Automatic semantic segmentation of EHG recordings by deep learning: An approach to a screening tool for use in clinical practice.

BACKGROUND AND OBJECTIVE: Preterm delivery is an important factor in the disease burden of the newborn and infants worldwide. Electrohysterography (EHG) has become a promising technique for predicting this condition, thanks to its high degree of sensitivity. Despite the technological progress made in predicting preterm labor, its use in clinical practice is still limited, one of the main barriers being the lack of tools for automatic signal processing without expert supervision, i.e. automatic screening of motion and respiratory artifacts in EHG records. Our main objective was thus to design and validate an automatic system of segmenting and screening the physiological segments of uterine origin in EHG records for robust characterization of uterine myoelectric activity, predicting preterm labor and help to promote the transferability of the EHG technique to clinical practice. METHODS: For this, we combined 300 EHG recordings from the TPEHG DS database and 69 EHG recordings from our own database (Ci2B-La Fe) of women with singleton gestations. This dataset was used to train and evaluate U-Net, U-Net++, and U-Net 3+ for semantic segmentation of the physiological and artifacted segments of EHG signals. The model's predictions were then fine-tuned by post-processing. RESULTS: U-Net 3+ outperformed the other models, achieving an area under the ROC curve of 91.4 % and an average precision of 96.4 % in detecting physiological activity. Thresholds from 0.6 to 0.8 achieved precision from 93.7 % to 97.4 % and specificity from 81.7 % to 94.5 %, detecting high-quality physiological segments while maintaining a trade-off between recall and specificity. Post-processing improved the model's adaptability by fine-tuning both the physiological and corrupted segments, ensuring accurate artifact detection while maintaining physiological segment integrity in EHG signals. CONCLUSIONS: As automatic segmentation proved to be as effective as double-blind manual segmentation in predicting preterm labor, this automatic segmentation tool fills a crucial gap in the existing preterm delivery prediction system workflow by eliminating the need for double-blind segmentation by experts and facilitates the practical clinical use of EHG. This work potentially contributes to the early detection of authentic preterm labor women and will allow clinicians to design individual patient strategies for maternal health surveillance systems and predict adverse pregnancy outcomes.

A randomized controlled trial reducing cesarean delivery rates in China by introducing trial of labor after cesarean and electrohysterography.

OBJECTIVE: A cesarean delivery (CD) can affect health of both mother and child and future pregnancies. Since the abandonment of the one-child policy in China, obstetricians tend to perform a repeat CD rather than a trial of labor after cesarean (TOLAC). This study aims to reduce CD rates by increasing vaginal births after cesarean (VBAC) rates and introducing electrohysterography (EHG) for accurate monitoring. METHODS: In total, 82 women received counseling regarding TOLAC at the Shijiazhuang Sixth Hospital in China. Women opting for TOLAC were randomized for either external tocodynamometry (TOCO, i.e. standard care) or EHG. The primary outcome was the VBAC rate. Secondary outcomes were indications for CD, percentage of assisted vaginal deliveries, labor duration, maternal blood loss, complications and neonatal outcomes. RESULTS: After accounting for preterm delivery and dropouts, all counseled women opted for a TOLAC (100%). After randomization, 42 women were included in the TOCO-group and 37 in the EHG-group. Women did not receive pain medication and labor was not augmented with oxytocin. The VBAC rate was 71.4% in the TOCO-group, versus 78.4% in the EHG-group (p = .48). Birth was assisted with forceps in 11.9% of TOCO-group versus 2.7% of EHG-group (p = .21). One secondary CD (i.e. a shift from intended vaginal delivery to surgical delivery within the same labor) was performed because of a suspicion of uterine rupture (TOCO-group). Other indications for CD were: fetal distress, labor dystocia, fetal position, cephalopelvic disproportion. There were no significant differences in secondary study outcomes. No complications were reported. CONCLUSION: This study showed an average VBAC rate of 75%, without any complications, in a hospital with no previous experience with TOLAC. The VBAC rate with EHG-monitoring was higher than TOCO, although this difference was not significant. To demonstrate a significant difference, larger clinical studies are necessary. TRIAL REGISTRATION: The Daily Board of the Medical Ethics Committee of The Maternal and Child Hospital of Shijiazhuang approved the study protocol (number 20171018, Dutch Trial Register NL8199).

