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*

Humans ; Pulmonary Atresia/therapy* ; Pregnancy ; Female ; China ; Consensus ; Fetal Heart ; Ultrasonography, Prenatal ; Heart Defects, Congenital/therapy* ; Ventricular Septum ; Cardiac Surgical Procedures/methods*

OBJECTIVE: To explore the genetic basis for a fetus with Cardiac-urogenital syndrome (CUGS). METHODS: A fetus with congenital heart disease identified at the Maternal Fetal Medical Center for Fetal Heart Disease, Beijing Anzhen Hospital Affiliated to Capital Medical University in January 2019 was selected as the study subject. Clinical data of the fetus was collected. Copy number variation sequencing (CNV-seq) and trio-whole exome sequencing (trio-WES) were carried out for the fetus and its parents. Candidate variants were verified by Sanger sequencing. RESULTS: Detailed fetal echocardiographic examination had revealed hypoplastic aortic arch. The results of trio-WES revealed that the fetus has harbored a de novo splice variant of the MYRF gene (c.1792-2A>C), for which both parents were of the wild-type. Sanger sequencing confirmed the variant to be de novo. Based on the guidelines from the American College of Medical Genetics and Genomics (ACMG), the variant was rated as likely pathogenic. CNV-seq has identified no chromosomal anomalies. And the fetus was diagnosed with Cardiac-urogenital syndrome. CONCLUSION The de novo splice variant of the MYRF gene probably underlay the abnormal phenotype in the fetus. Above finding has enriched the spectrum of MYRF gene variants.
Female ; Humans ; DNA Copy Number Variations ; Fetal Diseases ; Fetus/abnormalities* ; Heart Defects, Congenital/genetics* ; Mutation ; Transcription Factors/genetics*

Objective: To analysis the clinical characteristics of 400 fetuses with heart defects and the impactors of pregnancy decision making, and explore the influence of a multi-disciplinary team (MDT) cooperation approach on it. Methods: Clinical data of 400 fetuses with abnormal cardiac structure diagnosed at Peking University First Hospital from January 2012 to June 2021 were collected, which were divided into 4 groups according to the characteristics of fetal heart defects and the presence of extracardiac abnormalities or not: single cardiac defects without extracardiac abnormalities (122 cases), multiple cardiac defects without extracardiac abnormalities (100 cases), single cardiac defects with extracardiac abnormalities (115 cases), and multiple cardiac defects with extracardiac abnormalities (63 cases). The types of fetal cardiac structural abnormalities and genetic test results, and the detection rate of pathogenic genetic abnormalities, MDT consultation and management situation, and pregnancy decision of fetuses in each group were retrospectively analyzed. A logistics regression was used to analyze the influencing factors of fetal heart defects pregnancy decision. Results: (1) Among the 400 fetal heart defects, the four most common major types were ventricular septal defect 96 (24.0%, 96/400), tetralogy of Fallot 52 (13.0%, 52/400), coarctation of the aorta 34 (8.5%, 34/400), and atrioventricular septal defect 26 (6.5%, 26/400). (2) Among the 204 fetuses undergoing genetic examination, 44 (21.6%, 44/204) pathogenic genetic abnormalities were detected. (3) Detection rate of pathogenic genetic abnormalities (39.3%, 24/61) and pregnancy termination rate (86.1%, 99/115) in the single cardiac defects with extracardiac abnormalities group were significantly higher than those in the single cardiac defects without extracardiac abnormalities group [15.1% (8/53), 44.3% (54/122), respectively] and the multiple cardiac defects without extracardiac abnormalities group [6.1% (3/49), 70.0% (70/100), respectively, both P<0.05], and the pregnancy termination rate in the multiple cardiac defects without extracardiac abnormalities group and the multiple cardiac defects with extracardiac abnormalities group (82.5%,52/63) were significantly higher than that of the single cardiac abnormalities without extracardiac abnormalities group (both P<0.05). (4) After adjusting for age, gravity, parity and performed prenatal diagnosis, maternal age, the diagnosis of gestational age, prognosis grades, co-existence of extracardiac abnormalities, presence of pathogenic genetic abnormalities, and receiving MDT consultation and management were still independent influencing factors of termination of pregnancy of fetuses with cardiac defects (all P<0.05). A total of 29 (7.2%, 29/400) fetal cardiac defects received MDT consultation and management, and compared with those without MDT management, the pregnancy termination rate in the multiple cardiac defects without extracardiac abnormalities group [74.2%(66/89) vs 4/11] and the multiple cardiac defects with extracardiac abnormalities group [87.9%(51/58) vs 1/5] were lower, the differences were statistically significant respectively (all P<0.05). Conclusions: Maternal age, diagnosed gestational age, severity of cardiac defects, extracardiac abnormalities, pathogenic genetic abnormalities and MDT counseling and management are the influencing factors of fetal heart defects pregnancy decision. MDT cooperation approach influences pregnancy decision-making and should be recommended for the management of fetal cardiac defect to reduce unnecessary termination of pregnancy and improve pregnancy outcomes.
Pregnancy ; Female ; Humans ; Retrospective Studies ; Fetal Diseases/diagnosis* ; Heart Defects, Congenital/therapy* ; Fetus ; Decision Making ; Ultrasonography, Prenatal/methods*

