Prediction Of Preterm Birth Research Articles

Prediction of spontaneous preterm birth using supervised machine learning on metabolomic data: A case-cohort study.

To identify and internally validate metabolites predictive of spontaneous preterm birth (sPTB) using multiple machine learning methods and sequential maternal serum samples, and to predict spontaneous early term birth (sETB) using these metabolites. Case-cohort design within a prospective cohort study. Cambridge, UK. A total of 399 Pregnancy Outcome Prediction study participants, including 98 cases of sPTB. An untargeted metabolomic analysis of maternal serum samples at 12, 20, 28 and 36 weeks of gestation was performed. We applied six supervised machine learning methods and a weighted Cox model to measurements at 28 weeks of gestation and sPTB, followed by feature selection. We used logistic regression with elastic net penalty, followed by best subset selection, to reduce the number of predictive metabolites further. We applied coefficients from the chosen models to measurements from different gestational ages to predict sPTB and sETB. sPTB and sETB. We identified 47 metabolites, mostly lipids, as important predictors of sPTB by two or more methods and 22 were identified by three or more methods. The best 4-predictor model had an optimism-corrected area under the receiver operating characteristics curve (AUC) of 0.703 at 28 weeks of gestation. The model also predicted sPTB in 12-week samples (0.606, 95% CI 0.544-0.667) and 20-week samples (0.657, 95% CI 0.597-0.717) and it predicted sETB in 36-week samples (0.727, 95% CI 0.606-0.849). A lysolipid, 1-palmitoleoyl-GPE (16:1)*, was the strongest predictor of sPTB at 12 weeks of gestation (0.609, 95% CI 0.548-0.670), 20 weeks (0.630, 95% CI 0.569-0.690) and 28 weeks (0.660, 95% CI 0.599-0.722), and of sETB at 36 weeks (0.739, 95% CI 0.618-0.860). We identified and internally validated maternal serum metabolites predictive of sPTB. A lysolipid, 1-palmitoleoyl-GPE (16:1)*, is a novel predictor of sPTB and sETB. Further validation in external populations is required.

EG-VEGF maternal levels predict spontaneous preterm birth in the second and third trimesters in pregnant women with risk factors for placenta-mediated complications

Prediction of spontaneous preterm birth in asymptomatic women remains a great challenge for the public health system. The aim of the study was to determine the informational value of EG-VEGF circulating levels for prediction of spontaneous preterm birth in the second and third trimesters in pregnant women at high risk for placenta-mediated complications. A prospective multicenter cohort study including 200 pregnant patients with five-serum sampling per patient. Women with spontaneous preterm birth have higher concentrations of serum EG-VEGF than uncomplicated patients at 24 weeks, 28 weeks and 32 weeks (p = 0.03, 0.02 and < 0.001). The areas under the curve reached 0.9 with 100% sensitivity at 32 weeks for the prediction of spontaneous preterm birth. Serum EG-VEGF concentrations could be considered as a reliable biomarker of spontaneous preterm birth in high-risk for placenta-mediated complications pregnant women.

Establishment of a model for predicting preterm birth based on the machine learning algorithm

BackgroundThe purpose of this study was to construct a preterm birth prediction model based on electronic health records and to provide a reference for preterm birth prediction in the future.MethodsThis was a cross-sectional design. The risk factors for the outcomes of preterm birth were assessed by multifactor logistic regression analysis. In this study, a logical regression model, decision tree, Naive Bayes, support vector machine, and AdaBoost are used to construct the prediction model. Accuracy, recall, precision, F1 value, and receiver operating characteristic curve, were used to evaluate the prediction performance of the model, and the clinical application of the model was verified.ResultsA total of 5411 participants were included and were used for model construction. AdaBoost model has the best prediction ability among the five models. The accuracy of the model for the prediction of “non-preterm birth” was the highest, reaching 100%, and that of “preterm birth” was 72.73%.ConclusionsBy constructing a preterm birth prediction model based on electronic health records, we believe that machine algorithms have great potential for preterm birth identification. However, more relevant studies are needed before its application in the clinic.

