scholarly journals Prediction of Gestational Age at Birth using an Artificial Neural Networks in Singleton Preterm Birth

2018 ◽  
Vol 22 (3) ◽  
pp. 151-161
Author(s):  
이지윤 ◽  
정은진 ◽  
이광식 ◽  
김승우 ◽  
안기훈 ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Preterm Birth ◽  
Gestational Age ◽  
Artificial Neural ◽  
Gestational Age At Birth ◽  
Age At Birth

scholarly journals Maternal biological age assessed in early pregnancy is associated with gestational age at birth

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Eva E. Lancaster ◽  
Dana M. Lapato ◽  
Colleen Jackson-Cook ◽  
Jerome F. Strauss ◽  
Roxann Roberson-Nay ◽  
...  
Keyword(s):  
Risk Factors ◽  
Preterm Birth ◽  
Early Pregnancy ◽  
Gestational Age ◽  
Cellular Aging ◽  
Biological Age ◽  
Potential Candidate ◽  
A Genome ◽  
Gestational Age At Birth ◽  
Age At Birth

AbstractMaternal age is an established predictor of preterm birth independent of other recognized risk factors. The use of chronological age makes the assumption that individuals age at a similar rate. Therefore, it does not capture interindividual differences that may exist due to genetic background and environmental exposures. As a result, there is a need to identify biomarkers that more closely index the rate of cellular aging. One potential candidate is biological age (BA) estimated by the DNA methylome. This study investigated whether maternal BA, estimated in either early and/or late pregnancy, predicts gestational age at birth. BA was estimated from a genome-wide DNA methylation platform using the Horvath algorithm. Linear regression methods assessed the relationship between BA and pregnancy outcomes, including gestational age at birth and prenatal perceived stress, in a primary and replication cohort. Prenatal BA estimates from early pregnancy explained variance in gestational age at birth above and beyond the influence of other recognized preterm birth risk factors. Sensitivity analyses indicated that this signal was driven primarily by self-identified African American participants. This predictive relationship was sensitive to small variations in the BA estimation algorithm. Benefits and limitations of using BA in translational research and clinical applications for preterm birth are considered.

scholarly journals Preterm birth and risk of chronic kidney disease from childhood into mid-adulthood: national cohort study

BMJ ◽  
2019 ◽  
pp. l1346 ◽  
Author(s):  
Casey Crump ◽  
Jan Sundquist ◽  
Marilyn A Winkleby ◽  
Kristina Sundquist
Keyword(s):  
Cohort Study ◽  
Preterm Birth ◽  
Environmental Factors ◽  
Gestational Age ◽  
Early Term ◽  
Extremely Preterm ◽  
National Cohort ◽  
Gestational Age At Birth ◽  
Age At Birth

Abstract Objective To investigate the relation between preterm birth (gestational age <37 weeks) and risk of CKD from childhood into mid-adulthood. Design National cohort study. Setting Sweden. Participants 4 186 615 singleton live births in Sweden during 1973-2014. Exposures Gestational age at birth, identified from nationwide birth records in the Swedish birth registry. Main outcome measures CKD, identified from nationwide inpatient and outpatient diagnoses through 2015 (maximum age 43 years). Cox regression was used to examine gestational age at birth and risk of CKD while adjusting for potential confounders, and co-sibling analyses assessed the influence of unmeasured shared familial (genetic or environmental) factors. Results 4305 (0.1%) participants had a diagnosis of CKD during 87.0 million person years of follow-up. Preterm birth and extremely preterm birth (<28 weeks) were associated with nearly twofold and threefold risks of CKD, respectively, from birth into mid-adulthood (adjusted hazard ratio 1.94, 95% confidence interval 1.74 to 2.16; P<0.001; 3.01, 1.67 to 5.45; P<0.001). An increased risk was observed even among those born at early term (37-38 weeks) (1.30, 1.20 to 1.40; P<0.001). The association between preterm birth and CKD was strongest at ages 0-9 years (5.09, 4.11 to 6.31; P<0.001), then weakened but remained increased at ages 10-19 years (1.97, 1.57 to 2.49; P<0.001) and 20-43 years (1.34, 1.15 to 1.57; P<0.001). These associations affected both males and females and did not seem to be related to shared genetic or environmental factors in families. Conclusions Preterm and early term birth are strong risk factors for the development of CKD from childhood into mid-adulthood. People born prematurely need long term follow-up for monitoring and preventive actions to preserve renal function across the life course.

scholarly journals Risk of hypertension into adulthood in persons born prematurely: a national cohort study

2019 ◽  
Vol 41 (16) ◽  
pp. 1542-1550 ◽  
Author(s):  
Casey Crump ◽  
Jan Sundquist ◽  
Kristina Sundquist
Keyword(s):  
Cohort Study ◽  
Preterm Birth ◽  
Environmental Factors ◽  
Gestational Age ◽  
Large Population ◽  
Increased Risk ◽  
Extremely Preterm ◽  
National Cohort ◽  
Gestational Age At Birth ◽  
Age At Birth

