriate.

Automatic epileptic seizure detection using scalp EEG and advanced artificial intelligence techniques

The epilepsies are a heterogeneous group of neurological disorders and syndromes characterised by recurrent, involuntary, paroxysmal seizure activity, which is often associated with a clinicoelectrical correlate on the electroencephalogram. The diagnosis of epilepsy is usually made by a neurologist but can be difficult to be made in the early stages. Supporting paraclinical evidence obtained from magnetic resonance imaging and electroencephalography may enable clinicians to make a diagnosis of epilepsy and investigate treatment earlier. However, electroencephalogram capture and interpretation are time consuming and can be expensive due to the need for trained specialists to perform the interpretation. Automated detection of correlates of seizure activity may be a solution. In this paper, we present a supervised machine learning approach that classifies seizure and nonseizure records using an open dataset containing 342 records. Our results show an improvement on existing studies by as much as 10% in most cases with a sensitivity of 93%, specificity of 94%, and area under the curve of 98% with a 6% global error using a k-class nearest neighbour classifier. We propose that such an approach could have clinical applications in the investigation of patients with suspected seizure disorders.

Separating sets of term and pre-term uterine EMG records

The analysis of uterine EMG (electrohysterogram-EHG) records may help solve the problem of predicting pre-term labor. We investigated the adaptive autoregressive (AAR) method to estimate the EHG signal spectrograms and sample entropy, to separate and classify sets of term and pre-term delivery records, using the Term-Preterm EHG Database. The database contains four sets of records divided according to the time of delivery (term or pre-term: ⩾37 or < 37 weeks of gestation, respectively) and according to the time of recording (early or later: before or after the 26th week of gestation, respectively). Using the AAR method the term and pre-term delivery records recorded early can be separated (p = 0.002), as well as all term and pre-term delivery records (p < 0.001). Using the sample entropy, the results showed that all term and pre-term delivery records can be separated (p = 0.022). The spectra of the signals for term delivery records have the tendency of moving to lower frequencies as the time of pregnancy increases. We investigated a few classifiers to classify records between term and pre-term delivery sets. Using median frequency measurements and additional clinical information with the synthetic minority over-sampling technique, the quadratic discriminant analysis classifier achieved a 97% classification accuracy for the records recorded early, and 86% for all records regardless of the time of recording; while for the sample entropy measurements, for the same sets of records, using the support vector machine classifier, the classification accuracies were 80% and 87%, respectively.

Empirical mode decomposition applied for non-invasive electrohysterograhic signals denoising

The electrical activity of the uterus, i.e. the electrohysterogram (EHG), is one of the most prominent tool for preterm labour. There is no standard acquisition set up and often the EHG is corrupted with different types of noise: maternal and fetal electrocardiogram (mECG, fECG), electrical activity of the skeletal muscles, movement artifacts, power line interference (PLI) etc. Moreover, some of these noises overlap in frequency domain with the EHG. Thus, simple linear filtering approaches are not adequate. In this paper the empirical mode decomposition (EMD), a simple and data driven method, is proposed for EHG denoising. The method is evaluated on simulated data having different signal to noise ratios (SNRs) obtaining promising results.

Feasibility and analysis of bipolar concentric recording of electrohysterogram with flexible active electrode

The conduction velocity and propagation patterns of the electrohysterogram (EHG) provide fundamental information on the electrophysiological condition of the uterus. However, the accuracy of these measurements can be impaired by both the poor spatial selectivity and sensitivity to the relative direction of the contraction propagation associated with conventional disc electrodes. Concentric ring electrodes could overcome these limitations. The aim of this study was to examine the feasibility of picking up surface EHG signals using a new flexible tripolar concentric ring electrode (TCRE), and to compare these signals with conventional bipolar recordings. Simultaneous recording of conventional bipolar signals and bipolar concentric EHG (BC-EHG) were carried out on 22 pregnant women. Signal bursts were characterized and compared. No significant differences were found between the channels in either duration or dominant frequency in the Fast Wave High frequency range. Nonetheless, the high pass filtering effect of the BC-EHG recordings gave lower frequency content between 0.1 and 0.2 Hz. Although the BC-EHG signal amplitude was about 5-7 times smaller than that of bipolar recordings, a similar signal-to-noise ratio was obtained. These results suggest that the flexible TCRE is able to pick up uterine electrical activity and could provide additional information for deducing the uterine electrophysiological condition.