Validating staging criteria for sonographic and physical examination for cervical changes at

BackgroundPreterm birth represents a significant clinical challenge, and the ability to predict it effectively is a priority in obstetrics. The cervix undergoes specific changes during pregnancy, and staging these changes may offer a valuable predictive model for preterm birth, particularly in women with a mid-trimester short cervical length. ObjectiveThe study aims to validate a proposed staging model for asymptomatic women with mid-trimester short cervical length and evaluate its potential in predicting preterm birth. The integration of cervical examination and inspection with cervical length measurement was a novel approach to be assessed. Study DesignA multi-center retrospective cohort study included 925 pregnant women with a singleton fetus and a mid-trimester cervical length measurement of 25 mm or less. Cervical conditions were assessed using ultrasound, speculum, and physical examination, and classified according to five cervical staging to correlate with the likelihood of preterm birth. Statistical analyses included Kaplan-Meier Survival Analysis to illustrate the time-to-event characteristics across the five stages, and density plot evaluation to visualize the distribution of gestational ages within the stages. ResultsThe staging model included five stages based on cervical length, appearance, and dilatation. Among the 925 participants, 649 were classified as Stage 1, 245 as Stage 2, 18 as Stage 3, 10 as Stage 4, and 3 as Stage 5. The observed rates of preterm birth before 37 weeks for individuals classified in Stages 1, 2, 3, 4, and 5 were 22.3%, 26.5%, 44.4%, 60%, and 66.7%, respectively (p = 0.005). The overall observed rates of preterm birth before 28, 32, 34, and 37 weeks’ gestation were 5.5%, 9.9%, 12.2%, and 24.1%, respectively (p = 0.005). ConclusionsThis study validates the proposed staging criteria as an effective predictor of preterm birth due to cervical insufficiency. The results demonstrate a significant increase in the preterm birth rate with advancing stage classifications, indicating that the staging effectively stratifies women based on their risk of preterm birth, and highlighting the potential utility for targeted interventions. Implementing these staging criteria can potentially improve the counseling and management of pregnant women at risk for preterm birth.

Exploring Predictors of Preterm Birth: A Comparative Study of Turkish and Syrian Refugee Women.

This study is designed to explore associated sociodemographic, birth-related and household characteristics with preterm birth (< 37 weeks) among Turkish and Syrian refugee women. The data utilized in this study were obtained from the Turkey Demographic and Health Survey (TDHS) conducted in 2018. Various statistical analyses, including descriptive statistics, independent sample t-tests, and Chi-square tests, were employed to examine the differences in study variables between Turkish and Syrian refugee women. Furthermore, logistic regression analysis was conducted to identify the associated factors with preterm birth among Turkish and Syrian refugee women, allowing for comparative analysis. The key findings of this study revealed significant differences in sociodemographic (p < 0.05), birth-related (p < 0.05), and household characteristics (p < 0.05) that are associated with preterm birth among Turkish and Syrian refugee women. Also, nationality (OR: 3.427; 95% CI 2.770-4.241), delivery by c-section (OR: 1.630; 95% CI 1.370-1.939), educational status (OR: 0.674; 95% CI 0.547-0.832), place of delivery (OR: 0.806; 95% CI 0.666-0.975), and number of household members (OR: 1.206; 95% CI 1.013-1.437) were found to be important factors associated with preterm birth risk. The key findings of this study contribute to the identification of women's factors in preterm birth. By understanding the factors that contribute to preterm birth among both Syrian refugee and Turkish women, appropriate interventions can be developed to improve maternal and child health outcomes.

Assessment of cervical softening and the prediction of preterm birth (STIPP): protocol for a prospective cohort study

IntroductionPreterm birth (PTB) is among the leading causes of perinatal and childhood morbidity and mortality. Therefore, accurate identification of pregnant women at high risk of PTB is key to enable...

Uterocervical angle and cervical length as predictors for preterm birth in low-risk women

Uterocervical angle and cervical length as predictors for preterm birth in low-risk women

Vitamin D Status as an Important Predictor of Preterm Birth in a Cohort of Black Women.