Multi-channel electrohysterography enabled uterine contraction characterization and its effect in delivery assessment.

Uterine contractions are routinely monitored by tocodynamometer (TOCO) at late stage of pregnancy to predict the onset of labor. However, TOCO reveals no information on the synchrony and coherence of contractions, which are important contributors to a successful delivery. The electrohysterography (EHG) is a recording of the electrical activities that trigger the local muscles to contract. The spatial-temporal information embedded in multiple channel EHG signals make them ideal for characterizing the synchrony and coherence of uterine contraction. To proceed, contractile time-windows are identified from TOCO signals and are then used to segment out the simultaneously recorded EHG signals of different channels. We construct sample entropy SamEn and Concordance Correlation based feature ψ from these EHG segments to quantify the synchrony and coherence of contraction. To test the effectiveness of the proposed method, 122 EHG recordings in the Icelandic EHG database were divided into two groups according to the time difference between the gestational ages at recording and at delivery (TTD). Both SamEn and ψ show clear difference in the two groups (p<10-5) even when measurements were made 120 h before delivery. Receiver operating characteristic curve analysis of these two features gave AUC values of 0.834 and 0.726 for discriminating imminent labor defined with TTD ≤ 24 h. The SamEn was significantly smaller in women (0.1433) of imminent labor group than in women (0.3774) of the pregnancy group. Using an optimal cutoff value of SamEn to identify imminent labor gives sensitivity, specificity, and accuracy as high as 0.909, 0.712 and 0.743, respectively. These results demonstrate superiority in comparing to the existing SOTA methods. This study is the first research work focusing on characterizing the synchrony property of contractions from the electrohysterography signals. Despite the very limited dataset used in the validation process, the promising results open a new direction to the use of electrohysterography in obstetrics.

Detection of postpartum uterine activity with electrohysterography.

OBJECTIVE: Uterine contractions are essential for childbirth, but also for expulsion of the placenta and for limiting postpartum blood loss. Postpartum hemorrhage is associated with almost 25% of the maternal deaths worldwide and the leading cause of maternal death in most low-income countries. Little is known about the physiology of the uterus postpartum, particularly due to the lack of an accurate measurement tool. The primary objective of this pilot study is to explore the potential of using electrohysterography to detect postpartum uterine contractions. If postpartum uterine activity can be objectified, this could contribute to understanding the physiology of the uterus and improve diagnosis and treatment of postpartum hemorrhage. STUDY DESIGN: In this observational study we included women aiming for a vaginal birth in two large maternity clinics in the Netherlands, Amphia Hospital Breda (group A, N2018-0161) and Máxima Medical Center Veldhoven (group B, N17.149). An electrode patch was placed on the maternal abdomen to record real-time electrical uterine activity until one hour postpartum continuously. In group A, the placement of the patch was lower than in group B. For analysis, tracings were divided into five different phases (1: dilatation until start pushing, 2: from start pushing until childbirth, 3: from childbirth until placental expulsion, 4: first hour after placental expulsion and 5: after one hour postpartum). Readability, signal quality and contraction frequency per hour were assessed. Additionally, patient satisfaction was evaluated through a survey. RESULTS: In total 91 pregnant women were included of whom 45 in group A and 46 women in group B. Complete registrations were obtained throughout the five labor phases with very little artefacts or signal loss. The readability of the tracings decreased after childbirth. A significantly better readability was found in tracings where the patch placement was lower on the abdomen for phases 4 and 5. Contraction frequency was highest during phase 2 and decreased towards phase 5. Women rated the satisfaction with electrohysterography as high and mostly did not notice the patch. CONCLUSION: It is possible to detect uterine activity postpartum with electrohysterography. Further investigation is recommended to improve diagnosis and treatment of postpartum hemorrhage.

Implementation of the combined use of non-invasive fetal electrocardiography and electrohysterography during labor: A prospective clinical study.

