Predictive model for risk of cesarean section in pregnant women after induction of labor

Ensemble learning for fetal ultrasound and maternal-fetal data to predict mode of delivery after labor induction

Providing adequate counseling on mode of delivery after induction of labor (IOL) is of utmost importance. Various AI algorithms have been developed for this purpose, but rely on maternal-fetal data, not including ultrasound (US) imaging. We used retrospectively collected clinical data from 808 subjects submitted to IOL, totaling 2024 US images, to train AI models to predict vaginal delivery (VD) and cesarean section (CS) outcomes after IOL. The best overall model used only clinical data (F1-score: 0.736; positive predictive value (PPV): 0.734). The imaging models employed fetal head, abdomen and femur US images, showing limited discriminative results. The best model used femur images (F1-score: 0.594; PPV: 0.580). Consequently, we constructed ensemble models to test whether US imaging could enhance the clinical data model. The best ensemble model included clinical data and US femur images (F1-score: 0.689; PPV: 0.693), presenting a false positive and false negative interesting trade-off. The model accurately predicted CS on 4 additional cases, despite misclassifying 20 additional VD, resulting in a 6.0% decrease in average accuracy compared to the clinical data model. Hence, integrating US imaging into the latter model can be a new development in assisting mode of delivery counseling.

Retrospective evaluation of labor induction with scar uterus at the university hospital of Rennes

OBJECTIVE

The aim of the study was a retrospective evaluation of labor induction in women with one previous cesarean section. The primary outcome was the mode of delivery. We also studied the severe maternal and neonatal morbidity and identify some prediction factors of vaginal delivery after labor induction after one previous cesarean section.

STUDY DESIGN

This was a retrospective observational monocentric study performed over the period from January 1st, 2016 to April 30th, 2020 at the university hospital of Rennes. Were included women with scar uterus because of one previous cesarean section with a viable singleton fetus in cephalic presentation and an induction of labor for medical reason, at term. Multivariate logistic regression analysis was used to analyze prediction of vaginal delivery after labor induction after one previous cesarean section. We also studied maternal (included uterine rupture, loss of blood, obstetrical injury of anus sphincter) and neonatal (APGAR score, arterial umbilical pH after 1 minute of life and eventual admission to neonatal unit) morbidity. We used a stepwise multivariate logistic regression model to select variables for multivariate analysis. The model with the lowest Akaike Index Criteria was chosen.

RESULTS

The study enrolled 353 women with scar uterus: 121 women were induced by balloon catheter, 57 by osmotic cervical dilatators, 91 by oxytocin alone, 84 by amniotomy. Vaginal delivery rate was 47,9%. There was 45% of vaginal delivery in the group with Bishop < 6 before induction of labor versus 62% in the group with Bishop ≥ 6. There was no statistically significative difference in neonatal and maternal severe morbidities between vaginal delivery and cesarean section: 4,5% of severe maternal morbidities (n = 16). Among their, we highlighted 7 uterine ruptures (3,8%). We observed also 3% of postpartum severe hemorrhage in vaginal delivery group (n = 5) against 1,6% in cesarian section group (n = 3) with no statistical significant difference (p = 0,632). Regarding to the obstetric perineal tears and lacerations we noticed 1,2% of OASIS 3 (n = 2) and 0,6% of OASIS 4 (n = 1). Severe neonatal morbidities were comparable by mode of delivery without significant difference: APGAR score at 5 min was similar (p = 1), as well as arterial umbilical pH after 1 min. (p = 0.719) and admissions to a neonatal unit (p = 1). Two variables were statistically associated with vaginal delivery after labor induction in women with scar uterus: Bishop score ≥ 6 (OR = 0,44; 95%CI: 0,25-0,81) and/or previous vaginal delivery after cesarean section (OR = 0,17; 95%CI: 0,08-0,35).

CONCLUSION

With 47,9% of vaginal delivery after labor induction in women with scar uterus, only 3.8% (n = 7/353) of uterine ruptures, less than 1% APGAR < 7 at 5 min (n = 3/353), induction on scar uterus should be consider in obstetrical practice. Bishop score ≥ 6 and/or previous vaginal delivery after cesarean section are associated to vaginal delivery after labor induction.

