An artificial neural network (ANN) model was developed to predict the risks of congenital heart disease (CHD) in pregnant women.This hospital-based case-control study involved 119 CHD cases and 239 controls all recruited from birth defect surveillance hospitals in Hunan Province between July 2013 and June 2014. All subjects were interviewed face-to-face to fill in a questionnaire that covered 36 CHD-related variables. The 358 subjects were randomly divided into a training set and a testing set at the ratio of 85:15. The training set was used to identify the significant predictors of CHD by univariate logistic regression analyses and develop a standard feed-forward back-propagation neural network (BPNN) model for the prediction of CHD. The testing set was used to test and evaluate the performance of the ANN model. Univariate logistic regression analyses were performed on SPSS 18.0. The ANN models were developed on Matlab 7.1.The univariate logistic regression identified 15 predictors that were significantly associated with CHD, including education level (odds ratio = 0.55), gravidity (1.95), parity (2.01), history of abnormal reproduction (2.49), family history of CHD (5.23), maternal chronic disease (4.19), maternal upper respiratory tract infection (2.08), environmental pollution around maternal dwelling place (3.63), maternal exposure to occupational hazards (3.53), maternal mental stress (2.48), paternal chronic disease (4.87), paternal exposure to occupational hazards (2.51), intake of vegetable/fruit (0.45), intake of fish/shrimp/meat/egg (0.59), and intake of milk/soymilk (0.55). After many trials, we selected a 3-layer BPNN model with 15, 12, and 1 neuron in the input, hidden, and output layers, respectively, as the best prediction model. The prediction model has accuracies of 0.91 and 0.86 on the training and testing sets, respectively. The sensitivity, specificity, and Yuden Index on the testing set (training set) are 0.78 (0.83), 0.90 (0.95), and 0.68 (0.78), respectively. The areas under the receiver operating curve on the testing and training sets are 0.87 and 0.97, respectively.This study suggests that the BPNN model could be used to predict the risk of CHD in individuals. This model should be further improved by large-sample-size research.
Congenital heart defects (CHDs) are the most common birth defects (BDs) and account for nearly one-third of all BDs. The aim of this article was to investigate the epidemiology and major subtypes of CHDs in Hunan Province, China in the last 5 years.CHD surveillance data from 2012 to 2016 were collected from 52 registered hospitals in Hunan. The prevalence rates of CHDs, incidence rates of CHDs combined with other BDs, and rates of termination of pregnancy (TOP) for CHDs among different regions, infant sexes, and maternal ages were calculated for both early fetuses (<28 weeks of gestation) and perinatal infants (PIs) (between 28 weeks of gestation and 7 days after birth). Both the constituent ratio and prevalence rates were computed among subtypes.CHDs were found in 6289 out of 673,060 births. The overall prevalence was 93.44 per 10,000 PIs, with 19.27 and 74.17 per 10,000 in early fetuses and PIs, respectively. The risks of CHDs were higher in infants from urban areas than those from rural areas during the whole gestation and were higher in male infants than in female infants during the perinatal period. The total prevalence of CHDs increased significantly with maternal age (χ2 trend = 141.84, P < .05). Among fetuses in early gestation, there were 288 cases (22.21%) of CHDs combined with other BDs and 1292 cases (99.61%) of TOP for CHD. The 3 major subtypes of CHDs were ventricular septal defect (VSD) (22.06%), Tetralogy of Fallot (TOF) (9.43%), and atrioventricular septal defect (AVSD) (6.69%). Among PIs, there were 1541 cases (30.87%) of CHD diagnosed before delivery and 1184 cases (76.83%) were TOP. The 3 major subtypes were atrial septal defect (ASD) (42.81%), patent ductus arteriosus (PDA) (16.07%), and VSDs (15.21%).The total prevalence of CHD in Hunan Province and the rate of TOP for CHD was high, especially for early-gestation fetuses. Pregnancies in urban women, male PIs, and maternal age were the risk factors for CHDs. Among early-gestation fetuses, the most common types were VSD, TOF, and ASD, and among PIs, the most common types were ASD, PDA, and VSD.