INTRODUCTION: Fetal electrocardiography (NI-fECG) and electrohysterography (EHG) have been proven more accurate and reliable than conventional non-invasive methods (doppler ultrasound and tocodynamometry) and are less affected by maternal obesity. It is still unknown whether NI-fECG and EHG will eliminate the need for invasive methods, such as the intrauterine pressure catheter and fetal scalp electrode. We studied whether NI-fECG and EHG can be successfully used during labor. MATERIAL AND METHODS: A prospective clinical pilot study was performed in a tertiary care teaching hospital. A total of 50 women were included with a singleton pregnancy with a gestational age between 36+0 and 42+0 weeks and had an indication for continuous intrapartum monitoring. The primary study outcome was the percentage of women with NI-fECG and EHG monitoring throughout the whole delivery. Secondary study outcomes were reason and timing of a switch to conventional monitoring methods (i.e., tocodynamometry and fetal scalp electrode or doppler ultrasound), repositioning of the abdominal electrode patch, success rates (i.e., the percentage of time with signal output), and obstetric and neonatal outcomes. CLINICAL TRIAL REGISTRATION: Dutch trial register (NL8024). RESULTS: In 45 women (90%), NI-fECG and EHG monitoring was used throughout the whole delivery. In the other five women (10%), there was a switch to conventional methods: in two women because of insufficient registration quality of uterine contractions and in three women because of insufficient registration quality of the fetal heart rate. In three out of five cases, the switch was after full dilation was reached. Repositioning of the abdominal electrode patch occurred in two women. The overall success rate was 94.5%. In 16% (n = 8) of women, a cesarean delivery was performed due to non-progressing dilation (n = 7) and due to suspicion of fetal distress (n = 1). Neonatal metabolic acidosis did not occur. Two neonates (4%) were admitted to the neonatal intensive care unit for complications not related to intrapartum monitoring. CONCLUSIONS: NI-fECG and EHG can be successfully used during labor in 90% of women. Future research is needed to conclude whether implementation of electrophysiological monitoring can improve obstetric and neonatal outcomes.

End-to-end learning with interpretation on electrohysterography data to predict preterm birth.

Prediction of preterm birth is a difficult task for clinicians. By examining an electrohysterogram, electrical activity of the uterus that can lead to preterm birth can be detected. Since signals associated with uterine activity are difficult to interpret for clinicians without a background in signal processing, machine learning may be a viable solution. We are the first to employ Deep Learning models, a long-short term memory and temporal convolutional network model, on electrohysterography data using the Term-Preterm Electrohysterogram database. We show that end-to-end learning achieves an AUC score of 0.58, which is comparable to machine learning models that use handcrafted features. Moreover, we evaluate the effect of adding clinical data to the model and conclude that adding the available clinical data to electrohysterography data does not result in a gain in performance. Also, we propose an interpretability framework for time series classification that is well-suited to use in case of limited data, as opposed to existing methods that require large amounts of data. Clinicians with extensive work experience as gynaecologist used our framework to provide insights on how to link our results to clinical practice and stress that in order to decrease the number of false positives, a dataset with patients at high risk of preterm birth should be collected. All code is made publicly available.

Experiences with intrapartum fetal monitoring in the Netherlands: A survey study.

INTRODUCTION: Worldwide, cardiotocography is used for continuous monitoring of fetal heart rate (FHR) and uterine contractions during labour. Different methods for FHR registration and registration of contractions are available. Literature about the frequency of use of different fetal monitoring methods is lacking. OBJECTIVE: To evaluate the use of and preferences for fetal monitoring methods for intrapartum fetal monitoring among Dutch obstetric care providers. STUDY DESIGN: Between October and November 2020 the Dutch Society of Obstetrics and Gynaecology sent an email invitation to all secondary care midwives and gynaecologists (in training) in the Netherlands to complete an online survey regarding the use and personal experience with fetal monitoring methods. The survey mainly consisted of multiple choice questions. Descriptive statistics are reported. Continuous variables were presented as median with interquartile ranges (IQR). Categorical variables were expressed as numbers with percentages. RESULTS: The response rate was 29 % (n/N = 510/1748). All Dutch hospitals were represented. The respondents estimated the use of fetal scalp electrode (FSE) at 71 % (IQR 58-85 %) of deliveries. The most common indication for use of the FSE was inadequate external FHR registration (94 %). More than half (54 %) of the respondents reported to use intrauterine pressure catheter with an estimated use of 5 % (IQR 2-8 %) of deliveries. The most common indication for use of intrauterine pressure catheter was inadequate external contraction registration (75 %). The use of ST-analysis was reported in 25 % of the respondents with an estimated use of 60 % (IQR 30-72 %) of deliveries. Almost all respondents (99 %) reported to use fetal blood sampling with an estimated use of 15 % (IQR 10-23 %) of deliveries. Ninety percent of respondents would prefer a valid and reliable external monitoring technique during labour. Thirty-one percent of respondents assume that external fetal monitoring with non-invasive fetal electrocardiography and electrohysterography will become standard care within the next 5 years. CONCLUSIONS: Currently, the FSE is the most used technique for FHR monitoring during labour in the Netherlands. The most common indication for use of FSE is inadequate external FHR registration. Obstetric care providers would prefer a non-invasive external registration method that provides reliable data.

