scholarly journals Prediction of newborn’s body mass index using nationwide multicenter ultrasound data: a machine-learning study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Kwang-Sig Lee ◽  
◽  
Ho Yeon Kim ◽  
Se Jin Lee ◽  
Sung Ok Kwon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Body Mass Index ◽  
Random Forest ◽  
Body Mass ◽  
Gestational Age ◽  
Variable Importance ◽  
Abdominal Circumference ◽  
Learning Study ◽  
Gestational Age At Delivery ◽  
Maternal Bmi

Abstract Background This study introduced machine learning approaches to predict newborn’s body mass index (BMI) based on ultrasound measures and maternal/delivery information. Methods Data came from 3159 obstetric patients and their newborns enrolled in a multi-center retrospective study. Variable importance, the effect of a variable on model performance, was used for identifying major predictors of newborn’s BMI among ultrasound measures and maternal/delivery information. The ultrasound measures included biparietal diameter (BPD), abdominal circumference (AC) and estimated fetal weight (EFW) taken three times during the week 21 - week 35 of gestational age and once in the week 36 or later. Results Based on variable importance from the random forest, major predictors of newborn’s BMI were the first AC and EFW in the week 36 or later, gestational age at delivery, the first AC during the week 21 - the week 35, maternal BMI at delivery, maternal weight at delivery and the first BPD in the week 36 or later. For predicting newborn’s BMI, linear regression (2.0744) and the random forest (2.1610) were better than artificial neural networks with one, two and three hidden layers (150.7100, 154.7198 and 152.5843, respectively) in the mean squared error. Conclusions This is the first machine-learning study with 64 clinical and sonographic markers for the prediction of newborns’ BMI. The week 36 or later is the most effective period for taking the ultrasound measures and AC and EFW are the best predictors of newborn’s BMI alongside gestational age at delivery and maternal BMI at delivery.

scholarly journals Predictors of Newborn’s Weight for Height: A Machine Learning Study Using Nationwide Multicenter Ultrasound Data

Diagnostics ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1280
Author(s):  
Ki Ahn ◽  
Kwang-Sig Lee ◽  
Se Lee ◽  
Sung Kwon ◽  
Sunghun Na ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Performance Measures ◽  
Gestational Age ◽  
Mean Squared Error ◽  
Variable Importance ◽  
Learning Study ◽  
Delivery Time ◽  
Fetal Biometry ◽  
Squared Error

There has been no machine learning study with a rich collection of clinical, sonographic markers to compare the performance measures for a variety of newborns’ weight-for-height indicators. This study compared the performance measures for a variety of newborns’ weight-for-height indicators based on machine learning, ultrasonographic data and maternal/delivery information. The source of data for this study was a multi-center retrospective study with 2949 mother–newborn pairs. The mean-squared-error-over-variance measures of five machine learning approaches were compared for newborn’s weight, newborn’s weight/height, newborn’s weight/height2 and newborn’s weight/hieght3. Random forest variable importance, the influence of a variable over average node impurity, was used to identify major predictors of these newborns’ weight-for-height indicators among ultrasonographic data and maternal/delivery information. Regarding ultrasonographic fetal biometry, newborn’s weight, newborn’s weight/height and newborn’s weight/height2 were better indicators with smaller mean-squared-error-over-variance measures than newborn’s weight/height3. Based on random forest variable importance, the top six predictors of newborn’s weight were the same as those of newborn’s weight/height and those of newborn’s weight/height2: gestational age at delivery time, the first estimated fetal weight and abdominal circumference in week 36 or later, maternal weight and body mass index at delivery time, and the first biparietal diameter in week 36 or later. These six predictors also ranked within the top seven for large-for-gestational-age and the top eight for small-for-gestational-age. In conclusion, newborn’s weight, newborn’s weight/height and newborn’s weight/height2 are more suitable for ultrasonographic fetal biometry with smaller mean-squared-error-over-variance measures than newborn’s weight/height3. Machine learning with ultrasonographic data would be an effective noninvasive approach for predicting newborn’s weight, weight/height and weight/height2.

scholarly journals The possibility of modifications methods of determine volume of amniotic fluid

