Prediction of vaginal birth after cesarean deliveries using machine learning

Background Efforts to reduce cesarean delivery rates to 12–15% have been undertaken worldwide. Special focus has been directed towards parturients who undergo a trial of labor after cesarean delivery to reduce the burden of repeated cesarean deliveries. Complication rates are lowest when a vaginal birth is achieved and highest when an unplanned cesarean delivery is performed, which emphasizes the need to assess, in advance, the likelihood of a successful vaginal birth after cesarean delivery. Vaginal birth after cesarean delivery calculators have been developed in different populations; however, some limitations to their implementation into clinical practice have been described. Machine-learning methods enable investigation of large-scale datasets with input combinations that traditional statistical analysis tools have difficulty processing. Objective The aim of this study was to evaluate the feasibility of using machine-learning methods to predict a successful vaginal birth after cesarean delivery. Study Design The electronic medical records of singleton, term labors during a 12-year period in a tertiary referral center were analyzed. With the use of gradient boosting, models that incorporated multiple maternal and fetal features were created to predict successful vaginal birth in parturients who undergo a trial of labor after cesarean delivery. One model was created to provide a personalized risk score for vaginal birth after cesarean delivery with the use of features that are available as early as the first antenatal visit; a second model was created that reassesses this score after features are added that are available only in proximity to delivery. Results A cohort of 9888 parturients with 1 previous cesarean delivery was identified, of which 75.6% of parturients (n=7473) attempted a trial of labor, with a success rate of 88%. A machine-learning–based model to predict when vaginal delivery would be successful was developed. When features that are available at the first antenatal visit are used, the model showed a receiver operating characteristic curve with area under the curve of 0.745 (95% confidence interval, 0.728–0.762) that increased to 0.793 (95% confidence interval, 0.778–0.808) when features that are available in proximity to the delivery process were added. Additionally, for the later model, a risk stratification tool was built to allocate parturients into low-, medium-, and high-risk groups for failed trial of labor after cesarean delivery. The low- and medium-risk groups (42.4% and 25.6% of parturients, respectively) showed a success rate of 97.3% and 90.9%, respectively. The high-risk group (32.1%) had a vaginal delivery success rate of 73.3%. Application of the model to a cohort of parturients who elected a repeat cesarean delivery (n=2145) demonstrated that 31% of these parturients would have been allocated to the low- and medium-risk groups had a trial of labor been attempted. Conclusion Trial of labor after cesarean delivery is safe for most parturients. Success rates are high, even in a population with high rates of trial of labor after cesarean delivery. Application of a machine-learning algorithm to assign a personalized risk score for a successful vaginal birth after cesarean delivery may help in decision-making and contribute to a reduction in cesarean delivery rates. Parturient allocation to risk groups may help delivery process management.