Combination of Feature Selection and Resampling Methods to Predict Preterm Birth Based on Electrohysterographic Signals from Imbalance Data.

Due to its high sensitivity, electrohysterography (EHG) has emerged as an alternative technique for predicting preterm labor. The main obstacle in designing preterm labor prediction models is the inherent preterm/term imbalance ratio, which can give rise to relatively low performance. Numerous studies obtained promising preterm labor prediction results using the synthetic minority oversampling technique. However, these studies generally overestimate mathematical models' real generalization capacity by generating synthetic data before splitting the dataset, leaking information between the training and testing partitions and thus reducing the complexity of the classification task. In this work, we analyzed the effect of combining feature selection and resampling methods to overcome the class imbalance problem for predicting preterm labor by EHG. We assessed undersampling, oversampling, and hybrid methods applied to the training and validation dataset during feature selection by genetic algorithm, and analyzed the resampling effect on training data after obtaining the optimized feature subset. The best strategy consisted of undersampling the majority class of the validation dataset to 1:1 during feature selection, without subsequent resampling of the training data, achieving an AUC of 94.5 ± 4.6%, average precision of 84.5 ± 11.7%, maximum F1-score of 79.6 ± 13.8%, and recall of 89.8 ± 12.1%. Our results outperformed the techniques currently used in clinical practice, suggesting the EHG could be used to predict preterm labor in clinics.

[An EHG-based Preterm Delivery Prediction Algorithm via Convolution Neural Network].

Premature delivery is one of the direct factors that affect the early development and safety of infants. Its direct clinical manifestation is the change of uterine contraction intensity and frequency. Uterine Electrohysterography(EHG) signal collected from the abdomen of pregnant women can accurately and effectively reflect the uterine contraction, which has higher clinical application value than invasive monitoring technology such as intrauterine pressure catheter. Therefore, the research of fetal preterm birth recognition algorithm based on EHG is particularly important for perinatal fetal monitoring. We proposed a convolution neural network(CNN) based on EHG fetal preterm birth recognition algorithm, and a deep CNN model was constructed by combining the Gramian angular difference field(GADF) with the transfer learning technology. The structure of the model was optimized using the clinical measured term-preterm EHG database. The classification accuracy of 94.38% and F1 value of 97.11% were achieved. The experimental results showed that the model constructed in this paper has a certain auxiliary diagnostic value for clinical prediction of premature delivery.

Identification of Contractions from Electrohysterography for Prediction of Prolonged Labor.

The analysis of the uterine electrical activity and its propagation patterns could potentially predict the risk of prolonged/arrested progress of labor. In our study, the Electrohysterography (EHG) signals of 83 participants in labor at around 3-4 cm of cervical dilatation, were recorded for about 30 minutes each. These signals were analyzed for predicting prolonged labor. Out of the 83 participants, 70 participants had normal progress of labor and delivered vaginally. The remaining 13 participants had prolonged/ arrested progress of labor and had to deliver through a cesarean section. In this paper, we propose an algorithm to identify contractions from the acquired EHG signals based on the energy of the signals. The role of contraction consistency and fundal dominance was evaluated for impact on progress of the labor. As per our study, the correlation of contractions was higher in case of normal progress of labor. We also observed that the upper uterine segment was dominant in cases with prolonged/arrested progress of labor.

Enhancing classification of preterm-term birth using continuous wavelet transform and entropy-based methods of electrohysterogram signals.

