Impact of Race/Ethnicity and Insurance Status on Obstetric Outcomes: Secondary Analysis of the NuMoM2b Study.

OBJECTIVE: This study aimed to investigate the impact of race/ethnicity and insurance status on obstetric outcomes in nulliparous women. STUDY DESIGN: Secondary analysis of the Nulliparous Pregnancy Outcomes Study Monitoring Mothers-To-Be. Obstetric outcomes included the development of a hypertensive event during pregnancy, need for a cesarean section, delivery of a preterm neonate, and postpartum hemorrhage. RESULTS: Of 7,887 nulliparous women, 64.7% were non-Hispanic White (White), 13.4% non-Hispanic Black (Black), 17.8% Hispanic, and 4.1% were Asian. Black women had the highest rates of developing new-onset hypertension (32%) and delivering preterm (11%). Cesarean deliveries were the highest in Asian (32%) and Black women (32%). Individuals with government insurance were more likely to deliver preterm (11%) and/or experience hemorrhage after delivery. In multivariable analyses, race/ethnicity was associated with hypertension and cesarean delivery. More important, the adjusted odds ratios for preventable risk factors, such as obesity, diabetes, and severe anemia were greater than the adjusted odds ratios for race/ethnicity in terms of poor maternal outcome. CONCLUSION: Although disparities were observed between race/ethnicity and obstetric outcomes, other modifiable risk factors played a larger role in clinical differences. KEY POINTS: · Race or insurance alone had mixed associations with maternal morbidities.. · Race and insurance had low associations with maternal morbidities.. · Other, modifiable risk factors may be more important.. · Both social and biological factors impact health disparities..

Machine Learning Models for Predicting Neonatal Mortality: A Systematic Review.

INTRODUCTION: Approximately 7,000 newborns die every day, accounting for almost half of child deaths under 5 years of age. Deciphering which neonates are at increased risk for mortality can have an important global impact. As such, integrating high computational technology (e.g., artificial intelligence [AI]) may help identify the early and potentially modifiable predictors of neonatal mortality. Therefore, the objective of this study was to collate, critically appraise, and analyze neonatal prediction studies that included AI. METHODS: A literature search was performed in PubMed, Cochrane, OVID, and Google Scholar. We included studies that used AI (e.g., machine learning (ML) and deep learning) to formulate prediction models for neonatal death. We excluded small studies (n < 500 individuals) and studies using only antenatal factors to predict mortality. Two independent investigators screened all articles for inclusion. The data collection consisted of study design, number of models, features used per model, feature importance, internal and/or external validation, and calibration analysis. Our primary outcome was the average area under the receiving characteristic curve (AUC) or sensitivity and specificity for all models included in each study. RESULTS: Of 434 articles, 11 studies were included. The total number of participants was 1.26 M with gestational ages ranging from 22 weeks to term. Number of features ranged from 3 to 66 with timing of prediction as early as 5 min of life to a maximum of 7 days of age. The average number of models per study was 4, with neural network, random forest, and logistic regression comprising the most used models (58.3%). Five studies (45.5%) reported calibration plots and 2 (18.2%) conducted external validation. Eight studies reported results by AUC and 5 studies reported the sensitivity and specificity. The AUC varied from 58.3% to 97.0%. The mean sensitivities ranged from 63% to 80% and specificities from 78% to 99%. The best overall model was linear discriminant analysis, but it also had a high number of features (n = 17). DISCUSSION/CONCLUSION: ML models can accurately predict death in neonates. This analysis demonstrates the most commonly used predictors and metrics for AI prediction models for neonatal mortality. Future studies should focus on external validation, calibration, as well as deployment of applications that can be readily accessible to health-care providers.

Estriol: emerging clinical benefits.

OBJECTIVE: Estriol is the main estrogen in pregnancy, but has received less attention outside gestation. It is well known that pregnancy has an immunosuppressive effect on many autoimmune diseases such as multiple sclerosis, psoriasis, thyroiditis, uveitis, and rheumatoid arthritis. Emerging evidence indicates that estriol has potential immunomodulatory benefits for many disease states including autoimmune, inflammatory, and neurodegenerative conditions. In this review, we discuss emerging roles for estriol in the treatment of menopausal symptoms, osteoporosis, cancer, hyperlipidemia, vascular disease, and multiple sclerosis. Estriol appears to offer a potentially cost-effective approach to a variety of conditions and may offer a wide range of health benefits. METHODS: We reviewed the English language MEDLINE literature with estriol in the title with emphasis on publications including nonpregnant females between January 1974 and August 2016. Approximately 393 such articles were considered and 72 articles have been referenced in this review. RESULTS: Estriol offers considerable benefits for postmenopausal women with reduced risks that are normally associated with traditional hormone therapies. These benefits include improved control of menopausal symptoms and better urogenital health. Moreover, the immunomodulatory role of estriol in reducing proinflammatory cytokines may be an important new therapeutic option for chronic autoimmune and neurodegenerative illnesses. Since it is a relatively weak estrogen, there is potential for use in men for conditions such as multiple sclerosis. CONCLUSIONS: We conclude transvaginal estriol potentially offers a suitable physiologic delivery and cost-effective alternative to currently available estrogen regimens in selected patients. Additional studies on mode of delivery, safety, and efficacy merit further investigation.