What question did this study set out to answer?

To develop a predictive framework using AI for noninvasive risk stratification of preterm premature rupture of membranes (PPROM).

June 12, 2026npj Digital MedicineOpen Access

Noninvasive PPROM risk stratification with explainable AI using routine antenatal CRP and albumin

View Full Paper

Ask AI

Bookmark

To develop a predictive framework using AI for noninvasive risk stratification of preterm premature rupture of membranes (PPROM).
Utilized a dataset of 114,601 antenatal laboratory and ultrasound measurements.
Employed a multimodal AI model integrating maternal demographics, lab results, and ultrasound data.
Optimized XGBoost algorithm for prediction with AUC of 0.952.
Identified elevated CRP levels and decreased albumin as significant risk factors in late pregnancy.
SHAP analysis revealed dynamic risk patterns across gestation, ensuring model interpretability.
The AI-driven framework enhances accurate PPROM risk assessment.

No takes yet. Share an insight, caveat, or question.

Randomized trial demonstrates noninvasive PPROM risk stratification using AI in pregnancies, implying improved maternal care options.

Tan et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark