Development and validation of a nomogram for the early prediction of preeclampsia in pregnant Chinese women

Abstract

To make early predictions of preeclampsia before diagnosis, we developed and validated a new nomogram for the early prediction of preeclampsia in pregnant Chinese women. A stepwise regression model was used for feature selection. Multivariable logistic regression analysis was used to develop the prediction model. We incorporated BMI, blood pressure, uterine artery ultrasound parameters, and serological indicator risk factors, and this was presented with a nomogram. The performance of the nomogram was assessed with respect to its calibration, discrimination, and clinical usefulness. Internal validation was assessed. The signature, which consisted of 11 selected features, was associated with preeclampsia status (P < 0.1) for the development dataset. Predictors contained in the individualized prediction nomogram included BMI, blood pressure, uterine artery ultrasound parameters, and serological indicator levels. The model showed good discrimination, with an area under the ROC curve of 0.8563 (95% CI: 0.8364–0.8761) and good calibration. The nomogram still had good discrimination and good calibration when applied to the validation dataset (area under ROC curve of 0.8324, 95% CI: 0.7873–0.8775). Decision curve analysis demonstrated that the nomogram was clinically useful. The nomogram presented in this study incorporates BMI, blood pressure, uterine artery ultrasound parameters, and serological indicators and can be conveniently used to facilitate the individualized prediction of preeclampsia.