No abstract

Magnetic resonance imaging offers unrivaled visualization of the fetal brain, forming the basis for establishing age-specific morphologic milestones. However, gauging age-appropriate neural development remains a difficult task due to the constantly changing appearance of the fetal brain, variable image quality, and frequent motion artifacts. Here we present an end-to-end, attention-guided deep learning model that predicts gestational age with R2 score of 0.945, mean absolute error of 6.7 days, and concordance correlation coefficient of 0.970. The convolutional neural network was trained on a heterogeneous dataset of 741 developmentally normal fetal brain images ranging from 19 to 39 weeks in gestational age. We also demonstrate model performance and generalizability using independent datasets from four academic institutions across the U.S. and Turkey with R2 scores of 0.81–0.90 after minimal fine-tuning. The proposed regression algorithm provides an automated machine-enabled tool with the potential to better characterize in utero neurodevelopment and guide real-time gestational age estimation after the first trimester.

We found that women decreased their PA  and exercise levels significantly in the third trimester and, thus, in the absence of a medical contra-indication there is considerable scope for an exercise intervention to improve activity  and exercise levels as pregnancy advances. However, an increase in PA levels in obese women needs further studies to determine whether it will improve the clinical outcomes for the woman and her offspring.

Objective We aimed to assess the risk of developing gestational diabetes mellitus (GDM) in women with a normal A1C (<5.7) compared with those with an A1C in the pre-diabetic range (5.7–6.4). Study Design This study comprises of a retrospective cohort of non-anomalous singleton pregnancies with maternal body mass index (BMI) ≥40 at a single institution from 2013 to 2017. Pregnancies with multiple gestation, late entry to care, type 1 or 2 diabetes, and missing diabetes-screening information were excluded. The primary outcome was development of GDM. Secondary outcomes included fetal growth restriction, macrosomia, gestational age at delivery, large for gestational age, delivery BMI at delivery, total weight gain in pregnancy, induction of labor, shoulder dystocia, and cesarean delivery. Bivariate statistics were used to compare demographics, pregnancy complications, and delivery characteristics of women who had an early A1C < 5.7 and A1C 5.7 to 6.4. Multivariable analyses were used to estimate the odds of the primary outcome. Results Eighty women (68%) had an early A1C <5.7 and 38 (32%) had a A1C 5.7 to 6.4. Women in the lower A1C group were less likely to be Black (45 vs. 74%, p = 0.01). No differences in other baseline demographics were observed. The median A1C was 5.3 for women with A1C < 5.7 and 5.8 for women with A1C 5.7 to 6.4 (p < 0.001). GDM was significantly more common in women with A1C 5.7 to 6.4 (3.8 vs. 24%, p = 0.002). Women with pre-diabetic range A1C had an odd ratio of 11.1 (95% CI 2.49–48.8) for GDM compared with women with a normal A1C. Conclusion Women with class III obesity and a pre-diabetic range A1C are at an increased risk for gestational diabetes when compared with those with a normal A1C in early pregnancy. Key Points

No abstract