Search

Background Fetal ultrasound is an important component of antenatal care, but shortage of adequately trained healthcare workers has limited its adoption in low-to-middle-income countries. This study investigated the use of artificial intelligence for fetal ultrasound in under-resourced settings. Methods Blind sweep ultrasounds, consisting of six freehand ultrasound sweeps, were collected by sonographers in the USA and Zambia, and novice operators in Zambia. We developed artificial intelligence (AI) models that used blind sweeps to predict gestational age (GA) and fetal malpresentation. AI GA estimates and standard fetal biometry estimates were compared to a previously established ground truth, and evaluated for difference in absolute error. Fetal malpresentation (non-cephalic vs cephalic) was compared to sonographer assessment. On-device AI model run-times were benchmarked on Android mobile phones. Results Here we show that GA estimation accuracy of the AI model is non-inferior to standard fetal biometry estimates (error difference −1.4 ± 4.5 days, 95% CI −1.8, −0.9, n = 406). Non-inferiority is maintained when blind sweeps are acquired by novice operators performing only two of six sweep motion types. Fetal malpresentation AUC-ROC is 0.977 (95% CI, 0.949, 1.00, n = 613), sonographers and novices have similar AUC-ROC. Software run-times on mobile phones for both diagnostic models are less than 3 s after completion of a sweep. Conclusions The gestational age model is non-inferior to the clinical standard and the fetal malpresentation model has high AUC-ROCs across operators and devices. Our AI models are able to run on-device, without internet connectivity, and provide feedback scores to assist in upleveling the capabilities of lightly trained ultrasound operators in low resource settings.

A Lactobacillus-deficient, anaerobe-rich vaginal microbiome has been associated with local inflammation and spontaneous preterm birth (sPTB), but few studies have assessed this association in the setting of HIV. We performed metagenomic sequencing and inflammatory marker assays on vaginal swabs collected in pregnancy. We grouped samples into 7 metagenomic clusters (mgClust) using the non-redundant VIRGO catalogue, and derived inflammatory scores by factor analysis. Of 221 participants, median Shannon diversity index (SDI) was highest in HIV+ with detectable viral load (1.31, IQR: 0.85–1.66; p Gardnerella metagenomic subspecies > 50% predicted sPTB (RR 2.6; 95%CI: 1.1, 6.4) and was higher in HIV+ (23% vs. 10%; p = 0.001). A novel Gardnerella metagenomic subspecies more abundant in women with HIV predicted sPTB. The risk of sPTB among women with HIV may be mediated by the vaginal microbiome and inflammation, suggesting potential targets for prevention.

Objectives To estimate the rate of pregnancy-associated emergency care visits and identify maternal and pregnancy characteristics associated with high utilization of emergency care among pregnant Medicaid recipients in North Carolina. Methods A retrospective cohort study using linked Medicaid hospital claims and birth records of 107,207 pregnant Medicaid recipients who delivered a live-born infant in North Carolina between January 1, 2008 and December 31, 2009. Rates were estimated per 1000 member months of Medicaid coverage. High utilization was defined as ≥ 4 visits. Emergency care visits included encounters in the emergency department or obstetric triage unit during pregnancy that did not result in hospital admission. Results During the study period, 57.5% of pregnant Medicaid recipients sought emergency care at least once during pregnancy. There were 171,909 emergency care visits with an overall rate of 202.3 visits per 1000 member months. Among the subset of pregnant women with Medicaid coverage for the majority of their pregnancy (n = 75,157), 18.1% were high utilizers. High emergency care utilization was associated with young age, black race, lower education, tobacco use, late preterm delivery, multifetal gestation, and having ≥ 1 comorbidity. Threatened labor and abdominal pain were the leading indications for visits. Conclusion Utilization of hospital-based emergency care services was common in this cohort of pregnant Medicaid recipients. Additional research is needed to assess the drivers for accessing care through the emergency department, and to examine differences in pregnancy outcomes and health care costs between high and low utilizers.

Breastfeeding remains a common practice in parts of the world where the burden of HIV is highest and the fewest alternative feeding options exist. The impossible dilemma faced by HIV-positive mothers is whether to breastfeed their infants in keeping with cultural norms but in doing so risk transmitting the virus through breast milk, or to pursue formula feeding, which comes with its own set of risks, including a higher rate of infant mortality from diarrheal illnesses, while reducing transmission of HIV. Treatment of mothers and/or their infants with antiretroviral drugs is a strategy that has been employed for several decades to reduce HIV transmission through pregnancy and delivery, but the effect of these agents when taken during breastfeeding is a newer field of study. In this article we evaluate the latest clinical research, from trials that encourage exclusive breastfeeding to trials of antiretroviral therapy (ART) for either the mother or infant, in an attempt to prevent transmission of HIV through breast milk. Additionally, we discuss research that is in progress, with results anticipated in the next few years that will further shape clinical guidelines and practice. Exclusive breastfeeding is much safer than mixed feeding (the supplementation of breastfeeding with other foods), and should be encouraged even in settings where ART for either the mother or infant is not readily available. The research published regarding maternal treatment with highly active antiretroviral therapy (HAART) during pregnancy and the breastfeeding period has all been non-randomized with relatively little statistical power, but suggests maternal HAART can drastically reduce the risk of transmission of HIV. Infant prophylaxis has been intensively studied in several trials and has been shown to be as effective as maternal treatment with antiretrovirals, reducing the transmission rate after 6 weeks to as low as 1.2%. Research that is in progress will provide us with more answers about the relative contribution of maternal treatment and infant prophylaxis in preventing transmission, and the results of such research may be expected as early as this year through 2013. There is hope that perinatal HIV transmission may be greatly reduced in breastfeeding populations worldwide through a combination of behavioral interventions that encourage exclusive breastfeeding and pharmacologic interventions with antiretrovirals for mothers and/or their infants.