Search reports, ask a question, or jump to a page.
The problem
Intervention: Use of antenatal ultrasound markers (uterine artery Doppler, placental size, fetal weight), maternal blood tests (serology for fetal growth restriction risk), and maternal characteristics (blood pressure, BMI, parity) combined with machine learning to predict upper quartile childhood systolic blood
Who it was tested with: 75 children aged 3-6 years born to mothers identified as having higher fetal growth restriction risk based on abnormal maternal serology.
Experience from people who deliver programmes: stories, case studies and lessons learned. Valuable for understanding how and why, and for spotting what to test next, but not a measure of effect.
"Participants were born to mothers who had attended a specialised clinic, following identification of higher FGR risk based on abnormal maternal serology... Antenatal ultrasound data at 23 weeks gestation were obtained... RF analysis demonstrated antenatal markers relating to FGR risk predict the upper quartile of childhood SBP with an AUC 0.97." This demonstrates a predictive modelling approach correlating antenatal factors with childhood blood pressure outcomes measured years later.
Small sample size (n=75); population limited to high-risk pregnancies, reducing generalisability; single time-point measurement of childhood blood pressure without follow-up; cannot establish causation; machine learning model not validated in independent cohort
Across countries and designs
1 study · 1 country
