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

Establishment of a model for predicting preterm birth based on the machine learning algorithm

BACKGROUND

The purpose of this study was to construct a preterm birth prediction model based on electronic health records and to provide a reference for preterm birth prediction in the future.

METHODS

This was a cross-sectional design. The risk factors for the outcomes of preterm birth were assessed by multifactor logistic regression analysis. In this study, a logical regression model, decision tree, Naive Bayes, support vector machine, and AdaBoost are used to construct the prediction model. Accuracy, recall, precision, F1 value, and receiver operating characteristic curve, were used to evaluate the prediction performance of the model, and the clinical application of the model was verified.

RESULTS

A total of 5411 participants were included and were used for model construction. AdaBoost model has the best prediction ability among the five models. The accuracy of the model for the prediction of "non-preterm birth" was the highest, reaching 100%, and that of "preterm birth" was 72.73%.

CONCLUSIONS

By constructing a preterm birth prediction model based on electronic health records, we believe that machine algorithms have great potential for preterm birth identification. However, more relevant studies are needed before its application in the clinic.

An open dataset with electrohysterogram records of pregnancies ending in induced and cesarean section delivery

The existing non-invasive automated preterm birth prediction methods rely on the use of uterine electrohysterogram (EHG) records coming from spontaneous preterm and term deliveries, and are indifferent to term induced and cesarean section deliveries. In order to enhance current publicly available pool of term EHG records, we developed a new EHG dataset, Induced Cesarean EHG DataSet (ICEHG DS), containing 126 30-minute EHG records, recorded early (23rd week), and/or later (31st week) during pregnancy, of those pregnancies that were expected to end in spontaneous term delivery, but ended in induced or cesarean section delivery. The records were collected at the University Medical Center Ljubljana, Ljubljana, Slovenia. The dataset includes 38 and 43, early and later, induced; 11 and 8, early and later, cesarean; and 13 and 13, early and later, induced and cesarean EHG records. This dataset enables better understanding of the underlying physiological mechanisms involved during pregnancies ending in induced and cesarean deliveries, and provides a robust and more realistic assessment of the performance of automated preterm birth prediction methods.

Characterization and separation of preterm and term spontaneous, induced, and cesarean EHG records

To improve the understanding of the underlying physiological processes that lead to preterm birth, and different term delivery modes, we quantitatively characterized and assessed the separability of the sets of early (23rd week) and later (31st week) recorded, preterm and term spontaneous, induced, cesarean, and induced-cesarean electrohysterogram (EHG) records using several of the most widely used non-linear features extracted from the EHG signals. Linearly modeled temporal trends of the means of the median frequencies (MFs), and of the means of the peak amplitudes (PAs) of the normalized power spectra of the EHG signals, along pregnancy (from early to later recorded records), derived from a variety of frequency bands, revealed that for the preterm group of records, in comparison to all other term delivery groups, the frequency spectrum of the frequency band B0L (0.08-0.3 Hz) shifts toward higher frequencies, and that the spectrum of the newly identified frequency band B0L' (0.125-0.575 Hz), which approximately matches the Fast Wave Low band, becomes stronger. The most promising features to separate between the later preterm group and all other later term delivery groups appear to be MF (p=1.1⋅10^-5) in the band B0L of the horizontal signal S3, and PA (p=2.4⋅10^-8) in the band B0L' (S3). Moreover, the PA in the band B0L' (S3) showed the highest power to individually separate between the later preterm group and any other later term delivery group. Furthermore, the results suggest that in preterm pregnancies the resting maternal heart rate decreases between the 23rd and 31st week of gestation.

Prediction of preterm birth using artificial intelligence: a systematic review

Preterm birth is the leading cause of neonatal death. It is challenging to predict preterm birth. We elucidated the state of artificial intelligence research on the prediction of preterm birth, clarifying the predictive values and accuracy. We performed a systematic review using three databases (PubMed, Web of Science, and Scopus) in August 2020, with keywords as 'artificial intelligence,' 'deep learning,' 'machine learning,' and 'neural network' combined with 'preterm birth'. We included 22 publications between 2010 and 2020. Regarding the predictive values, electrohysterogram images were mostly used, followed by the biological profiles, the metabolic panel in amniotic fluid or maternal blood, and the cervical images on the ultrasound examination. The size of dataset in most studies was hundred cases and too small for learning, although only three studies used the medical database over a hundred thousand cases. The accuracy was better in the studies using the metabolic panel and electrohysterogram images. Impact statementWhat is already known on this subject? Preterm birth is the leading cause of newborn morbidity and mortality. Presently, the prediction of preterm birth in individual cases is still challenging.What the results of this study add? Using artificial intelligence such as deep learning and machine learning models, clinical data could lead to accurate prediction of preterm birth.What the implications are of these findings for clinical practice and/or further research? The size of the datasets was too small for the models using artificial intelligence in the previous studies. Big data should be prepared for the future studies.