Abstract Aims Preterm birth has been associated with elevated blood pressure early in life; however, hypertension risks from childhood into adulthood remain unclear. We conducted a large population-based study to examine gestational age at birth in relation to hypertension risks from childhood into adulthood. Methods and results A national cohort study was conducted of all 4 193 069 singleton live births in Sweden during 1973–2014, who were followed up for hypertension identified from nationwide inpatient and outpatient (specialty and primary care) diagnoses from any health care encounters through 2015 (maximum age 43 years; median 22.5). Cox regression was used to examine gestational age at birth in relation to hypertension risk while adjusting for other perinatal and maternal factors, and co-sibling analyses assessed the potential influence of unmeasured shared familial (genetic and/or environmental) factors. In 86.8 million person-years of follow-up, 62 424 (1.5%) persons were identified with hypertension (median age 29.8 years at diagnosis). Adjusted hazard ratios for new-onset hypertension at ages 18–29 years associated with preterm (&lt;37 weeks) and extremely preterm (22–27 weeks) birth were 1.28 [95% confidence interval (CI), 1.21–1.36] and 2.45 (1.82–3.31), respectively, and at ages 30–43 years were 1.25 (1.18–1.31) and 1.68 (1.12–2.53), respectively, compared with full-term birth (39–41 weeks). These associations affected males and females similarly and appeared substantially related to shared genetic or environmental factors in families. Conclusions In this large national cohort, preterm birth was associated with increased risk of hypertension into early adulthood. Persons born prematurely may need early preventive evaluation and long-term monitoring for the development of hypertension.

Effects of Antenatal Depression and Antidepressant Treatment on Gestational Age at Birth and Risk of Preterm Birth

2007 ◽  
Vol 164 (8) ◽  
pp. 1206-1213 ◽  
Author(s):  
Rita Suri ◽  
Lori Altshuler ◽  
Gerhard Hellemann ◽  
Vivien K. Burt ◽  
Ana Aquino ◽  
...  
Keyword(s):  
Preterm Birth ◽  
Gestational Age ◽  
Antidepressant Treatment ◽  
Antenatal Depression ◽  
Gestational Age At Birth ◽  
Age At Birth

Comparison of neural networks and statistical models to predict gestational age at birth

1997 ◽  
Vol 6 (3) ◽  
pp. 158-164 ◽  
Author(s):  
J. L. Eastaugh ◽  
S. W. Smye ◽  
S. Snowden ◽  
J. J. Walker ◽  
P. R. F. Dear ◽  
...  
Keyword(s):  
Neural Networks ◽  
Gestational Age ◽  
Statistical Models ◽  
Gestational Age At Birth ◽  
Age At Birth

scholarly journals Comparison of Data Mining Algorithms Using Artificial Neural Networks (ANN) and Naive Bayes for Preterm Birth Prediction

2020 ◽  
Vol 1641 ◽  
pp. 012068
Author(s):  
Diah Puspitasari ◽  
Kresna Ramanda ◽  
Adi Supriyatna ◽  
Mochamad Wahyudi ◽  
Erma Delima Sikumbang ◽  
...  
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Preterm Birth ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Data Mining Algorithms ◽  
Artificial Neural ◽  
Mining Algorithms

scholarly journals Uterine distention as a factor in birth timing: retrospective nationwide cohort study in Sweden

BMJ Open ◽  
2018 ◽  
Vol 8 (10) ◽  
pp. e022929 ◽  
Author(s):  
Jonas Bacelis ◽  
Julius Juodakis ◽  
Kristina M Adams Waldorf ◽  
Verena Sengpiel ◽  
Louis J Muglia ◽  
...  
Keyword(s):  
Cohort Study ◽  
Preterm Birth ◽  
Fetal Growth ◽  
Gestational Age ◽  
Large For Gestational Age ◽  
Maternal Height ◽  
Birth Timing ◽  
Gestational Age At Birth ◽  
Age At Birth ◽  
Singleton Pregnancies

ObjectivesTo determine whether uterine distention is associated with human pregnancy duration in a non-invasive observational setting.DesignRetrospective cohort study modelling uterine distention by interaction between maternal height and uterine load.SettingThe study is based on the 1990–2013 population data from all delivery units in Sweden.ParticipantsUncomplicated first pregnancies of healthy Nordic-born mothers with spontaneous onset of labour. Pregnancies were classified as twin (n=2846) or singleton (n=527 868). Singleton pregnancies were further classified as carrying a large for gestational age fetus (LGA, n=24 286) or small for gestational age fetus (SGA, n=33 780).Outcome measuresStatistical interaction between maternal height and uterine load categories (twin vs singleton pregnancies, and LGA vs SGA singleton pregnancies), where the outcome is pregnancy duration.ResultsIn all models, statistically significant interaction was found. Mothers carrying twins had 2.9 times larger positive linear effect of maternal height on gestational age than mothers carrying singletons (interaction p=5e−14). Similarly, the effect of maternal height was strongly modulated by the fetal growth rate in singleton pregnancies: the effect size of maternal height on gestational age in LGA pregnancies was 2.1 times larger than that in SGA pregnancies (interaction p<1e−11). Preterm birth OR was 1.4 when the mother was short, and 2.8 when the fetus was extremely large for its gestational age; however, when both risk factors were present together, the OR for preterm birth was larger than expected, 10.2 (interaction p<0.0005).ConclusionsAcross all classes, maternal height was significantly associated with child’s gestational age at birth. Interestingly, in short-statured women with large uterine load (twins, LGA), spontaneous delivery occurred much earlier than expected. The interaction between maternal height, uterine load size and gestational age at birth strongly suggests the effect of uterine distention imposed by fetal growth on birth timing.

scholarly journals Do maternal demographics and prenatal history impact the efficacy of betamethasone therapy for threatened preterm labor?