Prediction of successful labor induction in persons with a low Bishop score using machine learning: Secondary analysis of two randomized controlled trials

BACKGROUND

The objective of this paper was to identify predictors of a vaginal birth in individuals with singleton pregnancies and a Bishop Score <4, following Induction of Labor (IoL) using dinoprostone vaginal insert (DVI). Secondarily, we sought to understand the association between oxytocin use for labor augmentation and IoL outcomes.

METHODS

We developed and internally validated a multivariate prediction model using machine learning (ML) applied to data from two Phase-III randomized controlled double-blind trials (NCT01127581, NCT00308711). The model was internally validated using 10-fold cross-validation.

RESULTS

This study included 1107 participants. Despite unfavorable cervical status and inclusion of high-risk pregnancies, 72% of participants had vaginal births. The model's area under receiver operating characteristic curve was 0.73. The following factors increased the chance of vaginal birth: being parous; being between 37 and 41 weeks of gestation; having a lower Body Mass Index; having a lower maternal age; having fewer maternal comorbidities; and having a higher Bishop score. Parity alone correctly predicted the outcome in ~50% of cases, at a ~10% false-negative rate. Participants whose labors progressed without requiring oxytocin had a higher probability of vaginal birth than those requiring oxytocin for either induction or augmentation (81% vs 70% vs 77%, respectively).

DISCUSSION

Even in high-risk pregnancies and with low Bishop scores, the use of DVI results in a high chance of vaginal birth. Parity is a critical predictor of success. The judicious use of oxytocin for labor induction or augmentation can increase the chance of vaginal birth. Our study validates the use of ML and predictive modeling for treatment response prediction when considering IoL.

The influence of blood donation before pregnancy on neonatal birth weight

Objective

To evaluate the effect of blood donation before pregnancy on neonatal birth weight.

Methods

A total of 14996 women with singleton pregnancies at full-term in Ningbo Medical Center Lihuili Hospital and Ningbo Women’s and Children’s Hospital from November 2019 to November 2020 were enrolled in this study. Detailed records of whole blood donation before pregnancy were obtained through Alipay software. The records were classified into three groups: nondonors, low-frequency donors and high-frequency donors according to the total numbers of blood donations in the 3-year period before pregnancy. The demographics and clinical information of the enrolled participants and their fetuses were collected from electronic medical records (EMRs). The effect of blood donations in the 3-year period before pregnancy on neonatal birth weight was analyzed.

Results

There was no significant difference in neonatal birth weight among the three groups (P = 0.373). In line with this, there was no association between the number of blood donations in the 3-year period before pregnancy and neonatal birth weight (β = 14.5; 95% confidence interval [CI]: -3.9, 31.4; P = 0.094) in the bootstrapped multivariate linear regression analysis models, adjusted for maternal age, number of pregnancies, number of deliveries, gestational age, mode of delivery, years of education and blood type in pregnant women. Compared to the nondonors, the risk of fetal macrosomia was higher in both low-frequency donors and all donors (OR: 1.539, 95% CI: 1.058, 2.134, P = 0.016; OR: 1.454, 95% CI: 1.033, 1.952, P = 0.021, respectively), in the bootstrapped binary logistic regression analysis models after adjusting for the variables mentioned above.

Conclusion

Our study showed that maternal blood donation in the 3-year period before pregnancy may not lead to a reduction in neonatal birth weight, but may be associated with the incidence of fetal macrosomia.

Nomogram predicting cesarean delivery undergoing induction of labor among high-risk nulliparous women at term: a retrospective study

Background

Our aim was to create and validate a nomogram predicting cesarean delivery after induction of labor among nulliparous women at term.

Methods

Data were obtained from medical records from Nanjing Drum Tower Hospital. Nulliparous women with singleton pregnancies undergoing induction of labor at term were involved. A total of 2950 patients from Jan. 2014 to Dec. 2015 were served as derivation cohort. A nomogram was constructed by multivariate logistic regression using maternal, fetal and pregnancy characteristics. The predictive accuracy and discriminative ability of the nomogram were internal validated by 1000-bootstrap resampling, followed by external validation of a new dataset from Jan. 2016 to Dec. 2016.

Results

Logistic regression revealed nine predictors of cesarean delivery, including maternal height, age, uterine height, abdominal circumference, estimated fetal weight, indications for induction of labor, initial cervical consistency, cervical effacement and station. Nomogram was well calibrated and had an AUC of 0.73 (95% confidence interval [CI], 0.70-0.75) after bootstrap resampling for internal validation. The AUC in external validation reached 0.67, which was significantly higher than that of three models published previously (P<0.05).

