A study protocol for a predictive model to assess population‑based risk of adverse pregnancy outcomes: The Adverse Pregnancy Outcomes Population Risk Tool (PregPoRT) - PubMed
8 hours ago
- #Adverse Pregnancy Outcomes
- #Predictive Modeling
- #Health Equity
- Study protocol for PregPoRT, a predictive model to assess population-based risk of adverse pregnancy outcomes (APOs).
- APOs like gestational diabetes, preeclampsia, and placental abruption impact maternal and fetal health.
- Existing models lack social, behavioral, and environmental determinants; PregPoRT integrates these factors.
- Data sources include Canadian Community Health Survey (CCHS), CAN-Marg, CANUE, and Can-ALE datasets.
- Predictors selected based on a health equity-informed framework.
- Primary outcome is a composite of APOs identified via ICD codes.
- Model uses Weibull accelerated failure time model and LASSO for variable selection.
- Validation methods include split-sample, bootstrap, and temporal validation.
- PregPoRT aims to support public health planning, resource allocation, and maternal health equity monitoring.
- First Canadian model to use nationally representative linked survey and administrative data.