2016 ◽  
Vol 65 (3) ◽  
pp. 12-17
Author(s):  
Viktor A Mudrov
Keyword(s):  
Body Mass Index ◽  
Amniotic Fluid ◽  
Pregnant Women ◽  
Body Mass ◽  
Gestational Age ◽  
First Trimester ◽  
Fetal Weight ◽  
Abdominal Circumference ◽  
Pregnancy And Childbirth ◽  
Maternity Hospitals

Selection of the optimal tactics of pregnancy and childbirth significantly depends on the expected volume of amniotic fluid. The amount of amniotic fluid reflects a condition of a fetus and changes at pathological conditions of both a fetus, and an uteroplacental complex. The aim of the study was a modification of methods for determining the expected volume of amniotic fluid. On the basis of maternity hospitals Trans-Baikal Region in the years 2013-2015 was held retrospective and prospective analysis of 300 labor histories, which were divided into 3 equal groups: 1 group - pregnant women with a body mass index (BMI) for Quetelet less than 24, Group 2 - with a BMI from 24 to 30, group 3 - with a BMI more than 30. In order to determine the expected volume of amniotic fluid were used the subjective method, the Chamberlain’s and Phelan’s methods. The error in determining volume of amniotic fluid by the existing methods exceeds 10 %, that defined need of creation of a quantitative method. On the basis of mathematical and 3d-modeling of the volume of amniotic fluid and fetal weight determined pattern change, which is expressed by the formula: VAF = IAF × М × π / GA2, where IAF - index of amniotic fluid (mm), M - fetal weight (g), GA - gestational age (weeks). Through a comprehensive analysis of anthropometric research of the pregnant women defined formula’s volume of amniotic fluid: V = 0,017 × HUF × (AC - 25 × BMI / GA)2 - М, where GA - gestational age (weeks), AC - abdominal circumference of the pregnant women (cm), BMI - body mass index for Quetelet in the first trimester of pregnancy (kg/m2), HUF - height of an uterine fundus (cm), M - the estimated fetal weight (g). In calculating volume of amniotic fluid according to the proposed ultrasonic formula error does not exceed 5,3 %, anthropometric formula error does not exceed 10,2 %. Thus, the method has a smaller error compared to the standard, and can be used to reliably determine volume of amniotic fluid in II and III trimester of pregnancy.

scholarly journals An investigation into the correlation between pre-pregnancy body mass index and birth outcomes of newborn in Jersey

2020 ◽  
Vol 79 (OCE2) ◽  
Author(s):  
Urszula Sliwka ◽  
Katarzyna Przybylowicz ◽  
Neil MacLachlan ◽  
Jakub Morze ◽  
Anna Danielewicz ◽  
...  
Keyword(s):  
Body Mass Index ◽  
Nutritional Status ◽  
Pregnant Women ◽  
Body Mass ◽  
Birth Outcomes ◽  
Gestational Age ◽  
Newborn Outcomes ◽  
Infant Birth ◽  
Maternal Bmi ◽  
Delivery Type

AbstractThe role of nutritional status of pregnant women and birth outcomes is ambiguous. Recent studies show that pre-pregnancy body weight is equally important as weight gain during pregnancy. Body mass index (BMI) is the most accessible and easy to check a nutritional status index, which may help to control the gestation and predict infant health outcome. This study aimed to examine the associations between pre-pregnancy body mass index and the infant birth parameters. A presented observational study was offered to 200 pregnant women from Antenatal Clinic at Jersey General Hospital in 2017. Total number of 83 women agreed to take part in this project. Diet, lifestyle, socio-economic, and demographic data were obtained from participants. Delivery and birth data were taken from hospital records. Offspring feeding data and selected anthropometric measurements for mothers and their newborns were also collected. Differences between BMI for delivery type and way of feeding were verified with chi-square test. Differences and correlation between maternal BMI and newborn outcomes were verified with Kruskal-Wallis’ test and Spearman's rank test. Mean BMI of mothers included to the study was 22.8 ± 4.4 with mean weight 61.9 ± 11.6. Before pregnancy BMI was normal in 67% women and about 23% was overweight or obese. We do not observed differences between delivery type and way of feeding during first 48 hours, and women in BMI categories. Also no differences and correlation were observed for the Apgar score, gestational age of birth, and newborn's weight and length at birth. However, newborn weight correlated with newborn length (r = 0.433) and gestational age (r = 0.568) at birth. Concluding, the maternal pre-pregnancy BMI was not correlated with type of delivery, way of feeding and newborn outcomes. Previous studies show that high pre-pregnancy maternal BMI may be associated with adverse offspring outcomes at birth and later life. Future extended research is needed to explain these relations, with inclusion of the specific factors as maternal diet, lifestyle and ethnicity.