Introduction: Despite vast research, premature birth's electrophysiological mechanisms are not fully understood. Prediction of preterm birth contributes to child survival by providing timely and skilled care to both mother and child. Electrohysterography is an affordable, noninvasive technique that has been highly sensitive in diagnosing preterm labor. This study aimed to choose the more appropriate combination of characteristics, such as electrode channel and bandwidth, as well as those linear, time-frequency, and nonlinear features of the electrohysterogram (EHG) for predicting preterm birth using classifiers. Methods: We analyzed two open-access datasets of 30 minutes of EHG obtained in regular checkups of women around 31 weeks of pregnancy who experienced premature labor (P) and term labor (T). The current approach filtered the raw EHGs in three relevant frequency subbands (0.3-1 Hz, 1-2 Hz, and 2-3Hz). The EHG time series were then segmented to create 120-second windows, from which individual characteristics were calculated. The linear, time-frequency, and nonlinear indices of EHG of each combination (channel-filter) were fed to different classifiers using feature selection techniques. Results: The best performance, i.e., 88.52% accuracy, 83.83% sensitivity, and 93.22% specificity, was obtained in the 2-3 Hz bands using Medium Frequency, Continuous Wavelet Transform (CWT), and entropy-based indices. Interestingly, CWT features were significantly different in all filter-channel combinations. The proposed study uses small samples of EHG signals to diagnose preterm birth accurately, showing their potential application in the clinical environment. Discussion: Our results suggest that CWT and novel entropy-based features of EHG could be suitable descriptors for analyzing and understanding the complex nature of preterm labor mechanisms.

Association between Increased Uterine Activity, as Recorded Noninvasively from the Anterior Abdominal Wall at 34 Weeks' Gestation, and Preterm Birth.

Background: There is a need to accurately identify pregnant women at risk for preterm birth as early as possible. Recent developments in technology enable the recording of uterine electrical activity (electrohysterogram) from the anterior abdominal wall in a non-invasive way. Objective: To investigate whether uterine activity recorded under resting conditions at a gestational age of 34 weeks could identify a risk of preterm birth. Study design: A commercial antenatal holter device with its dedicated software was used to record and store raw data of the maternal and fetal electrocardiograms and uterine activity for the Safe Passage Study. Uterine activity was recorded under resting conditions from 34 weeks' gestation in epochs of 250 ms (millisecond) for at least 30 min. From this database the raw data, recorded at a mean gestational age of 34 weeks, of 50 women who had preterm deliveries were selected for comparison with data of women who had term deliveries. Mean uterine activity, expressed in microvolt (µV)/epoch, was used for the comparison. Results: After exclusion of 25 participants where labour was induced or augmented and another three for other reasons, 36 remained in each group. The participants in each group were comparable in respect of maternal age, gravidity, parity, gestational age at recruitment and duration of recording. Uterine activity in the preterm group (60.3 µV/epoch) differed significantly (p<0.01) from that of the comparison group (52.4 µV/epoch). Using a cut-off point of 52.3 µV/epoch as obtained from receiver operator characteristic curves (area under the curve 0.72), the sensitivity and specificity of identifying risks of preterm labour were 81% and 50% respectively. Conclusion: Results of this small study are promising but need to be confirmed in larger studies and preferably at earlier gestational age.

Non-invasive fetal electrocardiography, electrohysterography and speckle-tracking echocardiography in the second trimester: study protocol of a longitudinal prospective cohort study (BEATS-study).