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Mary T. Kinney ◽  
Sara K. Quinney ◽  
Hayley K. Trussell ◽  
Larissa L. Silva ◽  
Sherrine A. Ibrahim ◽  
...  
Keyword(s):  
Preterm Birth ◽  
Gestational Age ◽  
Race And Ethnicity ◽  
Fetal Lung ◽  
Control Analysis ◽  
Lung Maturation ◽  
Maternal Characteristics ◽  
Individualization Of Therapy ◽  
Gestational Age At Birth ◽  
Age At Birth

Abstract Background Betamethasone (BMZ) is used to accelerate fetal lung maturation in women with threatened preterm birth, but its efficacy is variable and limited by the lack of patient individualization in its dosing and administration. To determine sources of variability and potential opportunities for individualization of therapy, the objective of this study was to evaluate maternal factors associated with development of neonatal respiratory distress syndrome (RDS) in a cohort of women who received betamethasone. Methods This study prospectively enrolled women, gestational ages 23–34 weeks, who received betamethasone for threatened preterm birth. Maternal demographics, prenatal history, and neonatal outcomes were abstracted from hospital records. RDS was the primary outcome. Associations between RDS diagnosis and maternal demographics, prenatal history, and betamethasone dosing were evaluated in a case-control analysis and multivariable regression adjusted for gestational age at delivery. Secondary analyses limited the cohort to women who delivered within 1 or 2 weeks of betamethasone dosing. Results Of 209 deliveries, 90 (43 %) resulted in neonatal RDS. Within the overall cohort and controlling for gestational age at birth, RDS was only associated with cesarean births compared to vaginal births (adjusted OR 1.17 [1.06–1.29]). Route of delivery was also the only significant factor related to RDS in the 83 neonates delivered within 7 days of BMZ dosing. However, among 101 deliveries within 14 days of betamethasone dosing and controlling for gestational age at birth, women who experienced preterm premature rupture of membranes (PPROM) had lower RDS rates than those without PPROM (57.9 % vs. 80.2 %, adjusted OR 0.81 [0.67–0.99]). Maternal age, BMI, race, and ethnicity were not associated with RDS in the regression models. Conclusions Of maternal characteristics analyzed, only delivery by cesarean was associated with neonatal RDS after antenatal betamethasone use.

scholarly journals Prediction of preterm birth in nulliparous women using logistic regression and machine learning

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0252025
Author(s):  
Reza Arabi Belaghi ◽  
Joseph Beyene ◽  
Sarah D. McDonald
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Logistic Regression ◽  
Artificial Neural Networks ◽  
Preterm Birth ◽  
First Trimester ◽  
Validation Sample ◽  
Second Trimester ◽  
Nulliparous Women ◽  
Artificial Neural

Objective To predict preterm birth in nulliparous women using logistic regression and machine learning. Design Population-based retrospective cohort. Participants Nulliparous women (N = 112,963) with a singleton gestation who gave birth between 20–42 weeks gestation in Ontario hospitals from April 1, 2012 to March 31, 2014. Methods We used data during the first and second trimesters to build logistic regression and machine learning models in a “training” sample to predict overall and spontaneous preterm birth. We assessed model performance using various measures of accuracy including sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC) in an independent “validation” sample. Results During the first trimester, logistic regression identified 13 variables associated with preterm birth, of which the strongest predictors were diabetes (Type I: adjusted odds ratio (AOR): 4.21; 95% confidence interval (CI): 3.23–5.42; Type II: AOR: 2.68; 95% CI: 2.05–3.46) and abnormal pregnancy-associated plasma protein A concentration (AOR: 2.04; 95% CI: 1.80–2.30). During the first trimester, the maximum AUC was 60% (95% CI: 58–62%) with artificial neural networks in the validation sample. During the second trimester, 17 variables were significantly associated with preterm birth, among which complications during pregnancy had the highest AOR (13.03; 95% CI: 12.21–13.90). During the second trimester, the AUC increased to 65% (95% CI: 63–66%) with artificial neural networks in the validation sample. Including complications during the pregnancy yielded an AUC of 80% (95% CI: 79–81%) with artificial neural networks. All models yielded 94–97% negative predictive values for spontaneous PTB during the first and second trimesters. Conclusion Although artificial neural networks provided slightly higher AUC than logistic regression, prediction of preterm birth in the first trimester remained elusive. However, including data from the second trimester improved prediction to a moderate level by both logistic regression and machine learning approaches.

Sign in / Sign up

Export Citation Format

Share Document