Related Experiment Video
Updated: Dec 1, 2025

An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
External validation of a prediction model on vaginal birth after caesarean in a The Netherlands: a prospective cohort
Emy Vankan1, Sander M J van Kuijk2, Jan G Nijhuis3
1Maastricht Universitair Medisch Centrum, GROW-School for Oncology and Developmental Biology, Department of Obstetrics and Gynecology, Maastricht, Netherlands.
Objectives:
Discussing the individual probability of a successful vaginal birth after caesarean (VBAC) can support decision making. The aim of this study is to externally validate a prediction model for the probability of a VBAC in a Dutch population.
Methods:
In this prospective cohort study in 12 Dutch hospitals, 586 women intending VBAC were included. Inclusion criteria were singleton pregnancies with a cephalic foetal presentation, delivery after 37 weeks and one previous caesarean section (CS) and preference for intending VBAC. The studied prediction model included six predictors: pre-pregnancy body mass index, previous vaginal delivery, previous CS because of non-progressive labour, Caucasian ethnicity, induction of current labour, and estimated foetal weight ≥90th percentile. The discriminative and predictive performance of the model was assessed using receiver operating characteristic curve analysis and calibration plots.
Results:
The area under the curve was 0.73 (CI 0.69-0.78). The average predicted probability of a VBAC according to the prediction model was 70.3% (range 33-92%). The actual VBAC rate was 71.7%. The calibration plot shows some overestimation for low probabilities of VBAC and an underestimation of high probabilities.
Conclusions:
The prediction model showed good performance and was externally validated in a Dutch population. Hence it can be implemented as part of counselling for mode of delivery in women choosing between intended VBAC or planned CS after previous CS.
Related Concept Videos
Data Validation
Nursing assessment guides are generally based on holistic models rather than medical...
Regression Toward the Mean
Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
Reliability and Validity
Sensitivity, Specificity, and Predicted Value
Sensitivity is the...

