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

Abstract

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.

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

“…Recent studies use electronic medical information on maternal and fetal characteristics to construct prediction models regarding mode of delivery after IOL 26 – 28 . However, very few use ML with the same goal 2 , 29 . Also, several research studies explored third trimester US biometry planes for image segmentation 30 , 31 , image or plane classification 8 , 15 , 16 and fetal biometry estimation 32 , 33 .…”

“…Regarding tabular data collection, maternal age, gravidity, parity, BMI, height, GA, Bishop score, IOL indications, mode of delivery, CS indications, intrapartum complications, neonatal birth weight and neonatal outcomes were among the features examined 2 . Data were collected on admission and at the onset of the first stage of labor, after pelvic examination and assessment of both mother and fetus.…”

“…Successful IOL was determined as VD after induction. CS indications were stratified between non-reassuring fetal heart rate and failed induction/labor dystocia 2 . IOL duration was the time from IOL initiation to delivery 1 .…”

“…Induction of labor (IOL) is a common obstetric procedure that involves artificially initiating uterine contractions to start labor and delivery 1 . IOL rates are increasing worldwide, particularly in developed countries, accounting for 25% of deliveries in the UK and US 2 , 3 . IOL can lead to a cesarean section (CS), although it does not increase its rate 4 .…”