Conclusions

This validated nomogram, constructed by variables that were obtained form medical records, can help estimate risk of cesarean delivery before induction of labor.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12884-022-04386-8.

Application of pelvic floor ultrasound during pregnancy to detect patients at risk of cesarean section due to failure of labor progression in a Spanish population

OBJECTIVE

Our study is aimed at evaluating the characteristics of the pelvic floor, assessed through transperineal ultrasound, since it may influence or increase the possibility of having a cesarean delivery, with the objective of acting on those variables that can be modified during pregnancy.

STUDY DESIGN

Transperineal ultrasound was performed on 109 primiparous pregnant women in their first trimester of pregnancy, recruited between May 2018 and February 2019, with the purpose of studying the hiatus area at rest, retention and Valsalva. We have reassessed them at the end of pregnancy and delivery data were recorded. We selected 8 patients as case-study, who had cesarean section delivery due to failure of labor progression. We selected 4 control-cases for each, reaching the total of 32 controls, with similar age and body mass index, to avoid obtaining a biased result from these data.

RESULTS

In the study of hiatal areas, patients who delivered by cesarean section had a smaller hiatal area at rest, during levator ani muscle contraction and during Valsalva maneuver, at all visits. In early pregnancy, the range of the resting hiatal area was 13.8 ± 2.0 cm² for cesarean sections, compared to 16.2 ± 2.7 cm² for vaginal deliveries with an OR of 0.57 (0.34-0.95, 95% CI). For hiatal area on Valsalva, the OR was 0.55 (0.35-0.88, 95% CI). Therefore, the smaller the hiatal area, the greater the possibility of cesarean section. At the end of pregnancy, between 34 and 36 weeks of gestation, the OR of hiatal area on Valsalva was 0.78 (0.60-1.00, 95% CI).

CONCLUSION

The hiatus area measured by transperineal ultrasonography at the beginning and at the end of the pregnancy may be useful to identify the patients who are at a higher risk of cesarean delivery due to failure of labor progression.

Risk of caesarean delivery in labour induction: a systematic review and external validation of predictive models

BACKGROUND

Despite the existence of numerous published models predicting the risk of caesarean delivery in women undergoing induction of labour (IOL), validated models are scarce.

OBJECTIVES

To systematically review and externally assess the predictive capacity of caesarean delivery risk models in women undergoing IOL.

SEARCH STRATEGY

Studies published up to 15 January 2021 were identified through PubMed, CINAHL, Scopus and ClinicalTrials.gov, without temporal or language restrictions.

SELECTION CRITERIA

Studies describing the derivation of new models for predicting the risk of caesarean delivery in labour induction.

DATA COLLECTION AND ANALYSIS

Three authors independently screened the articles and assessed the risk of bias (ROB) according to the prediction model risk of bias assessment tool (PROBAST). External validation was performed in a prospective cohort of 468 pregnancies undergoing IOL from February 2019 to August 2020. The predictive capacity of the models was assessed by creating areas under the receiver operating characteristic curve (AUCs), calibration plots and decision curve analysis (DCA).

MAIN RESULTS

Fifteen studies met the eligibility criteria; 12 predictive models were validated. The quality of most of the included studies was not adequate. The AUC of the models varied from 0.520 to 0.773. The three models with the best discriminative capacity were those of Levine et al. (AUC 0.773, 95% CI 0.720-0.827), Hernández et al. (AUC 0.762, 95% CI 0.715-0.809) and Rossi et al. (AUC 0.752, 95% CI 0.707-0.797).

CONCLUSIONS

Predictive capacity and methodological quality were limited; therefore, we cannot currently recommend the use of any of the models for decision making in clinical practice.

TWEETABLE ABSTRACT

Predictive models that predict the risk of cesarean section in labor inductions are currently not applicable.

Can ultrasound on admission in active labor predict labor duration and a spontaneous delivery?

BACKGROUND

Identifying predictive factors for a normal outcome at admission in the labor ward would be of value for planning labor care, timing interventions, and preventing labor dystocia. Clinical assessments of fetal head station and position at the start of labor have some predictive value, but the value of ultrasound methods for this purpose has not been investigated. Studies using transperineal ultrasound before labor onset show possibilities of using these methods to predict outcomes.

OBJECTIVE

This study aimed to investigate whether ultrasound measurements during the first examination in the active phase of labor were associated with the duration of labor phases and the need for operative delivery.