Abstract P176: Maternal and Neonatal Outcomes in Normal and Preeclamptic Pregnancies - A Comparative Prospective Study

Hypertension ◽  
2016 ◽  
Vol 68 (suppl_1) ◽  
Author(s):  
Ram R Kalagiri ◽  
Syeda H Afroze ◽  
Niraj Vora ◽  
Nathan Drever ◽  
Madhava R Beeram ◽  
...  
Keyword(s):  
Blood Pressure ◽  
Body Mass Index ◽  
Prospective Study ◽  
Body Mass ◽  
Gestational Age ◽  
De Novo ◽  
Average Hospital ◽  
Gestational Age At Delivery ◽  
Student’S T ◽  
Placental Thickness

Background: Preeclampsia (PreE) is de novo development of hypertension and proteinuria after 20 weeks of gestation with multiple pathophysiologic triggers affecting 3-8% of pregnancies. PreE has a significant link to alterations of feto-placental stress that pass to the offspring causing detrimental effects. We assessed and compared the pregnancy outcomes between patients with and without PreE. Methods: We recruited 35 normal pregnant (NP) and 25 PreE consenting patients in an IRB approved prospective study at Scott & White Memorial Hospital, Temple, Texas. We evaluated maternal age, body mass index (BMI), blood pressures, proteinuria, and gestational age at delivery. We divided the PreE subjects into early (before 34 weeks) and late PreE (after 34 weeks) groups and compared their outcomes. Placental thickness and volumes were measured. We also evaluated neonates for intrauterine growth restriction (IUGR), gestational age at birth, anthropometric measurements including Ponderal Index (PI), length of hospitalization and other neonatal complications. Comparisons were performed using Student’s t test. Results: Maternal: The systolic blood pressure (SBP) and diastolic blood pressure (DBP) were higher in PreE (SBP 166 ± 11; DBP 93 ± 10) compared to normal pregnancies (SBP 122 ± 10; DBP 74 ± 9; p <0.05 for each case). PreE mothers had higher urinary protein excretion (457mg/24h ± 140) compared to NP (160 mg/24h ± 44; p <0.05 for each case). We did not find any difference in body mass index (BMI). Placenta: The placental thickness in early PreE subjects was 25mm compared to 32mm in late PreE (p <0.05) and placental volume in early PreE 296 cm 3 compared to 393cm 3 (p <0.05). Neonatal: The average GA at delivery was lower in PreE (34.8 wks. ± 4) compared to NP (39.2 weeks ± 0.3; p <0.05). Average hospital stay for PreE babies were longer (20 days ± 5) compared to NP (2 days ± 1; p <0.05). The PreE babies were SGA with lower PI (2.28 ± 0.3) compare to the NP babies (2.95 ± 0.2; p <0.05). Gestational age at delivery in early PreE is 32.4 weeks vs 36.8 weeks in late PreE (p <0.05). About 56% of the infants who are born to early PreE are small for gestational age (SGA) and 30% of the infants who are born to late PreE are SGA. PreE babies had multiple complications compared to NP babies.

scholarly journals Maternal body mass index in early pregnancy and severe asphyxia-related complications in preterm infants

2020 ◽  
Vol 49 (5) ◽  
pp. 1647-1660
Author(s):  
Ayoub Mitha ◽  
Ruoqing Chen ◽  
Stefan Johansson ◽  
Neda Razaz ◽  
Sven Cnattingius
Keyword(s):  
Body Mass Index ◽  
Preterm Infants ◽  
Body Mass ◽  
Early Pregnancy ◽  
Gestational Age ◽  
Maternal Body Mass Index ◽  
Neonatal Seizures ◽  
Maternal Body ◽  
Apgar Scores ◽  
Maternal Bmi