Study protocol: PoPE-Prediction of Preterm delivery by Electrohysterography

Background

Traditional methods used for prediction of preterm delivery are subjective and inaccurate. The Electrohysterogram (EHG) and in particular the estimation of the EHG conduction velocity, is a relatively new promising method for detecting imminent preterm delivery. To date the analysis of the conduction velocity has relied on visual inspection of the signals. As a next step towards the introduction of EHG analysis as a clinical tool, we propose an automated method for EHG conduction velocity estimation for both the speed and direction of single spike propagation.

Methods/Design

The study design will be an observational cohort study. 100 pregnant women, gestational age between 23 + 5 and 34 weeks, admitted for threatening preterm labor or preterm prelabor rupture of membranes, will be included. The length of the cervical canal will be measured by transvaginal ultrasound. The EHG will be recorded using 4 electrodes in a fixed configuration. Contractions will be detected by analysis of the EHG and using an estimation of the intra uterine pressure. In the selected contractions, the delays between channels will be estimated by cross-correlation, and subsequently, the average EHG conduction velocity will be derived. Patients will be classified as labor group and non-labor group based on the time between measurement and delivery. The average conduction velocity and cervical length will be compared between the groups. The main study endpoints will be sensitivity, specificity, and area under the ROC curve for delivery within 1,2,4,7, and 14 days from the measurement.

Discussion

In this study, the diagnostic accuracy of EHG conduction velocity analysis will be evaluated for detecting preterm labor. Visual and automatic detection of contractions will be compared. Planar wave propagation will be assumed for the calculation of the CV vector.

Trial registration

Current Controlled Trials ISRCTN07603227.

Low-complexity intrauterine pressure estimation using the Teager energy operator on electrohysterographic recordings

Monitoring the progression of maternal uterine activity provides important prognostic information during pregnancy and parturition. Currently used methods for intrauterine pressure (IUP) measurement are unsuitable for long-term observation of uterine activity. The abdominally measured electrohysterogram (EHG) provides a non-invasive alternative to the existing methods for long-term ambulatory uterine contraction monitoring. A new low-complexity method for IUP estimation based on the Teager energy (TE) operator is proposed. The TE operator was used as it mimics the physiologic phenomena underlying the generation of the EHG signals. Several EHG signal analysis methods for IUP estimation from the literature are compared with the new TE method. The comparison is based on correlation and root mean square error of the IUP estimate with the gold standard internally measured IUP as well as their respective computational complexity. The proposed method results in a superior IUP estimation accuracy and complexity compared to state-of-the-art methods from the literature, with a complexity as much as 55 times lower. Therefore, the proposed method offers a valuable new option for long-term ambulatory uterine monitoring.

Velocity and directionality of the electrohysterographic signal propagation

OBJECTIVE

The initiation of treatment for women with threatening preterm labor requires effective distinction between true and false labor. The electrohysterogram (EHG) has shown great promise in estimating and classifying uterine activity. However, key issues remain unresolved and no clinically usable method has yet been presented using EHG. Recent studies have focused on the propagation velocity of the EHG signals as a potential discriminator between true and false labor. These studies have estimated the propagation velocity of individual spikes of the EHG signals. We therefore focus on estimating the propagation velocity of the entire EHG burst recorded during a contraction in two dimensions.

STUDY DESIGN

EHG measurements were performed on six women in active labor at term, and a total of 35 contractions were used for the estimation of propagation velocity. The measurements were performed using a 16-channel two-dimensional electrode grid. The estimates were calculated with a maximum-likelihood approach.

RESULTS

The estimated average propagation velocity was 2.18 (±0.68) cm/s. No single preferred direction of propagation was found.

CONCLUSION

The propagation velocities estimated in this study are similar to those reported in other studies but with a smaller intra- and inter-patient variation. Thus a potential tool has been established for further studies on true and false labor contractions.

Automated conduction velocity analysis in the electrohysterogram for prediction of imminent delivery: a preliminary study

Background. Analysis of the electrohysterogram (EHG) is a promising diagnostic tool for preterm delivery. For the introduction in the clinical practice, analysis of the EHG should be reliable and automated to guarantee reproducibility. Study Goal. Investigating the feasibility of automated analysis of the EHG conduction velocity (CV) for detecting imminent delivery. Materials and Methods. Twenty-two patients presenting with uterine contractions (7 preterm) were included. An EHG was obtained noninvasively using a 64-channel high-density electrode grid. Contractions were selected based on the estimated intrauterine pressure derived from the EHG, the tocodynamometer, and maternal perception. Within the selected contractions, the CV vector was identified in two dimensions. Results. Nine patients delivered within 24 hours and were classified as a labor group. 64 contractions were analyzed; the average amplitude of the CV vector was significantly higher for the labor group, 8.65 cm/s ± 1.90, compared to the nonlabor group, 5.30 cm/s ± 1.47 (P < 0.01). Conclusion. The amplitude of the CV is a promising parameter for predicting imminent (preterm) delivery. Automated estimation of this parameter from the EHG signal is feasible and should be regarded as an important prerequisite for future clinical studies and applications.