BACKGROUND: Worldwide, hypertensive disorders of pregnancy (HDP), fetal growth restriction (FGR) and preterm birth remain the leading causes of maternal and fetal pregnancy-related mortality and (long-term) morbidity. Fetal cardiac deformation changes can be the first sign of placental dysfunction, which is associated with HDP, FGR and preterm birth. In addition, preterm birth is likely associated with changes in electrical activity across the uterine muscle. Therefore, fetal cardiac function and uterine activity can be used for the early detection of these complications in pregnancy. Fetal cardiac function and uterine activity can be assessed by two-dimensional speckle-tracking echocardiography (2D-STE), non-invasive fetal electrocardiography (NI-fECG), and electrohysterography (EHG). This study aims to generate reference values for 2D-STE, NI-fECG and EHG parameters during the second trimester of pregnancy and to investigate the diagnostic potential of these parameters in the early detection of HDP, FGR and preterm birth. METHODS: In this longitudinal prospective cohort study, eligible women will be recruited from a tertiary care hospital and a primary midwifery practice. In total, 594 initially healthy pregnant women with an uncomplicated singleton pregnancy will be included. Recordings of NI-fECG and EHG will be made weekly from 22 until 28 weeks of gestation and 2D-STE measurements will be performed 4-weekly at 16, 20, 24 and 28 weeks gestational age. Retrospectively, pregnancies complicated with pregnancy-related diseases will be excluded from the cohort. Reference values for 2D-STE, NI-fECG and EHG parameters will be assessed in uncomplicated pregnancies. After, 2D-STE, NI-fCG and EHG parameters measured during gestation in complicated pregnancies will be compared with these reference values. DISCUSSION: This will be the a large prospective study investigating new technologies that could potentially have a high impact on antepartum fetal monitoring. TRIAL REGISTRATION: Registered on 26 March 2020 in the Dutch Trial Register (NL8769) via https://www.trialregister.nl/trials and registered on 21 October 2020 to the Central Committee on Research Involving Human Subjects (NL73607.015.20) via https://www.toetsingonline.nl/to/ccmo_search.nsf/Searchform?OpenForm .

Advanced Bioelectrical Signal Processing Methods: Past, Present, and Future Approach-Part III: Other Biosignals.

Analysis of biomedical signals is a very challenging task involving implementation of various advanced signal processing methods. This area is rapidly developing. This paper is a Part III paper, where the most popular and efficient digital signal processing methods are presented. This paper covers the following bioelectrical signals and their processing methods: electromyography (EMG), electroneurography (ENG), electrogastrography (EGG), electrooculography (EOG), electroretinography (ERG), and electrohysterography (EHG).

Assessment of Dispersion and Bubble Entropy Measures for Enhancing Preterm Birth Prediction Based on Electrohysterographic Signals.

One of the remaining challenges for the scientific-technical community is predicting preterm births, for which electrohysterography (EHG) has emerged as a highly sensitive prediction technique. Sample and fuzzy entropy have been used to characterize EHG signals, although they require optimizing many internal parameters. Both bubble entropy, which only requires one internal parameter, and dispersion entropy, which can detect any changes in frequency and amplitude, have been proposed to characterize biomedical signals. In this work, we attempted to determine the clinical value of these entropy measures for predicting preterm birth by analyzing their discriminatory capacity as an individual feature and their complementarity to other EHG characteristics by developing six prediction models using obstetrical data, linear and non-linear EHG features, and linear discriminant analysis using a genetic algorithm to select the features. Both dispersion and bubble entropy better discriminated between the preterm and term groups than sample, spectral, and fuzzy entropy. Entropy metrics provided complementary information to linear features, and indeed, the improvement in model performance by including other non-linear features was negligible. The best model performance obtained an F1-score of 90.1 ± 2% for testing the dataset. This model can easily be adapted to real-time applications, thereby contributing to the transferability of the EHG technique to clinical practice.

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.

Optimized Feature Subset Selection Using Genetic Algorithm for Preterm Labor Prediction Based on Electrohysterography.

Electrohysterography (EHG) has emerged as an alternative technique to predict preterm labor, which still remains a challenge for the scientific-technical community. Based on EHG parameters, complex classification algorithms involving non-linear transformation of the input features, which clinicians found difficult to interpret, were generally used to predict preterm labor. We proposed to use genetic algorithm to identify the optimum feature subset to predict preterm labor using simple classification algorithms. A total of 203 parameters from 326 multichannel EHG recordings and obstetric data were used as input features. We designed and validated 3 base classifiers based on k-nearest neighbors, linear discriminant analysis and logistic regression, achieving F1-score of 84.63 ± 2.76%, 89.34 ± 3.5% and 86.87 ± 4.53%, respectively, for incoming new data. The results reveal that temporal, spectral and non-linear EHG parameters computed in different bandwidths from multichannel recordings provide complementary information on preterm labor prediction. We also developed an ensemble classifier that not only outperformed base classifiers but also reduced their variability, achieving an F1-score of 92.04 ± 2.97%, which is comparable with those obtained using complex classifiers. Our results suggest the feasibility of developing a preterm labor prediction system with high generalization capacity using simple easy-to-interpret classification algorithms to assist in transferring the EHG technique to clinical practice.

Electrodes in external electrohysterography: a systematic literature review.