OBJECTIVES: To study the left heart structure and functional characteristics of term neonates with intrauterine growth restriction (IUGR). METHODS: This study included 86 term neonates with IUGR admitted to the Neonatal Ward of Beijing Friendship Hospital, Capital Medical University from January 2019 to January 2022 as the IUGR group, as well as randomly selected 86 term neonates without IUGR born during the same period as the non-IUGR group. The clinical data and echocardiographic data were compared between the two groups. RESULTS: The analysis of left heart structure and function showed that compared with the non-IUGR group, the IUGR group had significantly lower left ventricular mass, left ventricular end-diastolic diameter, left ventricular end-systolic diameter, left atrial diameter, end-diastolic interventricular septal thickness, left ventricular posterior wall thickness, left ventricular end-diastolic volume, left ventricular end-systolic volume, and stroke volume (P<0.05) and significantly higher ratio of end-diastolic interventricular septal thickness to left ventricular posterior wall thickness, proportion of neonates with a mitral peak E/A ratio of ≥1, and cardiac index (P<0.05). The Spearman correlation analysis suggested that stroke volume was positively correlated with birth weight and body surface area (r_s=0.241 and 0.241 respectively; P<0.05) and that the ratio of end-diastolic interventricular septal thickness to left ventricular posterior wall thickness was negatively correlated with birth weight and body surface area (r_s=-0.229 and -0.225 respectively; P<0.05). CONCLUSIONS The left ventricular systolic function of neonates with IUGR is not significantly different from that of neonates without IUGR. However, the ventricular septum is thicker in neonates with IUGR. This change is negatively correlated with birth weight and body surface area. The left ventricular diastolic function may be impaired in neonates with IUGR.
Humans ; Infant, Newborn ; Birth Weight ; Echocardiography ; Fetal Growth Retardation ; Heart ; Heart Ventricles/diagnostic imaging* ; Ventricular Function, Left