STUDY DESIGN

This was a secondary analysis of a prospective cohort study at Landspitali University Hospital, Reykjavík, Iceland. Nulliparous women at ≥37 weeks' gestation with a single fetus in cephalic presentation and in active spontaneous labor were eligible for the study. The recruitment period was from January 2016 to April 2018. Women were examined by a midwife on admission and included in the study if they were in active labor, which was defined as regular contractions with a fully effaced cervix, dilatation of ≥4 cm. An ultrasound examination was performed by a separate examiner within 15 minutes; both examiners were blinded to the other's results. Transabdominal and transperineal ultrasound examinations were used to assess fetal head position, cervical dilatation, and fetal head station, expressed as head-perineum distance and angle of progression. Duration of labor was estimated as the hazard ratio for spontaneous delivery using Kaplan-Meier curves and Cox regression analysis. The hazard ratios were adjusted for maternal age and body mass index. The associations between study parameters and mode of delivery were evaluated using receiver operating characteristic curves.

RESULTS

Median times to spontaneous delivery were 490 minutes for a head-perineum distance of ≤45 mm and 682 minutes for a head-perineum distance of >45 mm (log-rank test, P=.009; adjusted hazard ratio for a shorter head-perineum distance, 1.47 [95% confidence interval, 0.83-2.60]). The median durations were 506 minutes for an angle of progression of ≥93° and 732 minutes for an angle of progression of <93° (log-rank test, P=.008; adjusted hazard ratio, 2.07 [95% confidence interval, 1.15-3.72]). The median times to delivery were 506 minutes for nonocciput posterior positions and 677 minutes for occiput posterior positions (log-rank test, P=.07; adjusted hazard ratio, 1.52 [95% confidence interval, 0.96-2.38]) Median times to delivery were 429 minutes for a dilatation of ≥6 cm and 704 minutes for a dilatation of 4 to 5 cm (log-rank test, P=.002; adjusted hazard ratio, 3.11 [95% confidence interval, 1.68-5.77]). Overall, there were 75 spontaneous deliveries; among those deliveries, 16 were instrumental vaginal deliveries (1 forceps delivery and 15 ventouse deliveries), and 8 were cesarean deliveries. Head-perineum distance and angle of progression were associated with a spontaneous delivery with area under the receiver operating characteristic curves of 0.68 (95% confidence interval, 0.55-0.80) and 0.67 (95% confidence interval, 0.55-0.80), respectively. Ultrasound measurement of cervical dilatation or position at inclusion was not significantly associated with spontaneous delivery.

CONCLUSION

Ultrasound examinations showed that fetal head station and cervical dilatation were associated with the duration of labor; however, measurements of fetal head station were the variables best associated with operative deliveries.

Cesarean Delivery and Gender of Delivering Physicians: A Systematic Review and Meta-analysis

OBJECTIVE

To assess the association of the gender of the delivering physician and the odds of performing cesarean delivery.

DATA SOURCES

CINAHL, ClinicalTrials.gov, Cochrane Library, PubMed, Scopus and Web of Science from the first year of records through May 2020.

METHODS OF STUDY SELECTION

We included studies that reported odds ratios (OR), or data allowing the calculation of ORs, for cesarean delivery performed by female and male delivering physicians. We also included studies that reported the preference of physicians for performing cesarean deliveries.

TABULATION, INTEGRATION, AND RESULTS

Independent data extraction was carried out by at least two researchers. Standard inverse-variance random effects meta-analysis was used to generate overall ORs. Finally, in two separate meta-analyses, we analyzed 15 studies containing clinical data for 1,269,625 births, and 11 studies containing data for the preference for delivery mode of 4,911 obstetricians. Both the crude and adjusted odds of a cesarean delivery were lower for those performed by female physicians (crude OR 0.75, 95% CI 0.68-0.84, τ=0.029, adjusted OR 0.74, 95% CI 0.65-0.85, τ=0.031). We also found that female physicians had a lower preference for cesarean delivery in both crude and adjusted analysis (crude OR 0.59, 95% CI 0.36-0.96, I=77%, adjusted OR 0.58, 95% CI 0.40-0.84, I=67%).

CONCLUSION

Female physicians are less likely to perform cesarean delivery and less likely to prefer it. This was observed across different health systems and populations.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO, CRD42020158442.

