Cardiotocography (CTG) is a non-invasive and important tool for diagnosing fetal distress during pregnancy. To meet the needs of intelligent fetal heart monitoring based on deep learning, this paper proposes a TWD-MOAL deep active learning algorithm based on the three-way decision (TWD) theory and multi-objective optimization Active Learning (MOAL). During the training process of a convolutional neural network (CNN) classification model, the algorithm incorporates the TWD theory to select high-confidence samples as pseudo-labeled samples in a fine-grained batch processing mode, meanwhile low-confidence samples annotated by obstetrics experts were also considered. The TWD-MOAL algorithm proposed in this paper was validated on a dataset of 16 355 prenatal CTG records collected by our group. Experimental results showed that the algorithm proposed in this paper achieved an accuracy of 80.63% using only 40% of the labeled samples, and in terms of various indicators, it performed better than the existing active learning algorithms under other frameworks. The study has shown that the intelligent fetal heart monitoring model based on TWD-MOAL proposed in this paper is reasonable and feasible. The algorithm significantly reduces the time and cost of labeling by obstetric experts and effectively solves the problem of data imbalance in CTG signal data in clinic, which is of great significance for assisting obstetrician in interpretations CTG signals and realizing intelligence fetal monitoring.
Humans ; Pregnancy ; Female ; Cardiotocography/methods* ; Deep Learning ; Neural Networks, Computer ; Algorithms ; Fetal Monitoring/methods* ; Heart Rate, Fetal ; Fetal Distress/diagnosis* ; Fetal Heart/physiology*

Fetal electrocardiogram signal extraction is of great significance for perinatal fetal monitoring. In order to improve the prediction accuracy of fetal electrocardiogram signal, this paper proposes a fetal electrocardiogram signal extraction method (GA-LSTM) based on genetic algorithm (GA) optimization with long and short term memory (LSTM) network. Firstly, according to the characteristics of the mixed electrocardiogram signal of the maternal abdominal wall, the global search ability of the GA is used to optimize the number of hidden layer neurons, learning rate and training times of the LSTM network, and the optimal combination of parameters is calculated to make the network topology and the mother body match the characteristics of the mixed signals of the abdominal wall. Then, the LSTM network model is constructed using the optimal network parameters obtained by the GA, and the nonlinear transformation of the maternal chest electrocardiogram signals to the abdominal wall is estimated by the GA-LSTM network. Finally, using the non-linear transformation obtained from the maternal chest electrocardiogram signal and the GA-LSTM network model, the maternal electrocardiogram signal contained in the abdominal wall signal is estimated, and the estimated maternal electrocardiogram signal is subtracted from the mixed abdominal wall signal to obtain a pure fetal electrocardiogram signal. This article uses clinical electrocardiogram signals from two databases for experimental analysis. The final results show that compared with the traditional normalized minimum mean square error (NLMS), genetic algorithm-support vector machine method (GA-SVM) and LSTM network methods, the method proposed in this paper can extract a clearer fetal electrocardiogram signal, and its accuracy, sensitivity, accuracy and overall probability have been better improved. Therefore, the method could extract relatively pure fetal electrocardiogram signals, which has certain application value for perinatal fetal health monitoring.
Algorithms ; Electrocardiography ; Female ; Fetal Monitoring ; Humans ; Memory, Short-Term ; Pregnancy ; Support Vector Machine

Fetal heart rate plays an essential role in maternal and fetal monitoring and fetal health detection. In this study, a method based on Poincare Plot and LSTM is proposed to realize the high performance classification of abnormal fetal heart rate. Firstly, the original fetal heart rate signal of CTU-UHB database is preprocessed via interpolation, then the sequential fetal heart rate signal is converted into Poincare Plot to obtain nonlinear characteristics of the signals, and then SquenzeNet is used to extract the features of Poincare Plot. Finally, the features extracted by SqueezeNet are classified by LSTM. And the accuracy, the true positive rate and the false positive rate are 98.00%, 100.00%, 92.30% respectively on 2 000 test set data. Compared with the traditional fetal heart rate classification method, all respects are improved. The method proposed in this study has good performance in CTU-UHB fetal monitoring database and has certain practical value in the clinical diagnosis of auxiliary fetal heart rate detection.
Databases, Factual ; Female ; Fetal Monitoring ; Fetus ; Heart Rate, Fetal ; Humans ; Pregnancy