Background This study aimed to evaluate the incidence rates and risks of pregnancy complications among nulliparous and multiparous women with advanced maternal age (AMA, ≥35 years) in China. Methods We performed a community-based prospective cohort study of 10,171 pregnant women in selected two sub-districts and 11 towns of Liuyang from 2013 to 2015. All subjects were followed up from the first prenatal care (at ≤12 weeks) to delivery, and risks of pregnancy complications were compared by parity and maternal age groups. Results Among nulliparas, women with AMA showed significantly increased risks for gestational hypertension (OR 8.44, 95%CI 1.68–2.88), preeclampsia/eclampsia (OR 9.92, 95%CI 4.87–18.78), premature rupture of membrane (OR 6.84, 95%CI 2.00–17.69), as compared to women in the 20–29-year age group. Among multiparas with AMA, increased risks were found for gestational diabetes mellitus (OR 3.29, 95%CI 1.76–5.94), anemia (OR 1.85, 95%CI 1.25–2.69), polyhydramnios (OR 3.29, 95%CI 1.56–6.64), premature rupture of membrane (OR 5.14, 95%CI 2.12–12.29), and preterm labor (OR 1.89, 95CI 1.42–2.50). Conclusions Women with AMA were associated with increased risks of pregnancy complications, and complications with increased risks differed in nulliparas and multiparas. Women with AMA should be identified as a high-risk group in clinical practice.
BackgroundA risk prediction model of non-syndromic cleft lip with or without cleft palate (NSCL/P) was established by a discriminant analysis to predict the individual risk of NSCL/P in pregnant women.MethodsA hospital-based case–control study was conducted with 113 cases of NSCL/P and 226 controls without NSCL/P. The cases and the controls were obtained from 52 birth defects’ surveillance hospitals in Hunan Province, China. A questionnaire was administered in person to collect the variables relevant to NSCL/P by face to face interviews. Logistic regression models were used to analyze the influencing factors of NSCL/P, and a stepwise Fisher discriminant analysis was subsequently used to construct the prediction model.ResultsIn the univariate analysis, 13 influencing factors were related to NSCL/P, of which the following 8 influencing factors as predictors determined the discriminant prediction model: family income, maternal occupational hazards exposure, premarital medical examination, housing renovation, milk/soymilk intake in the first trimester of pregnancy, paternal occupational hazards exposure, paternal strong tea drinking, and family history of NSCL/P. The model had statistical significance (lambda = 0.772, chi-square = 86.044, df = 8, P < 0.001). Self-verification showed that 83.8 % of the participants were correctly predicted to be NSCL/P cases or controls with a sensitivity of 74.3 % and a specificity of 88.5 %. The area under the receiver operating characteristic curve (AUC) was 0.846.ConclusionsThe prediction model that was established using the risk factors of NSCL/P can be useful for predicting the risk of NSCL/P. Further research is needed to improve the model, and confirm the validity and reliability of the model.
This article by Jiayou Luo et al. reminds us that even in countries with a large population, children with very traditional values end up being the victims of changes in work patterns, migration, and social norms. This article suggests that children who are attended by nonparents-either grandparents or other relatives-face less care and many nutrition problems, such as low intake of some nutrients and poor physical development related to nutritional status. The authors suggest that nutrition is the key factor and recommend nutritional intervention programs to improve the children's living conditions. However, in Spain, work by Bel et al. 1 showed an important proportion of children with significant growth retardation upon entering a foster home, although significant catch-up growth was observed at the end of their stay. Growth failure in this population did not appear to be related to nutritional status. While this article does make the case for nutrition being most affected by the setting upon being left behind, it also raises the important issue of how a society like China, which is changing so rapidly, overlooks some of the basic tenets of family life. It also highlights how ill-prepared China seems to be in safeguarding its most vulnerable citizens from such basic rights as a healthy diet and a safe and nurturing environment. 2 Changes in labor patterns directly affect social patterns, and traditional villages and small cities are not immune from their direct effects on children's well-being.