Development and Validation of a Risk Prediction Model for Cesarean Delivery After Labor Induction

Objective: The goal of the study was to develop and validate a prediction model for cesarean delivery after labor induction that included factors known before the start of induction, unlike prior studies that focused on characteristics at the time of induction. Materials and Methods: Using 17,370 term labor inductions without documented medical indications occurring at 14 U.S. hospitals, 2007-2012, we created and evaluated a model predicting cesarean delivery. We assessed model calibration and discrimination, and we used bootstrapping for internal validation. We externally validated the model by using 2122 labor inductions from a hospital not included in the development cohort. Results: The model contained eight variables-gestational age, maternal race, parity, maternal age, obesity, fibroids, excessive fetal growth, and history of herpes-and was well calibrated with good risk stratification at the extremes of predicted probability. The model had an area under the curve (AUC) for the receiver operating characteristic curve of 0.82 (95% confidence interval 0.81-0.83), and it performed well on internal validation. The AUC in the external validation cohort was 0.82. Conclusion: This prediction model can help providers estimate a woman's risk of cesarean delivery when planning a labor induction.

Prediction models for determining the success of labor induction: A systematic review

INTRODUCTION

The purpose of this study was to systematically identify and compare clinical models using universally accessible clinical and demographic factors that were derived and/or validated to predict the success of labor induction with a view to making recommendations for practice.

MATERIAL AND METHODS

MEDLINE, Embase, www.clinicaltrials.gov, and PubMed (for non-MEDLINE and studies in-progress) were searched from inception to November 2017. Only studies that derived and/or validated clinical prediction models using variables obtained through antenatal history and digital cervical examination were included. Two reviewers independently screened titles and abstracts and extracted data from eligible studies into a standardized form. Extracted data included: participant characteristics, sample size, variables considered and included, endpoint definitions, study design and model performance. The Prediction Study Risk of Bias Assessment Tool (PROBAST) was used to appraise included studies. In view of clinical and methodologic heterogeneity between studies, only descriptive analysis was possible. The protocol was registered with the PROSPERO International prospective register of systematic reviews [CRD42017081548].

RESULTS

The search identified 16 studies describing 14 prediction models derived between 1966 and 2018. Models varied and demonstrated major limitations with regard to methodology, scope and performance. Of the derived models, six were internally validated and three were externally validated. Performance was most commonly measured using the area under the receiver operator characteristic curve, which ranged from 0.68 to 0.79, 0.67 to 0.77 and 0.61 to 0.73 for derived, internally validated and externally validated models, respectively. The risk-of-bias of included studies ranged from some studies fulfilling only 36% and some others fulfilling 86% of eligible PROBAST items.

CONCLUSIONS

No published model can be recommended for use at the bedside to determine the success of vaginal birth after labor induction. Based on the limitations of included models, a list of recommendations for improving model performance and utilization is provided, as well as measures for encouraging appropriate use of prediction models. The attitudes of women and care providers, and the clinical and resource implications must be explored prior to recommending the use of prediction models for determining the success of labor induction.

Effect of fetal gender on induction of labor failure rates

PURPOSE

To evaluate gender effect on induction of labor (IoL) failure rates stratified by indication to delivery.

METHODS

Retrospective cohort analysis of singleton pregnancies 34-42 weeks undergoing cervical ripening using controlled-release PGE2 vaginal insert. IoL Indications were divided into: (1) maternal; (2) hypertensive disorders; (3) premature rupture of membrane or (4) fetal (growth abnormalities, oligohydramnios, postdate, etc,). IoL failure was defined as: (1) Bishop-score ≤7 after 24 hours of PGE2; (2) cesarean delivery due to failed induction; (3) fetal distress followed by PGE2 removal and emergent cesarean. IoL failure rates were stratified by neonatal gender and indication to induction. Logistic regression analysis was utilized to control outcomes to potential confounders.

RESULTS

Overall, 1062 pregnancies were included - 521 (49%) had male fetuses. IoL indications did not differ by gender. IoL failure rate was 20.1% (213/1062) - 76% for unfavorable Bishop-score after PGE2 removal; 5.2% for failed induction and 18.8% for fetal-distress while on PGE2. Overall, 14.3% delivered by cesarean section. There were no differences in IoL failure as a group or by indications to induction stratified by fetal gender (21.7% vs. 18.5%, male vs. females, p < 0.05).

CONCLUSIONS

IoL failure rate is not affected by fetal gender regardless of indication to induction.