OBJECTIVE: To explore the feasibility of remote monitoring of neonatal jaundice in newborns with ABO hemolytic disease. METHODS: Forty six neonates of gestational age >35 weeks with ABO hemolytic disease admitted to Women's Hospital, Zhejiang University School of Medicine from January 20th, 2020 to February 29th, 2020 were enrolled in the study (study group). The newborns were followed up at home after discharge, the transcutaneous bilirubin (TCB) levels were measured by parents using the provided device and the results were sent to the doctor by smart phone using the installed APP. Fifty six newborns with ABO hemolytic disease admitted in 2018 who received conventional outpatient follow-up after discharge served as the control group. The demographic characteristics, total serum bilirubin (TSB) level during hospitalization, number of outpatient visit and rate of re-admission due to rebound hyperbilirubinemia were compared between the two groups. RESULTS: There were no significant differences between the two groups in gestational age, birth weight, delivery mode, gender, length of the first hospitalization, TSB level before phototherapy and before discharge, and the managements during the first hospitalization (all CONCLUSIONS The remote follow-up for neonatal jaundice at home can effectively reduce the number of outpatient visits without increasing the risk of readmission and severe neonatal hyperbilirubinemia for newborns with ABO hemolytic disease.
Bilirubin ; Erythroblastosis, Fetal/diagnosis* ; Female ; Humans ; Hyperbilirubinemia, Neonatal/diagnosis* ; Infant, Newborn ; Jaundice, Neonatal/diagnosis* ; Monitoring, Physiologic/methods* ; Phototherapy

The existing fetal monitor is prone to false detection in the case of high maternal interference in the second stage of labor. With this background, the article designs and implements a combined maternal-fetal fetal heart monitoring system. The system obtains the Doppler signal of the abdominal fetal heart and the blood oxygen signal of the mother's finger, and estimates the maternal interference degree in the fetal heart rate Doppler signal according to the maximum correlation value between the maternal finger blood oxygen signal and the abdominal fetal heart Doppler signal, and switches the fetal heart rate extraction algorithm between the autocorrelation method suitable for lower interference and improved template method suitable for higher interference according to the maternal interference degree. The accuracy of our method is 9.2% which is higher than that of the improved template matching method and 6.1% higher than that of the autocorrelation method.
Algorithms ; Electrocardiography ; Female ; Fetal Monitoring ; instrumentation ; Fetus ; Heart Rate ; Heart Rate, Fetal ; Humans ; Pregnancy ; Signal Processing, Computer-Assisted

The ultrasound Doppler fetal heart rate measurement is the gold standard of fetal heart rate counting. However, the existing fetal heart rate extraction algorithms are not designed specifically to suppress the high maternal interference during the second stage of labor, and false detection occurrences are common during labor. With this background, a method combining time-frequency frame template library optimal selecting and non-linear template matching is proposed. The method contributes a template library, and the optimal template can be selected to match the signal frame. After the short-time Fourier transform of the signal, the difference between the signal and the template is optimized by leaky rectified linear unit (LReLU) function frame by frame. The heart rate was calculated from the peak of the matching curve and the heart rate was calculated. By comparing the proposed method with the autocorrelation method, the results show that the detection accuracy of the proposed method is improved by 20% on average, and the non-linear template matching of 23% samples is at least 50% higher than the autocorrelation method. This paper designs the algorithm by analyzing the characteristics of the interference and signal mixing. We hope that this paper will provide a new idea for fetal heart rate extraction which not only focuses on the original signal.
Algorithms ; Female ; Fetal Monitoring ; Fourier Analysis ; Heart Rate, Fetal ; Humans ; Pregnancy ; Signal Processing, Computer-Assisted ; Ultrasonography, Doppler

OBJECTIVE: To evaluate the significance of fetal Doppler parameters in predicting adverse neonatal outcomes and the risk of cesarean delivery due to non-reassuring fetal status, in severe small for gestational age (SGA) fetuses of late preterm and term gestation. METHODS: Fetal brain and umbilical artery (UmA) Doppler parameters of cerebroplacental ratio (CPR) and UmA pulsatility index (PI) were evaluated in a cohort of 184 SGA fetuses between 34 and 41 weeks gestational age, who were less than the 5th percentile. The risks of neonatal morbidities and cesarean delivery due to non-reassuring fetal status were analyzed. RESULTS: Univariate analysis revealed that abnormal CPR was significantly associated with cesarean delivery due to non-reassuring fetal status (P=0.018), but not with neonatal morbidities. However, abnormal CPR did not increase the risk of cesarean delivery due to non-reassuring fetal status in multivariate logistic regression analysis. Abnormal CPR with abnormal PI of UmA was associated with low Apgar score at 1 minute (P=0.048), mechanical ventilation (P=0.013) and cesarean delivery due to non-reassuring fetal status (P < 0.001), in univariate analysis. It increased risk of cesarean delivery for non-reassuring fetal status (adjusted odds ratio, 7.0; 95% confidence interval, 1.2–41.3; P=0.033), but did not increase risk of low Apgar score or mechanical ventilation in multivariate logistic regression analysis. CONCLUSION: Abnormal CPR with abnormal PI of UmA increases the risk of cesarean delivery for non-reassuring fetal status, in severe SGA fetuses of late preterm and term. Monitoring of CPR and PI of UmA can help guide management including maternal hospitalization and fetal monitoring.
Apgar Score ; Brain ; Cardiopulmonary Resuscitation ; Cesarean Section ; Cohort Studies ; Female ; Fetal Monitoring ; Fetus* ; Gestational Age ; Hospitalization ; Humans ; Infant, Newborn ; Infant, Small for Gestational Age ; Logistic Models ; Odds Ratio ; Pregnancy ; Respiration, Artificial ; Umbilical Arteries