Objective: To explore the current situation of fetal heart defects in Yunnan Province and surrounding high altitude areas and the social factors affecting pregnancy outcome. Methods: This is a retrospective study. Pregnant woman who underwent fetal echocardiography and diagnosed as fetal cardiac defects in Yunnan Fuwai Cardiovascular Hospital from June 2017 to January 2021 were included. According to the clinical prognostic risk scoring system and grading criteria of fetal cardiac birth defects, the cases were divided into grade Ⅰ to Ⅳ. The disease distribution and proportion of each prognostic grade, pregnancy outcomes were analyzed and compared. The cases were divided into continued pregnancy group and terminated pregnancy group according to pregnancy outcome. The social factors that may affect the selection of pregnancy outcomes were analyzed by multivariate logistic regression analysis. Results: A total of 4 929 fetal echocardiography examination data were collected, and 4 464 cases (90.57%) were from Yunnan Province and surrounding high altitude areas. 2 166 cases of heart defects were finally analyzed, including 998 cases of congenital heart disease (CHD), 93 cases of cardiac tumors, cardiomyopathy and arrhythmia, 1 075 cases of foramen ovale, ductus arteriosus abnormalities and normal variations. The pregnant women were (29.2±5.0) years old with (25.6±3.8) gestational weeks. The number of cases with prognostic grade from Ⅰ to Ⅳ was 1 037 (47.88%), 620 (28.62%), 314 (14.50%), and 44 (2.03%), respectively. And 151 cases (6.97%) were not classified. The cases of normal variation and thin aortic arch development accounted for 42.66% (924/2 166), 5.22% (113/2 166), respectively. The top 3 diseases of grade Ⅱ were ventricular septal defect, coarctation of aorta and mild-moderate pulmonary stenosis, respectively, and their distribution was 11.63% (252/2 166), 3.92% (85/2 166) and 2.35% (51/2 166) respectively in all cases of heart defects, and 25.25% (252/998), 8.52% (85/998) and 5.11% (51/998) respectively in cases of CHD. Among the cases rated as grade Ⅲ and Ⅳ, most of them were complicated congenital heart disease, and the disease types are scattered. The more common cases in grade Ⅲ were complete transposition of great arteries (accounting for 2.40% (52/2 166) of all cases with heart defects, 5.21% (52/998) of all cases with CHD) and pulmonary artery occlusion (type Ⅰ to Ⅲ) with ventricular septal defect (accounting for 2.17% (47/2 166) of all cases with heart defects, and 4.71% (47/998) of all cases with CHD). In grade Ⅳ, single ventricle (0.74% (16/2 166) of all cases with heart defects, 1.60% (16/998) of all cases with CHD) and left ventricular dysplasia syndrome (0.65% (14/2 166) of all cases with heart defects, 1.40% (14/998) of all cases with CHD) are more common. A total of 1 084 cases were successfully followed up, and 675 cases were born, 392 cases were terminated, spontaneous abortion occurred in 17 cases. The proportion of terminated pregnancy cases was significantly increased from grade Ⅰ to Ⅳ, accounting for 5.24% (21/401), 27.78% (70/252), 89.54% (214/239) and 95.56% (43/45), respectively. Among the terminated pregnancy cases, those with grade Ⅲ accounted for the highest proportion (54.59% (214/392)). The distribution of terminated pregnancy cases was mainly complex congenital malformations or diseases with very poor prognosis (pregnancy outcome grade Ⅲ and Ⅳ), and proportion of terminated pregnancy with pregnancy outcome grade Ⅰ and Ⅱ cases (normal variation or good prognosis) accounted for 5.36% (21/392) and 17.86% (70/392), respectively. The results of multivariate logistic regression analysis showed that pregnant women with low education (high school and below: OR=2.73, 95%CI 1.26-5.93, P<0.001; illiteracy: OR=3.27, 95%CI 1.29-7.10, P<0.001) and low family income (Annual income<100 000 yuan: OR=2.47, 95%CI 1.69-5.12, P<0.001) were more likely to choose termination of pregnancy in case of fetal heart defect. Conclusion: In Yunnan province and the surrounding high altitude areas, the disease distribution of fetal heart defect is mainly simple or low-risk disease, but the complex malformation, especially the disease with poor pregnancy outcome, accounts for a relative high proportion. Pregnancy termination also occurs in some cases with good pregnancy outcome. The education level and family income of pregnant women may affect their choice of pregnancy outcome in case of fetal heart defect.
Pregnancy ; Female ; Humans ; Young Adult ; Adult ; Retrospective Studies ; Altitude ; China/epidemiology* ; Heart Defects, Congenital/diagnostic imaging* ; Heart Septal Defects, Ventricular ; Echocardiography ; Fetal Heart/diagnostic imaging*

Objective: To investigate the relationship between the levels of selenium, iron and copper in cord blood of neonates and the risk of congenital heart disease (CHD), and analyze their interaction effects. Methods: The subjects were obtained from the birth cohort in Lanzhou area established from 2010 to 2012. A baseline survey was conducted in the first trimester, and the follow-up was conducted in the second trimester, third trimester and 42 days after delivery. The umbilical vein blood was collected from newborns at delivery, and information on their birth outcomes was extracted from medical records. A nested case-control study was used to select 97 neonates with CHD newly diagnosed by echocardiography as the case group, and 194 neonates were selected as the control group by 1∶2 matching according to their mother's age, block and CHD onset time. Inductively coupled ion mass spectrometry was used to detect the concentrations of selenium, iron and copper in neonatal cord blood. The element exposure was categorized into three groups, the low, medium and high concentrations, according to the quartiles Q₁ and Q₃ of selenium, iron and copper concentrations in the control group. The association between cord blood selenium, iron and copper concentrations and CHD was analyzed by conditional logistic regression model using medium concentration as the reference standard. The association of their interactions with CHD was analyzed by a phase multiplication model. Results: The M (Q₁, Q₃) concentration of neonatal cord blood copper was 746.12 (467.48, 759.74) μg/L in the case group and 535.69 (425.21, 587.79) μg/L in the control group, with a statistically significant difference between the two groups (P<0.05). After adjustment for confounders, logistic regression models showed that the risk of CHD development was increased in neonates with either high copper in cord blood (OR=4.062, 95%CI: 2.013-8.199) or high copper combined with high iron (OR=3.226, 95%CI: 1.343-7.750). No correlation was observed between selenium and iron concentrations and the development of CHD in neonates. There was a multiplicative interaction between copper and iron in cord blood on the risk of developing CHD (OR=1.303, 95%CI: 1.056-1.608). Conclusion: There is a multiplicative interaction between iron and copper elements. The high copper and the high copper combined with high iron in umbilical cord blood are risk factors for neonatal CHD.
Humans ; Infant, Newborn ; Copper/analysis* ; Selenium ; Iron/analysis* ; Fetal Blood/chemistry* ; Case-Control Studies ; Heart Defects, Congenital

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

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