Vitamin D deficiency (25 (OH)D < 20 ng/mL) is a modifiable risk factor that has been associated with an increased risk of preterm birth (PTB) (<37 weeks gestation). Black women are at a high risk for vitamin D deficiency due to higher melanin levels. Vitamin D sufficiency may be protective against PTB risk in Black women. Black participants between 8 and 25 weeks of gestation were included in this nested case-control study. The sample consisted of women who had either PTBs (n = 57) or term births, were selected based on maternal age compared to those who had PTBs (n = 118), and had blood samples available between 8 and 25 weeks of gestation. The women completed questionnaires about depressive symptoms and smoking behavior and had blood collected to determine their vitamin D levels. Gestational age at birth, hypertensive disorders, and body mass index (BMI) were collected from the medical records. The odds of PTB were increased by 3.34 times for participants with vitamin D deficiency after adjusting for hypertensive disorders of pregnancy and depressive symptoms. Vitamin D assessment and supplementation may be an important intervention for preventing PTB in pregnant Black women.

Role of Uterocervical Angle, Cervical Length, and Cervicovaginal Fetal Fibronectin in the Prediction of Preterm Birth

BACKGROUND:Cervical length measurement and fetal fibronectin (FFN) are widely used to estimate the risk of preterm birth. Another potential predictor of preterm birth is the uterocervical angle, and this additional measurement may improve the risk assessment. This study aimed to predict the onset of labor in women who present with preterm labor through cervical length, uterocervical angle, and FFN.METHODS:A prospective cohort study was carried out on 90 symptomatic women at high risk of preterm labor attending the Gynecology and Obstetrics department at Fayoum University Hospital. FFN in the cervicovaginal fluid was assessed by ELISA technique. The uterocervical angle and cervical length were measured by transvaginal ultrasound. Maternal history and pregnancy data were recorded. Delivery data were subsequently collected.RESULTS:The average age was 21.79 ± 3.3 years, and the average body mass index (BMI) was 24.6 ± 5.8 kg/m2. The mean gestational age (GA) was 32.83 ± 2.3 weeks. Twelve women in our cohort reported previous preterm labor. The cervical length and FFN showed better sensitivity and specificity compared with the uterocervical angle in predicting preterm birth. Logistic regression analysis demonstrated that preterm birth depended only on the cervical length and quantitative FFN.CONCLUSION:The combination of FFN and cervical length could improve preterm birth prediction accuracy.

Neutrophil Elastase as a Predictor of Delivery in Pregnant Women with Preterm Labour.

No previous study has been conducted in Nigeria on the role of neutrophil elastase in predicting preterm birth. The present study aimed to determine the role of the neutrophil elastase test in predicting birth in women with preterm labor. The present prospective cohort study recruited 83 pregnant women with preterm labor between 28 and 36+6 weeks of gestation, and followed up these subjects for 14 days. The controls comprised 85 pregnant women without preterm labor. The cervicovaginal fluid was collected and tested using the neutrophil elastase test. Then, the sensitivity, specificity, and positive and negative predictive parameters were determined. Afterward, the data were scrutinized using the SPSS arithmetic software (Sort23). Among the 168 pregnant women analyzed in the present study, 83 pregnant women were assigned to the preterm labor group, and 85 pregnant women were assigned to the control group. Furthermore, among the 83 pregnant women in the preterm labor group, 11 women had spontaneous preterm delivery, leading to a spontaneous preterm birth proportion of 13.3%. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the neutrophil elastase test within 14 days post-enrollment were 93.8%, 61.2%, 36.6%, 97.6%, and 67.5%, respectively, for the general population, and 87.5%, 66.7%, 35.0%, 96.3%, and 70.2%, respectively, for subjects at <35 weeks of gestation. The positive and negative likelihood ratios for preterm birth prediction were 2.62 and 0.19, respectively. The neutrophil elastase test exhibited high predictive accuracy in pregnant women with preterm labor, when compared to the controls, based on the sensitivity and negative predictive value, but this had poor positive predictive values. The neutrophil elastase test may be used as a screening test, but not as a potential predictive test, in the routine clinical setting.

