The abstract is read at the publisher; the summary is JClub's.
In the nuMoM2b cohort of 9289 nulliparous women, fetal growth outcomes show added value from prediction history: emerging-high risk predicts higher rates than persistent-high by 6.1 and 3.8 percentage points.
- Why it matters: Clinicians reassess risk at each antenatal visit, but it is unclear whether earlier predictions improve accuracy beyond the most recent visit, especially when uncertainty is reported.
- What they did: Using Mondrian conformal prediction at 6–13, 16–21, and 22–29 weeks for gestational diabetes, pre-eclampsia, preterm birth, suspected fetal growth restriction, and large for gestational age, the analysis compared emerging-high vs persistent-high among women high risk at Visit 3, adjusting for Visit 3 predicted probability.
- The result: Coverage was 89.6–90.6% per visit at a 90% calibration level but fell to 79.0–85.4% when combining three visits; for fetal growth outcomes, risk evolution may add information beyond Visit 3.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.