A prognostic model to predict the risk of cesarean delivery after induction of labour: development, validation, and clinical utility

Induction of labour (IoL) is an increasingly common obstetric procedure aimed at artificially stimulating labour. However, cesarean delivery could occur due to various complications associated with the procedure. Evaluating the risk of cesarean delivery after IoL is crucial for making informed decisions between IoL and pre-labour cesarean delivery. A prospective cohort study was conducted at the University of Gondar Specialized and Tertiary Hospital, Ethiopia, involving 628 pregnant women. Univariable and multivariable analyses were used to identify predictors, and model selection was based on the log-likelihood ratio test and Bayesian information criterion. Model accuracy was assessed using the area under the receiver operating characteristic curve (AUC) and a calibration plot. Internal validation was performed through bootstrapping, and the clinical utility of the model was evaluated using decision curve analysis. A simplified risk score and web calculator were developed for practical use. The rate of cesarean delivery (CS) was 51%. The final model included three predictors: parity, history of stillbirth, and Bishop score. The model exhibited good discrimination (AUC = 0.82; 95% CI: 0.79 to 0.85) and calibration. The model demonstrated similar performance (AUC: 0.82) to the original model in the validation sample, indicating a low risk of overfitting. Decision curve analysis demonstrated a higher net benefit for treatment decisions guided by the model. The risk prediction model, based on parity, history of stillbirth, and Bishop score, demonstrated good discrimination, calibration, and clinical utility in stratifying women undergoing IoL based on their risk of CS. This model has the potential to guide clinicians in decision-making regarding IoL, thereby improving labour outcomes.