Comparison of different EHG feature selection methods for the detection of preterm labor

Numerous types of linear and nonlinear features have been extracted from the electrohysterogram (EHG) in order to classify labor and pregnancy contractions. As a result, the number of available features is now very large. The goal of this study is to reduce the number of features by selecting only the relevant ones which are useful for solving the classification problem. This paper presents three methods for feature subset selection that can be applied to choose the best subsets for classifying labor and pregnancy contractions: an algorithm using the Jeffrey divergence (JD) distance, a sequential forward selection (SFS) algorithm, and a binary particle swarm optimization (BPSO) algorithm. The two last methods are based on a classifier and were tested with three types of classifiers. These methods have allowed us to identify common features which are relevant for contraction classification.

Prediction of preterm deliveries from EHG signals using machine learning

There has been some improvement in the treatment of preterm infants, which has helped to increase their chance of survival. However, the rate of premature births is still globally increasing. As a result, this group of infants are most at risk of developing severe medical conditions that can affect the respiratory, gastrointestinal, immune, central nervous, auditory and visual systems. In extreme cases, this can also lead to long-term conditions, such as cerebral palsy, mental retardation, learning difficulties, including poor health and growth. In the US alone, the societal and economic cost of preterm births, in 2005, was estimated to be $26.2 billion, per annum. In the UK, this value was close to £2.95 billion, in 2009. Many believe that a better understanding of why preterm births occur, and a strategic focus on prevention, will help to improve the health of children and reduce healthcare costs. At present, most methods of preterm birth prediction are subjective. However, a strong body of evidence suggests the analysis of uterine electrical signals (Electrohysterography), could provide a viable way of diagnosing true labour and predict preterm deliveries. Most Electrohysterography studies focus on true labour detection during the final seven days, before labour. The challenge is to utilise Electrohysterography techniques to predict preterm delivery earlier in the pregnancy. This paper explores this idea further and presents a supervised machine learning approach that classifies term and preterm records, using an open source dataset containing 300 records (38 preterm and 262 term). The synthetic minority oversampling technique is used to oversample the minority preterm class, and cross validation techniques, are used to evaluate the dataset against other similar studies. Our approach shows an improvement on existing studies with 96% sensitivity, 90% specificity, and a 95% area under the curve value with 8% global error using the polynomial classifier.

Characterization of EHG contractions at term labor by nonlinear analysis

Uterine electromyogram on the abdomen of pregnant women (electrohysterogram, EHG) plays an interesting role to evaluate possible risks to the binomial mother-fetus. In this sense, the present study explored the characterization of contractions by EHG during active phase of labor at term in a population at low risk. The goal was to investigate the differences in the contractions generated by women that evolve labor to a vaginal delivery (group 1) to those associated with caesarean section (group 2). Abdominal signals were acquired using Ag-AgCl electrodes in a bipolar configuration and the EHG was obtained by band-pass filtering in the range of 0.3 to 4 Hz. Sample entropy (SampEn) was used to calculate the irregularity of manually selected contractions of the EHG time series. The results showed that it is plausible to discriminate contractions from both groups as the average SampEn was 2.1359 with a standard deviation of 0.0583 for group 1 (N=8), while for group 2 (N=8) was 2.0352 with standard deviation of 0.0946; it was found significant statistical difference between groups as p was 0.046. Consequently, the nonlinear analysis via SampEn of EHG could provide an index to evaluate the quality of the active phase labor at term.

Effect of an oxytocin receptor antagonist (atosiban) on uterine electrical activity

OBJECTIVE

The purpose of this study was to investigate the effect of atosiban (Tractocile; Ferring, Limhamn, Sweden), an oxytocin receptor antagonist, on uterine electrical activity in women with preterm labor and to determine whether this information can assist in the prediction of preterm delivery.

