Development of a multivariate predictive nomogram among women with antepartum fetal death diagnosed at ≥34 weeks of gestation for outcome of TOLAC

Abstract

Abstract Objective A priori estimate on probability of having successful vaginal birth, helps to reduce maternal complications and increases treating physician’s confidence when planning a TOLAC in women with antepartum fetal death. Aim for this study was to develop a nomogram which will give probability of vaginal birth from maternal features in women with antepartum fetal death diagnosed at ≥ 34 week’s gestation and previous one low transverse cesarean section (LTCS). Methods This was a prospective observational study where participants were managed based on a predesigned protocol. Data was collected on different predelivery maternal features. Outcomes were categorized into two classes - vaginal delivery and cesarean delivery. Different classifiers were trained with data obtained on maternal features and accuracy of predicting outcome class determined. The machine learning model giving highest accuracy was used to develop a nomogram. Result Classical machine learning models by using selective maternal features could predict outcome of TOLAC among women attempting VBAC with IUFD with high accuracy. Factors found to have a significant impact on outcome of TOLAC according to their order of importance were maternal BMI at admission, bishop score, duration of augmentation, estimated foetal weight, interval from previous LTCS, admission to active labor interval, vaginal delivery after LTCS and gestational age. The Naïve -Bayes model gave the highest prediction accuracy (0.88). Conclusion Non-linear classifiers by using selective features could predict outcome of TOLAC among women attempting VBAC with IUFD at or beyond 34 weeks gestation with high accuracy.