Preterm-term birth classification using EMD-based time-domain features of single-channel electrohysterogram data

Preterm birth anticipation is a crucial task that can reduce both the rate and the complications of preterm birth. Electrohysterogram (EHG) or uterine electromyogram (EMG) data have shown that they can provide useful information for preterm birth anticipation. Four distinct time-domain features (mean absolute value, average amplitude change, difference in absolute standard deviation value, and log detector) that are commonly applied to EMG signal processing were utilized and investigated in this study. A single channel of EHG data was decomposed into its constituent components (i.e., into intrinsic mode functions) by using empirical mode decomposition (EMD) before their time-domain features were extracted. The time-domain features of the intrinsic mode functions of the EHG data associated with preterm and term births were applied for preterm-term birth classification by using a support vector machine with a radial basis function. The preterm-term birth classifications were validated by using 10-fold cross validation. From the computational results, it was shown that excellent preterm-term birth classification can be achieved by using single-channel EHG data. The computational results further suggested that the best overall performance concerning preterm-term birth classification was obtained when thirteen (out of sixteen) EMD-based time-domain features were applied. The best accuracy, sensitivity, specificity, and [Formula: see text]-score achieved were 0.9382, 0.9130, 0.9634, and 0.9366, respectively.

Optimization of Imminent Labor Prediction Systems in Women with Threatened Preterm Labor Based on Electrohysterography

Preterm birth is the leading cause of death in newborns and the survivors are prone to health complications. Threatened preterm labor (TPL) is the most common cause of hospitalization in the second half of pregnancy. The current methods used in clinical practice to diagnose preterm labor, the Bishop score or cervical length, have high negative predictive values but not positive ones. In this work we analyzed the performance of computationally efficient classification algorithms, based on electrohysterographic recordings (EHG), such as random forest (RF), extreme learning machine (ELM) and K-nearest neighbors (KNN) for imminent labor (<7 days) prediction in women with TPL, using the 50th or 10th–90th percentiles of temporal, spectral and nonlinear EHG parameters with and without obstetric data inputs. Two criteria were assessed for the classifier design: F1-score and sensitivity. RF_{F1_2} and ELM_{F1_2} provided the highest F1-score values in the validation dataset, (88.17 ± 8.34% and 90.2 ± 4.43%) with the 50th percentile of EHG and obstetric inputs. ELM_{F1_2} outperformed RF_{F1_2} in sensitivity, being similar to those of ELM_Sens (sensitivity optimization). The 10th–90th percentiles did not provide a significant improvement over the 50th percentile. KNN performance was highly sensitive to the input dataset, with a high generalization capability.

Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis

BACKGROUND

Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm or modeling method.

OBJECTIVE

This study aims to review and compare the predictive performances between logistic regression (LR) and other machine learning algorithms for developing or validating a multivariable prognostic prediction model for pregnancy care to inform clinicians' decision making.

METHODS

Research articles from MEDLINE, Scopus, Web of Science, and Google Scholar were reviewed following several guidelines for a prognostic prediction study, including a risk of bias (ROB) assessment. We report the results based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were primarily framed as PICOTS (population, index, comparator, outcomes, timing, and setting): Population: men or women in procreative management, pregnant women, and fetuses or newborns; Index: multivariable prognostic prediction models using non-LR algorithms for risk classification to inform clinicians' decision making; Comparator: the models applying an LR; Outcomes: pregnancy-related outcomes of procreation or pregnancy outcomes for pregnant women and fetuses or newborns; Timing: pre-, inter-, and peripregnancy periods (predictors), at the pregnancy, delivery, and either puerperal or neonatal period (outcome), and either short- or long-term prognoses (time interval); and Setting: primary care or hospital. The results were synthesized by reporting study characteristics and ROBs and by random effects modeling of the difference of the logit area under the receiver operating characteristic curve of each non-LR model compared with the LR model for the same pregnancy outcomes. We also reported between-study heterogeneity by using τ2 and I2.

