Analysis of Influencing Factors of Embryo Development Arrest During Early Pregnancy and Construction and Validation...

Area of Science:

• Obstetrics and Gynecology
• Reproductive Medicine
• Medical Diagnostics

Background:

• Early pregnancy embryo development arrest lacks typical symptoms and predictive tools.
• Accurate prediction of embryo development arrest is crucial for timely clinical intervention.

Purpose of the Study:

• To identify key factors influencing early pregnancy embryo development arrest.
• To develop and evaluate a predictive model for embryo development arrest risk.

Main Methods:

• Retrospective analysis of 277 patients suspected of embryo development arrest.
• Development of logistic regression and random forest models using clinical and ultrasound data.
• Comparison of the predictive performance of the developed models.

Main Results:

• Older age, higher ultrasound resistance index (RI), and higher MSD/CRL ratio were risk factors.
• Lower progesterone, lower pregnancy-associated protein A (PAPP-A), and lower vascular endothelial growth factor (VEGF) were protective factors.
• The random forest model demonstrated superior predictive performance compared to the logistic regression model.

Conclusions:

• A random forest model incorporating age, ultrasound RI, progesterone, PAPP-A, MSD/CRL ratio, and VEGF can effectively predict embryo development arrest risk.
• This model provides a valuable tool for clinicians to identify at-risk pregnancies.
• Early identification facilitates timely management and potentially improves pregnancy outcomes.