STUDY DESIGN

Uterine electrical activity was recorded prospectively in 21 women with preterm labor before and during treatment with Tractocile and, for purpose of comparison, in 4 pregnant women without uterine contractions to set the baseline of uterine electrical activity in a quiescent uterus. Uterine activity was recorded with a noninvasive, 9-channel recorder with an electromyography amplifier and a 3-dimensional position sensor with an automatic data analyzer. Uterine electrical activity was quantified by an electrical uterine monitor (EUM) and measured in microwatts per second (μW/s).

RESULTS

The overall pre-Tractocile EUM index was 3.43 ± 0.58 μW/s, which was significantly higher than baseline uterine activity in women without preterm contractions (2.3 ± 0.11 μW/s; P = .001). During the administration of Tractocile, the EUM index gradually decreased in a relatively constant rate from 3.43 ± 0.58 μW/s to 2.56 ± 0.88 μW/s after 330 minutes of continuous therapy (P < .001). The peak effect of Tractocile was observed 4 hours after the initiation of treatment and was followed by a relative plateau. Women with a latency of <7 days from treatment to delivery were characterized by a distinct EUM-pattern in response to Tractocile, compared with women with a latency of ≥7 days (P < .001). A similar EUM-pattern after the administration of Tractocile was also observed for women who delivered at <37 weeks of gestation compared with the women who delivered at term.

CONCLUSION

Tractocile reduces uterine electrical activity in women with preterm labor. This information can provide more insight into the effects of tocolytic agents and to aid in the risk stratification of preterm delivery in women with preterm contractions.

Assessment of parturition with cervical light-induced fluorescence and uterine electromyography

Parturition involves increasing compliance (ripening) of the uterine cervix and activation of the myometrium. These processes take place in a different time frame. Softening and shortening of the cervix starts in midpregnancy, while myometrial activation occurs relatively close to delivery. Methods currently available to clinicians to assess cervical and myometrial changes are subjective and inaccurate, which often causes misjudgments with potentially adverse consequences. The inability to reliably diagnose true preterm labor leads to unnecessary treatments, missed opportunities to improve neonatal outcome, and inherently biased research of treatments. At term, the likelihood of cesarean delivery depends on labor management, which in turn depends on accurate assessments of cervical change and myometrial contractility. Studies from our group and others show that noninvasive measurements of light-induced fluorescence (LIF) of cervical collagen and uterine electromyography (EMG) objectively detect changes in the composition of the cervix and myometrial preparedness to labor and are more reliable than clinical observations alone. We present a conceptual model of parturition constructed on cervical LIF and uterine EMG studies. We also explore how these methodologies could be helpful with managing patients experiencing preterm contractions and with optimizing labor management protocols aimed to reduce cesarean section.

Automatic evaluation of progression angle and fetal head station through intrapartum echographic monitoring

Labor progression is routinely assessed through transvaginal digital inspections, meaning that the clinical decisions taken during the most delicate phase of pregnancy are subjective and scarcely supported by technological devices. In response to such inadequacies, we combined intrapartum echographic acquisitions with advanced tracking algorithms in a new method for noninvasive, quantitative, and automatic monitoring of labor. Aim of this work is the preliminary clinical validation and accuracy evaluation of our automatic algorithm in assessing progression angle (PA) and fetal head station (FHS). A cohort of 10 parturients underwent conventional labor management, with additional translabial echographic examinations after each uterine contraction. PA and FHS were evaluated by our automatic algorithm on the acquired images. Additionally, an experienced clinical sonographer, blinded regarding the algorithm results, quantified on the same acquisitions of the two parameters through manual contouring, which were considered as the standard reference in the evaluation of automatic algorithm and routine method accuracies. The automatic algorithm (mean error ± 2SD) provided a global accuracy of 0.9 ± 4.0 mm for FHS and 4° ± 9° for PA, which is far above the diagnostic ability shown by the routine method, and therefore it resulted in a reliable method for earlier identification of abnormal labor patterns in support of clinical decisions.

Costs of unnecessary admissions and treatments for "threatened preterm labor"

OBJECTIVE

Cervical length (CL) of 3 cm or greater has been shown to have a 97-99% negative predictive value for preterm delivery in women with threatened preterm labor. Consequently, hospitalization and treatment are not indicated in these patients. We analyzed how often patients with a CL of 3 cm or greater are still being admitted and treated for preterm labor and how much this contributes to the economic burden of preterm labor hospitalizations.

