Predicting vaginal birth after previous cesarean: Using machine‐learning models and a population‐based cohort in Sweden

Abstract

This is an open access article under the terms of the Creat ive Commo ns Attri bution-NonCo mmerc ial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

Predictive Models for Estimating the Probability of Successful Vaginal Birth After Cesarean Delivery

“…The external validations of Grobman et al 2007 23 with low risk of bias demonstrated AUROCs of 0.71 (95% CI 0.67-0.76), 25 0.68 (95% CI 0.63-0.72), 26 and 0.64 (95% CI 0.61-0.67). 27 The external validation of Grobman et al 2009, 28 which had low risk of bias, demonstrated an AUROC of 0.72 (95% CI 0.67-0.76). 26 The models that included predictors available only close to delivery (eg, cervical examination findings) generally performed better than models designed for use during the antenatal period only, as illustrated in Figure 3.…”

Reliable Prediction Models Based on Enriched Data for Identifying the Mode of Childbirth by Using Machine Learning Methods: Development Study

“…Others analyzed the socioeconomic or sociodemographic features [1,19] and some have determined the main causes to be the region and level of medical services afforded [9]. Wollmann et al [3] attempted to predict the chances of normal births after a c-section. In this regard, they collected data of women with one previous birth in Sweden during 2008-2014 and built 3 machine learning models and 1 regression model.…”

“…According to Sana et al [1], machine learning techniques provide diagnosis and analytical amenities in several medical fields and their applications in clinical factors and analytics such as disease prediction, decision making based on extracted medical knowledge, and serving in patient management. Moreover, with the increasing amount of available data, machine learning techniques have significant benefits as prediction tools in health care [2] that sometimes provide surprising prediction models that help in clinical counseling [3]. These tools are fundamental to biomedical research and are utilized as an integral part of the clinical decision-making process [4].…”

The Stockholm–Gotland perinatal cohort—A population‐based cohort including longitudinal data throughout pregnancy and the postpartum period

“…The SGPC is further enriched with data from 10 National Health Care and Quality Registers. Initially, SGPC covered singleton births up to 22 October 2014 ( N = 175,522), and numerous studies have been published using this study population 1–28 . Recently, the cohort has been updated to include all births until 15 June 2020 ( N = 335,153 singleton and N = 11,025 multiple pregnancies).…”