Primary prevention with vaginal chlorhexidine before 16 weeks reduces the incidence of preterm birth: results of the Preterm Labor Prevention Using Vaginal Antiseptics study

Preterm labor is one of the leading causes of perinatal death and is currently considered a syndrome with many causes. One of the most important causes of preterm birth is ascending infection from bacterial vaginosis. Chlorhexidine has proven to be effective against bacterial vaginosis and against bacterial biofilms without affecting gestation. We aimed to evaluate the effectiveness of a universal primary prevention strategy for preterm birth using intravaginal chlorhexidine applied before 16 weeks (Preterm Labor Prevention Using Vaginal Antiseptics study). We performed a prospective observational study with 2 cohorts of pregnant women that were assigned either to prevention of preterm birth by means of intravaginal chlorhexidine (Cum Laude Chlorhexidine, chlorhexidine digluconate 0.2%) before 16 weeks (n=413), or to no treatment following the usual hospital protocol (n=704). Primary outcomes were the incidence of spontaneous preterm birth before 34 and 37 weeks; the incidence of preterm birth before 34 and 37 weeks, including inductions for premature rupture of membranes; and the incidence of preterm birth before 34 and 37 weeks, including any indication for termination of pregnancy. Both cohorts were compared using Mann-Whitney and Fisher tests. Finally, a multivariable analysis, including the odds ratio was performed, adjusting for clinical parameters, to evaluate the importance of the different determinants in the prediction of preterm birth. In pregnancies treated with chlorhexidine, the incidences of spontaneous preterm birth; preterm birth, including induction for premature rupture of membranas; and preterm birth, including any indication for termination of pregnancy were at 34 and 37 weeks: 0% and 0%, 0.24% and 1.69, and 2.90% and 3.15%, respectively; whereas in nontreated pregnancies, these incidences were 9% and 11%, 12% and 23%, and 35% and 43%, respectively. According to the multivariable analysis, the incidence of preterm birth among women treated with chlorhexidine before 16 weeks was halved (Odds ratio, 0.52; P<.05). Universal treatment with vaginal chlorhexidine before 16 weeks reduces the incidence of preterm birth, especially before 34 weeks.

Ultrasonographic cervical length screening at 20-24 weeks of gestation in twin pregnancies for prediction of spontaneous preterm birth: A 10-year Taiwanese cohort.

Shortened cervical length is one of the primary predictors for spontaneous preterm deliveries in twin pregnancies. However, there is lack of consensus regarding cut-off values. Recent evidence highlights that established cut-offs for cervical length screening might not always apply across different populations. This study aims to present the distribution of cervical length in Taiwanese twin pregnancies and to assess its predictive value for spontaneous preterm birth during mid-trimester screening. This retrospective analysis of cervical length screening in Taiwan evaluated 469 twin pregnancies between 20-24 weeks of gestation. Outcome data were obtained directly from the medical records of the delivery hospital. The study explored the predictive value of cervical length screening for spontaneous preterm birth and the characteristics of cervical length distribution in Taiwanese twin pregnancies. The average gestational age at screening was 22.7 weeks. Cervical length values displayed a non-normal distribution (p-value <0.001). The median, 5th and 95th centiles were 37.5 mm 25.1 mm, and 47.9 mm, respectively. Various cut-off values were assessed using different methods, yielding positive [negative] likelihood ratios for spontaneous preterm births between 32-37 weeks of gestational age (GA) (1.3-30.1 and [0.51-0.92]) and for very preterm births between 28-32 weeks GA (5.6-51.1 and [0.45-0.64]). The findings from our analysis of Taiwanese twin pregnancies uphold the moderate predictive potential of cervical length screening, consistent with prior investigations. The presented likelihood ratios for predicting preterm birth at different gestational ages equip clinicians with valuable tools to enhance their diagnostic rationale and resource utilization. By fine-tuning screening parameters according to the spontaneous preterm birth prevalence and clinical priorities of the particular population, healthcare providers can enhance patient care. Our data implies that a cervical length below 20 mm might provide an optimal balance between minimizing false negatives and managing false positives when predicting spontaneous preterm birth.