STUDY DESIGN

Twelve month hospitalizations for preterm labor at less than 34 weeks at a single institution were reviewed and patients with a CL of 3 cm or greater were identified. We chose to use patients' hospital charges as a surrogate for health care costs, recognizing that charges are not synonymous with the final patient bill and also do not reflect additional costs such as the cost of treatment at the referring facility, transportation, physician fees, and other such costs as lost wages, need for additional child care, etc.

RESULTS

Between July 2009 and June 2010, 139 patients were admitted and treated for preterm labor at our level III center. Fifty of these patients (36%) had a CL of 3 cm or greater. None of them delivered preterm. Total hospital charges for the management of these patients were $1,018 589 (mean, $20,372; median, $14,444).

CONCLUSION

Unnecessary admissions and treatments for threatened preterm labor are part of clinical practice and contribute to exploding health care costs. Using currently available diagnostics, these costs could be lowered significantly without jeopardizing outcome.

Electrohysterography of labor contractions: propagation velocity and direction

OBJECTIVE

Electrohysterographic assessment of the propagation velocity of uterine depolarization has been introduced as a promising predictor of preterm labor. Therefore, the objectives of this study were to characterize the uterine electrohysterographic signals during labor and to determine the propagation velocity and propagation direction of electrohysterographic signals.

DESIGN

Descriptive study.

SETTING

Department of Obstetrics and Gynecology, Aarhus University Hospital, Denmark.

POPULATION

Eight women in active labor at term.

METHODS

Electrohysterograms (three channels) were recorded using surface electrodes placed abdominally along the vertical median axis with an inter-electrode distance of 6.5-11.2 cm. In total, 89 contractions were analyzed.

RESULTS

Electrohysterographic characteristics: The duration of the contractions was 61.0 ± 18.0 s (mean ± SD). The median frequency of the power spectrum density was 0.51 (0.44; 0.51) Hz (median; 10th; 90th percentile). The greatest signal magnitude was obtained by the electrode in the centermost position. The propagation velocity: 2.15 (0.66; 13.8) cm/s in the upper part and 1.53 (0.58; 6.7) cm/s in the lower part of the uterus. Propagation direction: Both downward (58%) and upward (42%) propagation of the electrohysterographic signals occurred. Moreover, downward and upward propagations were recorded simultaneously in the upper and lower part of the uterus, suggesting a multidirectional propagation pattern.

CONCLUSIONS

Labor contractions, expressed by electrohysterographic signals, propagate both in the downward and upward direction, a phenomenon that must be taken into account when determining the propagation velocity for preterm labor diagnostics.

Abdominal electromyography in laboring and non-laboring pregnant women at term and its clinical implications

OBJECTIVE

To determine the patterns of uterine action potentials in laboring and non-laboring women at term using the non-invasive abdominal electromyography technique.

METHODS

One hundred pregnant women at term who fulfilled the inclusion criteria were enrolled in the study and equally divided into two groups. Group I consisted of 50 women in active labor, while group II included 50 women not in labor. After enrollment, the cardiotocograph was applied to all women. Abdominal electromyographic recording was started and for every burst of action potential, we measured the amplitude, frequency and duration of action potential. The results were tabulated and statistically analyzed.

RESULTS

Both groups were comparable in demographic characteristics. Four patterns of EMG were detected. The amplitude of action potentials was significantly higher in laboring compared to non-laboring women (77.44 ± 11.25 vs 13.71 ± 8.57, P < 0.001). Similar significantly longer durations of electrical bursts were also noted in laboring women (45.94 ± 8.77 vs 7.11 ± 4.68 s, P < 0.001). Specific electromyographic changes were noted in women passing from the non-laboring to laboring state and in women who required oxytocin augmentation during labor.

CONCLUSION

Abdominal electromyography may help to distinguish between women in true active labor from those who are not. It also may help to identify women who will enter into labor within 24-72 h and those who require augmentation of labor.

Better pregnancy monitoring using nonlinear correlation analysis of external uterine electromyography

The objective of this paper is to evaluate the novel method for analyzing the nonlinear correlation of the uterine electromyography (EMG). The application of this method may improve monitoring in pregnancy, labor detection, and preterm labor detection. Uterine EMG signals recorded from a 4 × 4 matrix of electrodes on the subjects' abdomen are used here. The propagation was analyzed using the nonlinear correlation coefficient h(2). Signals from 49 women (36 during pregnancy and 13 in labor) at different gestational age were used. ROC curves were computed to evaluate the potential of three methods to differentiate between 174 contractions recorded during pregnancy and 115 contractions recorded during labor. The results indicate considerably better performance of the nonlinear correlation analysis (area under curve = 0.85) when compared to classical frequency parameters (area under curve = 0.76 and 0.66) in distinguishing labor contractions from normal pregnancy contractions. We conclude that the analysis of the propagation of the uterine electrical activity using the nonlinear correlation coefficient h(2) is a promising way of improving the usefulness of uterine EMG signals for clinical purposes, such as monitoring in pregnancy, labor detection, and prediction of preterm labor.

