A new model for screening for early-onset preeclampsia

Area of Science:

• Obstetrics and Gynecology
• Maternal-Fetal Medicine
• Biomedical Engineering

Background:

• Early identification of preeclampsia is vital for minimizing adverse perinatal outcomes.
• Existing multiparametric algorithms may be overfitted, limiting reliability across diverse populations.
• There is a need for adaptable screening models for preeclampsia risk assessment.

Purpose of the Study:

• To evaluate a first-trimester multivariate Gaussian distribution model for early-onset preeclampsia screening.
• The model incorporates maternal characteristics and biophysical/biochemical parameters.
• Screening was conducted in a routine care, low-risk setting for pregnancies delivering before 34 weeks of gestation.

Main Methods:

• A prospective cohort study included singleton pregnancies undergoing routine first-trimester screening (8-14 weeks gestation).
• A multivariate Gaussian model utilized maternal a priori risk, serum pregnancy-associated plasma protein-A, and placental growth factor (8-14 weeks).
• Mean arterial pressure and uterine artery pulsatility index were measured at 11-14 weeks.

Main Results:

• The analysis included 6893 pregnancies; early-onset preeclampsia incidence was 0.2% (17 cases).
• The combined model (maternal characteristics, biophysical parameters, placental growth factor) achieved a 59% detection rate at a 5% false-positive rate.
• Adding placental growth factor significantly improved detection rates, reaching 94% for a 10% false-positive rate (AUC 0.96).

Conclusions:

• A multivariate Gaussian model integrating maternal factors, early placental growth factor, and biophysical variables is a feasible tool for early-onset preeclampsia screening in routine care.
• This model demonstrates effective screening capabilities in a low-risk population.
• Further comparison with regression-based prediction models is recommended.