FRI406 Maternal Biomarkers Of Adiposity And Stress For Preterm Birth

Abstract Disclosure: G. Mayne: None. P.E. DeWitt: None. J. Wen: None. U. Christians: None. D. Dabelea: None. J. Schulkin: None. K. Hurt: None. Background: Adiponectin is a potent uterine tocolytic and decreases with gestational age, so it could be a maternal metabolic quiescence factor during pregnancy. Maternal stress can influence risk for preterm birth, and adiponectin may be inversely related to cortisol. Therefore, we characterized a potential mechanistic link between preterm birth, adiponectin, and cortisol. In this pilot study, we hypothesized maternal plasma adiponectin and cortisol concentrations are inversely related and that lower adiponectin and higher cortisol associate with spontaneous preterm birth. Methods: We performed a nested case-control study using biobank morning fasting plasma samples, taken twice in pregnancy for the Healthy Start pre-birth cohort. We included low-risk women with singleton pregnancies and excluded mothers with major medical illness, preeclampsia, chronic hypertension, or prior preterm birth. We matched preterm cases with term controls (1:3) by gestational age at first blood sample and least variation in time between blood samples (16 preterm, 46 term). We quantified high (HMW), low molecular weight (LMW), and total adiponectin using an ELISA assay. We also quantified cortisol and five related steroid hormones from the same specimens using HPLC/mass spectrometry. We used generalized estimating equations and additive models to compare group means and associations between adiponectin and cortisol. We used machine learning with gradient boosting for predictive modeling. Results: Contrary to our hypothesis, total, HMW, and LMW adiponectin positively associated with cortisol across gestation (P&amp;lt;0.001 for all), however the association was reduced in the preterm compared with term group and significantly so for LMW (P=0.044). In predictive modelling, HMW adiponectin, maternal pre-pregnancy BMI, maternal age, and cortisol were the four most highly relevant predictors for preterm birth (AUROC=0.704). Conclusion: In healthy low-risk patients, we found associations between adiponectin and cortisol differ across gestation for pregnancies ending with term or preterm delivery and have some predictive value in this cohort. This suggests a possible mechanistic link between maternal metabolism and stress for pregnancy maintenance. These biomarkers may prove useful as predictors in larger studies and might indicate possible maternal metabolic therapies for preterm birth prevention. Presentation: Friday, June 16, 2023

An open dataset with electrohysterogram records of pregnancies ending in induced and cesarean section delivery

The existing non-invasive automated preterm birth prediction methods rely on the use of uterine electrohysterogram (EHG) records coming from spontaneous preterm and term deliveries, and are indifferent to term induced and cesarean section deliveries. In order to enhance current publicly available pool of term EHG records, we developed a new EHG dataset, Induced Cesarean EHG DataSet (ICEHG DS), containing 126 30-minute EHG records, recorded early (23rd week), and/or later (31st week) during pregnancy, of those pregnancies that were expected to end in spontaneous term delivery, but ended in induced or cesarean section delivery. The records were collected at the University Medical Center Ljubljana, Ljubljana, Slovenia. The dataset includes 38 and 43, early and later, induced; 11 and 8, early and later, cesarean; and 13 and 13, early and later, induced and cesarean EHG records. This dataset enables better understanding of the underlying physiological mechanisms involved during pregnancies ending in induced and cesarean deliveries, and provides a robust and more realistic assessment of the performance of automated preterm birth prediction methods.

Predicting the Risk of Preterm Birth Throughout Pregnancy Based on a Novel Transcriptomic Signature

Abstract Objective This study focused on the prediction of preterm birth (PTB). It aimed to identify the transcriptomic signature essential for the occurrence of PTB and evaluate its predictive value in early, mid, and late pregnancy and in women with threatened preterm labor (TPTL). Methods Blood transcriptome data of pregnant women were obtained from the Gene Expression Omnibus database. The activity of biological signatures was assessed using gene set enrichment analysis and single-sample gene set enrichment analysis. The correlation among molecules in the interleukin 6 (IL6) signature and between IL6 signaling activity and the gestational week of delivery and latent period were evaluated by Pearson correlation analysis. The effects of molecules associated with the IL6 signature were fitted using logistic regression analysis; the predictive value of both the IL6 signature and IL6 alone were evaluated using receiver operating characteristic curves and pregnancy maintenance probability was assessed using Kaplan-Meier analysis. Differential analysis was performed using the DEseq2 and limma algorithms. Results Circulatory IL6 signaling activity increased significantly in cases with preterm labor than in those with term pregnancies (normalized enrichment score (NES) = 1.857, P = 0.001). The IL6 signature (on which IL6 signaling is based) was subsequently considered as the candidate biomarker for PTB. The area under the curve (AUC) values for PTB prediction (using the IL6 signature) in early, mid, and late pregnancy were 0.810, 0.695, and 0.779, respectively; these values were considerably higher than those for IL6 alone. In addition, the pregnancy curves of women with abnormal IL6 signature differed significantly from those with normal signature. In pregnant women who eventually had preterm deliveries, circulatory IL6 signaling activity was lower in early pregnancy (NES = −1.420, P = 0.031) and higher than normal in mid (NES = 1.671, P = 0.002) and late pregnancy (NES = 2.350, P &lt; 0.001). In women with TPTL, the AUC values for PTB prediction (or PTB within 7 days and 48 hours) using the IL6 signature were 0.761, 0.829, and 0.836, respectively; the up-regulation of IL6 signaling activity and its correlation with the gestational week of delivery (r = −0.260, P = 0.001) and latency period (r = −0.203, P = 0.012) were more significant than in other women. Conclusion Our findings suggest that the IL6 signature may predict PTB, even in early pregnancy (although the predictive power is relatively weak in mid pregnancy) and is particularly effective in symptomatic women. These findings may contribute to the development of an effective predictive and monitoring system for PTB, thereby reducing maternal and fetal risk.