Classification performance of the frequency-related parameters derived from uterine EMG signals

Frequency-related parameters derived from the uterine electromyogram (EMG) signals are widely used in many pregnancy monitoring and preterm delivery prediction studies. Although they are classical parameters, they are well suited for quantifying uterine EMG signals and have many advantages over amplitude-related parameters. The present work aims to compare various frequency-related parameters according to their classification performances (pregnancy vs. labor) using the receiver operating characteristic (ROC) curve analysis. The comparison between the parameters indicates that median frequency is the best frequency-related parameter that can be used for distinguishing between pregnancy and labor contractions. We conclude that median frequency can be the representative frequency-related parameter for classification problems of uterine EMG.

Classification of multichannel uterine EMG signals

Classification of multichannel uterine electromyogram (EMG) signals is addressed. Signals were recorded by a matrix of 16 electrodes. First, signals corresponding to each channel were individually classified using an artificial neural network (ANN) based on radial basis functions (RBF). The results have shown that the classification performance varies from one channel to another. Then, a decision fusion method based on these classification performances was tested. After fusion, the network yielded better classification accuracy than any individual channel could provide. The high percentage of correctly classified labor/non-labor events proves the efficiency of multichannel recordings in detecting labor. These findings can be very useful for the aim of classifying antepartum versus labor patients.

Conduction velocity of the uterine contraction in serial magnetomyogram (MMG) data: event based simulation and validation

We propose a novel approach to calculate the conduction velocity (CV) of the uterine contraction bursts in magnetomyogram (MMG) signals measured using a multichannel SQUID array. For this purpose, we partition the sensor coordinates into four different quadrants and identify the contractile bursts using a previously proposed Hilbert-wavelet transform approach. If contractile burst is identified in more than one quadrant, we calculate the center of gravity (CoG) in each quadrant for each time point as the sum of the product of the sensor coordinates with the Hilbert amplitude of the MMG signals normalized by the sum of the Hilbert amplitude of the signals over all sensors. Following this we compute the delay between the CoGs of all (six) possible quadrant pairs combinations. As a first step, we validate this approach by simulating a stochastic model based on independent second-order autoregressive processes (AR2) and we divide them into 30 second disjoint windows and insert burst activity at specific time instances in preselected sensors. Also we introduce a lag of 5 ± 1 seconds between different quadrants. Using our approach we calculate the CoG of the signals in a quadrant. To this end, we compute the delay between CoGs obtained from different quadrants and show that our approach is able to reliably capture the delay incorporated in the model. We apply the proposed approach to 19 serial MMG data obtained from two subjects and show an increase in the CV as the subjects approached labor.

Progestin treatment for the prevention of preterm birth

Progestin supplementation appears to be a promising approach to both preventing initiation of preterm labor and treating it once it is already established, given the role of progesterone in maintaining pregnancy, as well as support from basic and clinical research. Progesterone and 17α-hydroxyprogesterone acetate slow the process of cervical ripening, and this is the rationale for prophylactic long-term progestin supplementation mostly studied so far. However, progesterone (but not 17α-hydroxyprogesterone acetate) also inhibits myometrial activity even after the cervix has already ripened. Moreover, these effects depend greatly on the vehicle used and the route of administration. Understanding different mechanisms of action, as well as the importance of progestin formulation, vehicle and route of administration, is the key to finding the optimal progestin treatment for prevention of preterm birth.

Nonlinearity of EHG signals used to distinguish active labor from normal pregnancy contractions

Labor prediction using the electrohysterogram has immediate clinical applications and has been the aim of several studies in recent years. Studies using various linear methods such as classic spectral analysis do not give clinically useful results. In this paper we present the use of two methods that investigate nonlinearity to predict normal labor. We show the comparison between a linear method that is known from the literature (mean power frequency) and two nonlinear methods (approximate entropy and time reversibility) using ROC analysis. The comparison indicates that the best method for pretreatment to classify pregnancy and labor signals is time reversibility. The results indicate that time reversibility is a very promising tool for distinguishing between labor and physiological contractions during pregnancy. This could be the first step in developing a clinical application method to predict preterm labor.