ObjectiveTo evaluate perinatal outcomes and congenital heart defect (CHD) prognosis in a non-selected population.MethodsThe population-based surveillance data used in this assessment of CHDs were based on birth defect surveillance data collected from 2010–2012 in Liuyang City, China. Infants living with CHDs were followed up for 5 years to determine their prognosis. Prevalence, prenatal diagnosis, perinatal outcomes, and total and type-specific prognosis data were assessed using SPSS 18.0.ResultsIn total, 190 CHD cases were identified among the 53313 included perinatal infants (PIs), indicating a CHD prevalence of 35.64 per 10000 PIs in this non-selected population. The five most frequently identified types of CHDs were ventricular septal defects (VSDs, 38.95%), atrial septal defects (ASDs, 15.79%), cardiomegaly (7.89%), tetralogy of Fallot (TOF, 5.79%), and atrioventricular septal defects (AVSDs, 5.26%). Of the 190 CHD cases, 110 (57.89%) were diagnosed prenatally, 30 (15.79%) were diagnosed with associated malformations, and 69 (36.32%) resulted in termination of pregnancy (TOP). Moreover, 15 (7.89%) PIs died within 7 days after delivery, and 42 (22.10%) died within 1 year. In contrast, 79 (41.58%) were still alive after 5 years. When TOP cases were included, the 5-year survival rate of PIs with prenatally detected CHDs was lower than that of PIs with postnatally detected CHDs (25.45% vs. 63.75%). The CHD subtype associated with the highest rate of infant (less than 1 year old) mortality was transposition of the great arteries (100%). The subtypes associated with higher 5-year survival rates were patent ductus arteriosus (80%), ASD (63.33%), VSD (52.70%) and AVSD (50%).ConclusionsThe rates of prenatal CHD detection and TOP were high in this study population, and the 5-year survival rate of PIs with CHDs was low. The government should strengthen efforts to educate pediatricians regarding this issue and provide financial assistance to improve the prognosis of infants living with CHDs, especially during the first year of life.
Aim To investigate the epidemiology of chromosomal abnormalities (CA) in fetuses of all pregnancies based on a provincial‐wide birth defects‐monitoring system, which could provide scientific basis for making relatively policy and research. Methods Chromosomal abnormalities cases were collected from all hospitals in Hunan Province, China, between 2016 and 2019. The prevalence of CAs was calculated to examine associations among infant sex, maternal age and region. The rates of prenatal diagnosis and termination of pregnancy (TOP) involving CA or associated anomalies were calculated as rates or proportions. Results From 2016 to 2019, a total of 2 883 890 perinatal infants (28 weeks of gestation to postpartum 7 days) underwent prenatal screening and diagnostic tests, and 3181 fetuses were diagnosed as CA, with the prevalence of 11.03/10 000. The average prevalence of CAs was higher for male than female fetuses (11.33/10 000 vs 10.06/10 000) (OR = 1.13, 95% CI: 1.05–1.21), which was higher in urban areas than rural areas (23.03/10 000 vs 7.13/10 000) (OR = 3.23, 95% CI: 3.02–3.47), and the prevalence increased linearly with maternal age (Xtrend2 = 1821.844, P = 0.000). Among the fetuses with CAs, 3097 (97.36%) were diagnosed prenatally, and 3046 (98.35%) underwent TOP. The majority of CA were numerical abnormalities (90.18%). The main types of numerical autosomal abnormalities were trisomy 21 (6.69/10 000, 59.57%), trisomy 18 (1.13/10 000, 10.04%) and trisomy 13 (0.21/10 000, 1.88%). The main types of numerical gonosomal abnormalities were Klinefelter syndrome (0.68/10 000, 6.02%), Turner syndrome (0.49/10 000, 4.39%), Triple X syndrome (0.26/10 000, 2.29%) and 47,XYY syndrome (0.21/10 000, 1.91%). The three associated anomalies with the highest proportions were congenital heart defects (CHD) (41.06%), cleft palate or/and cleft lip (10.89%) and congenital talipes equinovarus (8.94%). Conclusion The prevalence of CA was lower than that reported. Chromosome detection should be further promoted including test contest and coverage, especially for urban areas, older mothers and fetuses with CHD, cleft palate or/and cleft lip or congenital talipes equinovarus.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.