Machine Learning Models for Prediction of Maternal Hemorrhage and Transfusion: Model Development Study.

Background: Current postpartum hemorrhage (PPH) risk stratification is based on traditional statistical models or expert opinion. Machine learning could optimize PPH prediction by allowing for more complex modeling.

Objective: We sought to improve PPH prediction and compare machine learning and traditional statistical methods.

Prediction of birthweight from third-trimester ultrasound in morbidly obese women.

Objective: The gestation-adjusted projection method (GAP method) uses third trimester ultrasound fetal weight to predict birthweight. Our study sought to assess if the accuracy of the GAP method in morbidly obese women depended on (1) ultrasound timing or (2) extreme elevations in maternal body mass index (BMI).

Study Design: We conducted a diagnostic accuracy study from 2007 to 2012 of all singleton pregnancies with BMI >40 kg/m(2) at the time of delivery that had fetal growth assessment between 30+0 and 35+0 weeks (EARLY) and greater than 35+0 weeks (LATE).