RESULTS

Of the 2093 records, we included 142 studies for the systematic review and 62 studies for a meta-analysis. Most prediction models used LR (92/142, 64.8%) and artificial neural networks (20/142, 14.1%) among non-LR algorithms. Only 16.9% (24/142) of studies had a low ROB. A total of 2 non-LR algorithms from low ROB studies significantly outperformed LR. The first algorithm was a random forest for preterm delivery (logit AUROC 2.51, 95% CI 1.49-3.53; I2=86%; τ2=0.77) and pre-eclampsia (logit AUROC 1.2, 95% CI 0.72-1.67; I2=75%; τ2=0.09). The second algorithm was gradient boosting for cesarean section (logit AUROC 2.26, 95% CI 1.39-3.13; I2=75%; τ2=0.43) and gestational diabetes (logit AUROC 1.03, 95% CI 0.69-1.37; I2=83%; τ2=0.07).

CONCLUSIONS

Prediction models with the best performances across studies were not necessarily those that used LR but also used random forest and gradient boosting that also performed well. We recommend a reanalysis of existing LR models for several pregnancy outcomes by comparing them with those algorithms that apply standard guidelines.

TRIAL REGISTRATION

PROSPERO (International Prospective Register of Systematic Reviews) CRD42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=136106.

Acquisition and Analysis of Electrohysterogram Signal

Electrohysterogram (EHG) signal is the signal related to action potentials propagating through smooth muscle cells of the uterus (myometrium) to the abdomen of pregnant women which is also known as uterine contraction signal. Cardiotocography (CTG) is the most common method used for monitoring fetal heart rate (FHR) and uterine contractions during pregnancy and labor. This method detects mechanical activity of fetal heart and uterus, however, it provides low accuracy and sensibility and hence more accurate methods are required. The abdominal electrode method of FECG monitoring and Electrohysterography (EHG) are alternative noninvasive method to monitor the FHR and uterine contractions during pregnancy which provides better results compared to CTG. Each information such as the frequency of uterine contractions, length of the contraction and contraction power of uterus, indicates the condition of the uterus which will help the obstetricians to identify the progress of labor. All these above mentioned parameters can be identified from the EHG signal acquired non-invasively by placing the electrodes on the abdomen of the pregnant women. In this work the acquisition of EHG signal as well as analysis of EHG signal in both antepartum condition and labor condition have been carried out and parameters such as number of contractions, contraction duration, amplitude, power of contraction are computed and the quantitative analysis of EHG signals in both above mentioned conditions are performed and it is compared with the simultaneously recorded uterine contraction signal parameters from Cardiotocography (CTG).

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

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

Preliminary Study on the Efficient Electrohysterogram Segments for Recognizing Uterine Contractions with Convolutional Neural Networks

Background

Uterine contraction (UC) is the tightening and shortening of the uterine muscles which can indicate the progress of pregnancy towards delivery. Electrohysterogram (EHG), which reflects uterine electrical activities, has recently been studied for UC monitoring. In this paper, we aimed to evaluate different EHG segments for recognizing UCs using the convolutional neural network (CNN).

Materials and Methods

In the open-access Icelandic 16-electrode EHG database (122 recordings from 45 pregnant women), 7136 UC and 7136 non-UC EHG segments with the duration of 60 s were manually extracted from 107 recordings of 40 pregnant women to develop a CNN model. A fivefold cross-validation was applied to evaluate the CNN based on sensitivity (SE), specificity (SP), and accuracy (ACC). Then, 1056 UC and 1056 non-UC EHG segments were extracted from the other 15 recordings of 5 pregnant women. Furthermore, the developed CNN model was applied to identify UCs using different EHG segments with the durations of 10 s, 20 s, and 30 s.

Results

The CNN achieved the average SE, SP, and ACC of 0.82, 0.93, and 0.88 for a 60 s EHG segment. The EHG segments of 10 s, 20 s, and 30 s around the TOCO peak achieved higher SE and ACC than the other segments with the same duration. The values of SE from 20 s EHG segments around the TOCO peak were higher than those from 10 s to 30 s EHG segments on the same side of the TOCO peak.