PURPOSE: This study examined the effect on uterine contraction frequency (UCF), blood pressure (BP), heart rate (HR), fetal heart rate (FHR) patterns and psychophysical symptoms (physical discomfort, anxiety, and depression) of structured bed exercise (SBE) in hospitalized high-risk pregnant women prescribed bed rest. METHODS: Forty-five hospitalized high risk pregnant women at >24 weeks of pregnancy prescribed bed rest were randomly assigned to the experimental or control group. From January to May 2014, data were collected using electronic fetal monitoring and patient monitoring of UCF, BP, HR and FHR patterns, and psychophysical symptoms were measured using the antenatal physical discomfort scale, state-trait anxiety scale, and Edinburgh postnatal depression scale. RESULTS: UCF, BP, HR, and FHR patterns (rate, variability, acceleration, and deceleration) did not differ significantly between the experimental and control groups. The experimental group showed a significant increase in baseline FHR after SBE within the normal range, and after SBE, it reduced to the FHR before SBE. The variability, acceleration and deceleration of FHR before and after SBE did not differ significantly between two groups. Moreover, there was no statistically significant difference before and after SBE in the experimental group. Also, the experimental group showed statistically significant decreases in physical discomfort score. However, there were no significant differences in depression and anxiety score between two groups. CONCLUSIONS: SBE in hospitalized high-risk pregnant women under bed rest did not increase the risk to the fetus, and relieved physical discomfort and anxiety. Therefore, SBE should be considered as a nursing intervention in hospitalized high-risk pregnant women.
Acceleration ; Anxiety ; Bed Rest ; Blood Pressure ; Cardiotocography ; Deceleration ; Depression ; Depression, Postpartum ; Female ; Fetal Heart* ; Fetus ; Heart Rate ; Heart Rate, Fetal* ; Humans ; Monitoring, Physiologic ; Nursing ; Pregnancy ; Pregnancy, High-Risk ; Pregnant Women* ; Reference Values ; Uterine Contraction*

PURPOSE: This study aimed to develop supplementary material about the electronic fetal monitoring for nursing students, and to test the effects on electronic fetal monitoring related knowledge and confidence on nursing performance in delivery room. METHODS: Totally 58 nursing students were recruited either experimental group (n=30) or a control group (n=28). A non-equivalent control group pretest-posttest design was employed to test the effects on fetal monitoring related knowledge and confidence on nursing performance in delivery room. The supplementary material about the electronic fetal monitoring was developed based on Analysis, Design, Development, Implement and Evaluation (ADDIE) model. Fetal monitoring related knowledge and confidence on nursing performance in delivery room were self-reported by the scales that author developed. Data were collected at pre-test and after the 6-week intervention. RESULTS: There was significant difference in confidence on nursing performance in delivery room between two groups after intervention. CONCLUSION: These findings suggest the importance of the supplementary material about the electronic fetal monitoring for nursing students to improve confidence on nursing performance in delivery room.
Delivery Rooms ; Fetal Monitoring* ; Humans ; Nursing* ; Students, Nursing* ; Weights and Measures

INTRODUCTIONFetal distress is a result of acute or chronic disturbances in the system of "mother-placenta-fetus" in pre-eclampsia (PE). The aim of the investigation was to compare the accuracy of antenatal fetal distress diagnostics in cases of traditional cardiotocography (CTG) waveform evaluation and analysis of morphological non-invasive electrocardiogram (ECG) parameters in anterpartum patients with PE.

MATERIALS AND METHODSFetal non-invasive ECG antenatal recordings of 122 pregnant patients at 34 to 40 weeks of gestation were examined. In Group I, there were 32 women with physiological gestation and normal fetal condition according to haemodynamic Doppler values. Group II involved 48 patients with mild and moderate PE whom were performed Doppler investigation. In Group III, 42 patients with severe PE were monitored with haemodynamic Doppler.

RESULTSFetal autonomic tone was lower with the relative increase of low frequency (LF) branch in the patients of pre-eclamptic group. The increased value of the amplitude of mode (AMo) and stress index (SI) was associated with adrenergic overactivity. It has induced pQ and QT shortening, increased T/QRS ratio and decelerations appearance. The rate of antenatal fetal distress retrospectively was 31.1 % in PE. The traditional analysis of CTG parameters has showed sensitivity (72.7%) and specificity (87.1%). In addition to the conventional CTG analysis, evaluation of ECG parameters has contributed to better diagnostics of fetal distress. Sensitivity and specificity of non-invasive fetal ECG were absolutely equal in this study (100%).

CONCLUSIONThe results suggest that fetal non-invasive ECG monitoring is more objective than conventional CTG.

Cardiotocography ; methods ; Cross-Sectional Studies ; Electrocardiography ; methods ; Female ; Fetal Distress ; diagnosis ; physiopathology ; Fetal Monitoring ; Heart Rate, Fetal ; Humans ; Pre-Eclampsia ; Pregnancy ; Pregnancy Trimester, Third ; Retrospective Studies ; Sensitivity and Specificity ; Severity of Illness Index ; Ultrasonography, Doppler ; Ultrasonography, Prenatal