A dynamic prediction model for preeclampsia using the sFlt-1/PLGF ratio combined with multiple factors

Area of Science:

• Obstetrics and Gynecology
• Maternal-Fetal Medicine
• Biomarkers in Pregnancy

Background:

• Preeclampsia (PE) is a severe pregnancy complication with significant maternal and neonatal mortality worldwide.
• Current management relies on delivery as the only definitive treatment.
• There is a need for effective prediction models to improve clinical management.

Purpose of the Study:

• To establish a dynamic prediction model for preeclampsia (PE).
• To evaluate the predictive performance of the soluble FMS-like tyrosine kinase-1/placental growth factor (sFlt-1/PLGF) ratio combined with maternal characteristics and laboratory results.
• To assess the model's accuracy across different gestational trimesters.

Main Methods:

• A dataset of 737 patients and a verification set of 176 pregnant women were analyzed.
• The sFlt-1/PLGF ratio was investigated alongside maternal factors and routine prenatal laboratory results.
• Multivariate logistic regression was employed to build and validate predictive models for PE.

Main Results:

• The prediction model incorporating the sFlt-1/PLGF ratio and maternal factors demonstrated improved performance.
• Area Under the Curve (AUC) values ranged from 0.826 at 20-24 weeks to 0.879 at 25-29 weeks and 0.862 at 30-34 weeks.
• The model showed good predictive accuracy and excellent clinical application value.

Conclusions:

• The combination of the sFlt-1/PLGF ratio and multiple factors between 25-29 weeks effectively predicts preeclampsia.
• Late pregnancy re-examinations for PE prediction using this model showed less significant improvement.
• The developed model offers valuable clinical utility for early PE detection.