Using the Delphi Technique to Achieve Consensus on Prevention and Treatment of Preterm Single Birth in China

Abstract Objective This study aimed to reach a consensus among obstetric experts on the prevention and treatment of preterm single births in China. Methods Based on the scoping literature review and the 2014 edition of preterm birth of Clinical Diagnosis and Treatment guidelines, we generated the Delphi survey statements with five evaluation dimensions, including the definition of preterm birth, exclusion of risk factors for preterm birth, prevention, and prediction of preterm birth, treatment of preterm birth, and evaluation of intervention outcomes of preterm birth. Obstetric experts from the Obstetrics and Gynecology Branch of the Chinese Medical Association formed the expert group for this survey. All the obstetric experts participated two-round modified Delphi survey via an anonymous online survey and an online panel. Mean scores, rank sum, full score ratio, and the lowest score ratio were calculated to reflect the concentration of expert opinions. The coefficient of variation and Kendall W coefficient were used to reflect the expert opinion coordination degree of the survey statement. Results The expert response rate for both rounds of surveys was 100% (41/41). Experts reached an agreement on 36 statements in five dimensions of preterm birth prevention and treatment in the first round of the survey and reached a consensus on the remaining 13 statements in the second round. A total of 49 statements (mean scores ≥3, full score ratio ≥20%, coefficient of variation ≤0.3) were explicitly included in this guideline to form recommendations, while the remaining three clinical issues that did not reach a consensus require further determination based on evidence quality. The Kendall W coefficient in the two rounds of the Delphi survey were 0.20 (P &lt; 0.001) and 0.29 (P &lt; 0.001). Conclusion The five dimensions and 49 statements, agreed upon through a two-round Delphi study, determined the recommended statements to be included in the updated guidelines for the prevention and treatment of preterm birth in China. The defined lower limit is set at ≥28 gestational weeks; however, an update has been made to the definition of premature birth, specifying that “with the consent of the mother and her family, treatment is not abandoned for viable infants ≥26 gestational weeks.”

EP19.22: Prediction of spontaneous preterm birth using maternal history, PAPP‐A and cervical length at 11–13 weeks in a South Asian Population

EP19.22: Prediction of spontaneous preterm birth using maternal history, PAPP‐A and cervical length at 11–13 weeks in a South Asian Population

EP15.15: Prediction of preterm birth for growth‐restricted infants using PlGF levels and sFlt‐1/PlGF ratio

EP15.15: Prediction of preterm birth for growth‐restricted infants using PlGF levels and sFlt‐1/PlGF ratio

EP13.06: Prediction of preterm birth for growth‐restricted infants using PlGF, sFlt‐1/PlGF ratio and umbilical artery pulsatility index in combination

EP13.06: Prediction of preterm birth for growth‐restricted infants using PlGF, sFlt‐1/PlGF ratio and umbilical artery pulsatility index in combination

EP19.09: Changes in sFlt‐1/PlGF ratio over gestation is a good predictor of preterm birth regardless of infant size

EP19.09: Changes in sFlt‐1/PlGF ratio over gestation is a good predictor of preterm birth regardless of infant size