BACKGROUND: In low-income countries, pregnant women do not have easy access to health care, especially in rural and peri-urban areas. In this context, they can be surprised by the uterine contractions that precede childbirth and sometimes find themselves giving birth at home or on the way to the nearest health facility (located miles away from their home). In view of the development of an external uterine electrohysterogram acquisition system for labour prediction, a review of the literature on electrodes and their characteristics is necessary. METHODS: A comprehensive literature review was conducted to collate information on the use of electrodes in external EHG recording and their characteristics. RESULTS: Wet electrodes based on Ag/AgCl redox chemistry are the most common type of electrodes for EHG, employed in different configurations on the pregnant woman's abdomen. All positioning configurations are around the vertical median axis if they are not placed directly on it. Positioning below the navel seems to be the most efficient. The number of source, reference, and ground electrodes used varies from one author to another, as does the distance between the electrodes. CONCLUSION: Two well-positioned source electrodes on the vertical median axis, with ground electrode on the right side of the hip and reference one on the left side, are able to generate a good external EHG recording signal. The minimum allowed inter-electrode distance is approximately 17.5 to 25mm.

Clinical evaluation of electrohysterography as method of monitoring uterine contractions during labor: A propensity score matched study.

OBJECTIVE: Electrohysterography is a non-invasive technique to monitor uterine activity and has a significantly higher sensitivity compared to conventional external tocodynamometry. Whether this technique could lead to improved obstetrical outcomes is still unknown. In this propensity score matched study, clinical results of the first pilot implementing electrohysterography during labor were evaluated. The hypothesis tested is that electrohysterography will help to optimize uterine activity and thereby lead to fewer obstetric interventions. Secondary outcomes were Apgar score, arterial umbilical pH values, first stage labor duration, episiotomy rate and postpartum vaginal blood loss. STUDY DESIGN: From November 2017 until October 2018, electrohysterography was introduced as a standard alternative for monitoring uterine activity in high-risk deliveries. It could be applied in case of induced labor, previous cesarean delivery, body mass index ≥30 kg/m2 or an inadequate external tocodynamometry monitoring. Outcomes were compared to a matched group of women in which external tocodynamometry was applied for uterine activity monitoring during labor. These women were identified using propensity scores. RESULTS: A total of 348 women received electrohysterography as standard method of uterine monitoring during labor. A match (1:1 ratio) was found for 317 women, resulting in a total population of 634 women. No significant differences were seen in obstetric interventions (i.e. cesarean deliveries and assisted vaginal deliveries) between the electrohysterography and tocodynamometry group (P = 0.80). No statistically significant differences were seen regarding the secondary outcomes. CONCLUSIONS: This first pilot study implementing electrohysterography as monitoring method during labor in a high-risk population did not result in statistically significant differences regarding obstetric interventions, low Apgar scores or low umbilical artery pH values. Therefore, we suggest that electrohysterography causes no harm and we recommend further implementation and evaluation in clinical practice.

The assessment of selected parameters of bioelectric and mechanical activity of the uterus during pharmacologic treatment of threatening preterm delivery.

OBJECTIVES: To analyze and compare the bioelectric and mechanical activity of the uterus in pregnant women with threatening preterm delivery treated with tocolysis. Additionally, auxiliary parameters of the bioelectric signal, as registered by electrohysterography and characteristic only for this method, were measured and analyzed. MATERIAL AND METHODS: Forty-five women with pregnancies from 24 to 36 weeks of gestation with typical clinical symptoms of threatening preterm delivery were given tocolytic therapy. Registration and analysis of bioelectric activity with electrohysterography was performed simultaneously with registration and analysis of mechanical activity with tocography. RESULTS: After administration of tocolytic treatment, the presence of bioelectric activity was accompanied by the lack of or minimal occurrence of mechanical activity. All parameters of contraction recorded by electrohysterography had significantly greater values than those recorded by tocography. CONCLUSIONS: Measurement of bioelectric activity is more sensitive than measurement of mechanical activity of the uterus. Elevated bioelectric activity of the uterine muscle was observed despite the use of tocolysis, a lack of symptoms of threatening preterm delivery, as well as a lack of contraction in tocography. The presence of bioelectric activity may precede the occurrence of mechanical activity of the uterus, but further research is required on larger groups of patients.