A Primary Screening Predictive Model for Abnormally Invasive Placenta Based on Clinical and Basic Ultrasound Factors...

Area of Science:

• Obstetrics and Gynecology
• Maternal-Fetal Medicine
• Diagnostic Imaging

Background:

• Abnormally invasive placenta (AIP) poses significant risks during pregnancy.
• Accurate prediction and screening are crucial for improved maternal outcomes.
• Existing prediction methods have limitations in comprehensive risk assessment.

Purpose of the Study:

• To identify risk factors for abnormally invasive placenta (AIP) in singleton pregnancies.
• To develop and validate a predictive model for AIP using clinical and basic ultrasound features.
• To enhance early screening of high-risk pregnancies for AIP.

Main Methods:

• Retrospective analysis of 16,735 singleton pregnancies.
• Inclusion of 18 clinical and 3 basic ultrasound features.
• Development of clinical-only, ultrasound-only, and combined predictive models.
• Validation using ROC curves, AUC, calibration curves, and DCA.

Main Results:

• AIP occurred in 0.962% of cases.
• Independent predictors included prior placenta accreta spectrum, advanced maternal age, ART, obesity, and placenta previa.
• The combined model achieved an AUC of 0.844 in the validation set.
• The combined model demonstrated good discrimination, calibration, and clinical utility.

Conclusions:

• A combined clinical and basic ultrasound model offers superior performance for AIP prediction compared to single-component models.
• The developed nomogram provides a practical tool for rapid screening of pregnant women at high risk for AIP.
• This model can aid clinicians in timely identification and management of AIP.