Abstract Background Little is known about the associations between maternal body mass index (BMI) and asphyxia-related morbidity in preterm infants (&lt;37 weeks). We aimed to investigate associations between maternal BMI in early pregnancy and severe asphyxia-related neonatal complications in preterm infants (&lt;37 weeks) and to examine whether possible associations were mediated by overweight- or obesity-related complications. Methods In this Swedish population-based cohort of 62 499 singleton non-malformed preterm infants born from 1997 to 2011, risks of low Apgar scores (0–3) at 5 and 10 minutes, neonatal seizures and intraventricular haemorrhage (IVH) were estimated through two analytical approaches. In the conventional approach, the denominator for risk was all live births at a given gestational age. In the fetuses-at-risk (FAR) approach, the denominator for risk was ongoing pregnancies at a given gestational age. Results Using the conventional approach, adjusted risk ratios per 10-unit BMI increase were 1.32 [95% confidence interval (CI) 1.13–1.54] and 1.37 (95% CI 1.12–1.67) for low Apgar scores at 5 and 10 minutes, respectively; 1.28 (95% CI 1.00–1.65) for neonatal seizures; and 1.18 (95% CI 1.01–1.37) for IVH. Using the FAR approach, corresponding risks were higher. These associations varied by gestational age (&lt;32 and 32–36 weeks). Associations between maternal BMI and asphyxia-related outcomes were partly mediated through lower gestational age. Conclusions Increasing maternal BMI in early pregnancy is associated with increased risks of severe asphyxia-related complications in preterm infants. Our findings add to the evidence to support interventions to reduce obesity in woman of reproductive age.

scholarly journals Assessing the relationship between pregravid body mass index and risk of adverse maternal pregnancy and neonatal outcomes: prospective data in Southwest China

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yue Chen ◽  
Ke Wan ◽  
Yunhui Gong ◽  
Xiao Zhang ◽  
Yi Liang ◽  
...  
Keyword(s):  
Body Mass Index ◽  
Cesarean Delivery ◽  
Body Mass ◽  
Gestational Age ◽  
Pregnancy Outcomes ◽  
Maternal Age ◽  
Southwest China ◽  
Adverse Pregnancy Outcomes ◽  
Relative Importance ◽  
Adverse Pregnancy

AbstractThe relevance of pregestational body mass index (BMI) on adverse pregnancy outcomes remained unclear in Southwest China. This study aimed to investigate the overall and age-category specific association between pre-gestational BMI and gestational diabetes mellitus (GDM), preeclampsia, cesarean delivery, preterm delivery, stillbirth, macrosomia, and small-for-gestational age (SGA) or large-for-gestational age (LGA) neonates in Southwest China. Furthermore, it explores the relative importance of influence of pregravid BMI and maternal age on pregnancy outcomes. 51,125 Chinese singleton pregnant women were recruited as study subjects. Multiple logistic regression models were used to examine the influence of pre-pregnancy BMI on adverse pregnancy outcomes. Gradient boosting machine was used to evaluate the relative importance of influence of pregravid BMI and maternal age on pregnancy outcomes. It is found that women who were overweight or obese before pregnancy are at higher risk of adverse pregnancy outcomes except for SGA neonates, while pre-pregnancy underweight is a protective factor for GDM, preeclampsia, cesarean delivery, macrosomia and LGA, but not SGA. Younger mothers are more susceptible to GDM and macrosomia neonates, while older mothers are more prone to preeclampsia. Pre-pregnancy BMI has more influence on various pregnancy outcomes than maternal age. To improve pregnancy outcomes, normal BMI weight as well as relatively young maternal ages are recommended for women in child-bearing age.

Body Mass Index Change Between Pregnancies and Small for Gestational Age Births

2004 ◽  
Vol 104 (2) ◽  
pp. 286-292 ◽  
Author(s):  
Christine J. Cheng ◽  
Kerry Bommarito ◽  
Akihiko Noguchi ◽  
William Holcomb ◽  
Terry Leet
Keyword(s):  
Body Mass Index ◽  
Body Mass ◽  
Gestational Age ◽  
Small For Gestational Age ◽  
Body Mass Index Change ◽  
Index Change
Sign in / Sign up

Export Citation Format

Share Document