Conclusion

The proposed method could be used to determine the efficient EHG segments for recognizing UC with the CNN.

An Automatic Method for the Segmentation and Classification of Imminent Labor Contraction From Electrohysterograms

OBJECTIVE

Preterm birth is the first cause of perinatal morbidity and mortality. Despite continuous clinical routine improvements, the preterm rate remains steady. Moreover, the specificity of the early diagnosis stays poor as many hospitalized women for preterm delivery threat finally deliver at term. In this context, the use of electrohysterograms may increase the sensitivity and the specificity of early diagnosis of preterm labor.

METHODS

This paper proposes a clinical application of electrohysterogram processing for the classification of patients as prone to deliver within a week or later. The approach relies on non-linear correlation analysis for the contraction bursts extraction and uses computation of various features combined with the use of Gaussian mixture models for their classification. The method is tested on a new dataset of 68 records collected on women hospitalized for preterm delivery threat.

RESULTS

This paper presents promising results for the automatic segmentation of the contraction and a classification sensitivity, specificity, and accuracy of, respectively, 80.7%, 76.3%, and 76.2%.

CONCLUSION

These results are in accordance with the gold standards but have the advantage to be non-invasive and could be performed at home.

SIGNIFICANCE

Diagnosis of imminent labor is possible by electrohysterography recording and may help in avoiding over-medication and in providing better cares to at-risk pregnant women.

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.

Diagnosis of mesothelioma with deep learning

Malignant mesothelioma (MM) is a rare but aggressive cancer. The definitive diagnosis of MM is critical for effective treatment and has important medicolegal significance. However, the definitive diagnosis of MM is challenging due to its composite epithelial/mesenchymal pattern. The aim of the current study was to develop a deep learning method to automatically diagnose MM. A retrospective analysis of 324 participants with or without MM was performed. Significant features were selected using a genetic algorithm (GA) or a ReliefF algorithm performed in MATLAB software. Subsequently, the current study constructed and trained several models based on a backpropagation (BP) algorithm, extreme learning machine algorithm and stacked sparse autoencoder (SSAE) to diagnose MM. A confusion matrix, F-measure and a receiver operating characteristic (ROC) curve were used to evaluate the performance of each model. A total of 34 potential variables were analyzed, while the GA and ReliefF algorithms selected 19 and 5 effective features, respectively. The selected features were used as the inputs of the three models. SSAE and GA+SSAE demonstrated the highest performance in terms of classification accuracy, specificity, F-measure and the area under the ROC curve. Overall, the GA+SSAE model was the preferred model since it required a shorter CPU time and fewer variables. Therefore, the SSAE with GA feature selection was selected as the most accurate model for the diagnosis of MM. The deep learning methods developed based on the GA+SSAE model may assist physicians with the diagnosis of MM.

Multifractal Analysis of Uterine Electromyography Signals for the Assessment of Progression of Pregnancy in Term Conditions

OBJECTIVES

The objectives of this paper are to examine the source of multifractality in uterine electromyography (EMG) signals and to study the progression of pregnancy in the term (gestation period > 37 weeks) conditions using multifractal detrending moving average (MFDMA) algorithm.

METHODS

The signals for the study, considered from an online database, are obtained from the surface of abdomen during the second (T1) and third trimester (T2). The existence of multifractality is tested using Hurst and scaling exponents. With the intention of identifying the origin of multifractality, the preprocessed signals are converted to shuffle and surrogate data. The original and the transformed signals are subjected to MFDMA to extract multifractal spectrum features, namely strength of multifractality, maximum, minimum, and peak singularity exponents.

RESULTS

The Hurst and scaling exponents extracted from the signals indicate that uterine EMG signals are multifractal in nature. Further analysis shows that the source of multifractality is mainly owing to the presence of long-range correlation, which is computed as 79.98% in T1 and 82.43% in T2 groups. Among the extracted features, the peak singularity exponent and strength of multifractality show statistical significance in identifying the progression of pregnancy. The corresponding coefficients of variation are found to be low, which show that these features have low intersubject variability.

CONCLUSION

It appears that the multifractal analysis can help in investigating the progressive changes in uterine muscle contractions during pregnancy.

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.