Machine Learning in Electronic Health Records: Identifying High-Risk Obstetric Patients Pre and During Labor.

Our goal is to apply artificial intelligence (AI) and statistical analysis to understand the relationship between various factors and outcomes during pregnancy and labor and delivery, in order to personalize birth management and reduce complications for both mothers and newborns. We use a structured electronic health records database with data from approximately 130,000 births to train, test and validate our models. We apply machine learning (ML) methods to predict various obstetrical outcomes before and during labor, with the aim of improving patient care management in the delivery ward. Using a large cohort of data (∼180 million data points), we then demonstrated that ML models can predict successful vaginal delivery, in the general population as well as a sub-cohort of women attempting trial of labor after a cesarean delivery. The real-time dynamic model showed increasing rates of accuracy as the delivery process progressed and more data became available for analysis. Additionally, we developed a cross-facilities application of an AI model that predicts the need for an unplanned cesarean delivery, illuminating the challenges associated with inter-facility variation in reporting practices. Overall, these studies combine novel technologies with currently available data to predict and assist safe deliveries for mothers and babies, both locally and globally.

Membrane stripping in group B streptococcus carriers does not impede adequate intrapartum antibiotic prophylaxis: a retrospective study.

Objective: Membrane stripping in group B streptococcus (GBS) carriers poses an increased risk of inadequate antibiotic prophylaxis, potentially due to accelerated labor, thereby potentially impacting the management of GBS colonization during delivery. We compared the adequacy of intrapartum antibiotic prophylaxis between pregnant women colonized with GBS, who underwent membrane stripping and those who did not. The study aimed to determine whether the performance of membrane stripping, by potentially shortening labor duration, increases the risk of inadequate antibiotic prophylaxis dispensation. Study design: A retrospective cohort study was conducted on GBS screen-positive women with a full-term singleton pregnancy in cephalic presentation, who were eligible for vaginal delivery. The exposed group consisted of women who underwent membrane stripping, while the unexposed group consisted of women who did not undergo membrane stripping. The primary outcome was defined as inadequate duration of antibiotic prophylaxis during labor, wherein less than 4 h of beta-lactam antibiotics were administered prior to delivery. Neonatal outcome was compared between the groups. Results: This retrospective cohort study comprised 1,609 women, with 129 in the exposed group (stripping group) and 1,480 in the unexposed group (no stripping group). Adequate intrapartum antibiotic prophylaxis was received by 64.3% (83/129) of the exposed group, compared to 46.9% (694/1,480) of the unexposed group (p = 0.003). Membrane stripping was associated with increased odds of receiving adequate prophylaxis (OR 1.897, 95% CI 1.185-3.037, p = 0.008). After excluding women who presented to the labor ward in active labor and delivered in less than 4 h, both the exposed and unexposed groups had similarly high rates of adequate intrapartum antibiotic prophylaxis (87.5% vs. 85.8%, respectively). No significant difference was observed in adverse neonatal outcomes between the groups. Conclusion: The provision of membrane stripping did not impede adequate intrapartum antibiotic prophylaxis and was correlated with a higher rate of sufficient prophylaxis in comparison to non-swept patients. These observations suggest that membrane stripping can be considered a safe option for ensuring adequate antibiotic prophylaxis in women colonized with GBS.

Maternal hybrid immunity and risk of infant COVID-19 hospitalizations: national case-control study in Israel.

Hybrid immunity, acquired through vaccination followed or preceded by a COVID-19 infection, elicits robust antibody augmentation. We hypothesize that maternal hybrid immunity will provide greater infant protection than other forms of COVID-19 immunity in the first 6 months of life. We conducted a case-control study in Israel, enrolling 661 infants up to 6 months of age, hospitalized with COVID-19 (cases) and 59,460 age-matched non-hospitalized infants (controls) between August 24, 2021, and March 15, 2022. Infants were grouped by maternal immunity status at delivery: Naïve (never vaccinated or tested positive, reference group), Hybrid-immunity (vaccinated and tested positive), Natural-immunity (tested positive before or during the study period), Full-vaccination (two-shot regimen plus 1 booster), and Partial-vaccination (less than full three shot regimen). Applying Cox proportional hazards models to estimate the hazard ratios, which was then converted to percent vaccine effectiveness, and using the Naïve group as the reference, maternal hybrid-immunity provided the highest protection (84% [95% CI 75-90]), followed by full-vaccination (66% [95% CI 56-74]), natural-immunity (56% [95% CI 39-68]), and partial-vaccination (29% [95% CI 15-41]). Maternal hybrid-immunity was associated with a reduced risk of infant hospitalization for Covid-19, as compared to natural-immunity, regardless of exposure timing or sequence. These findings emphasize the benefits of vaccinating previously infected individuals during pregnancy to reduce COVID-19 hospitalizations in early infancy.

Women's attitudes towards disclosure of genetic information in pregnancy with varying levels of penetrance.

BACKGROUND: Chromosomal-microarray-analysis (CMA) may reveal susceptibility-loci (SL) of varied penetrance for autism-spectrum-disorder (ASD) and other neurodevelopmental conditions. Attitudes of women/parents to disclosure of SL during pregnancy are understudied. METHODS: A multiple-choice questionnaire was distributed to postpartum women. Data were collected on women's interest to receive prenatal genetic information with various levels of penetrance. RESULTS: Women's (n = 941) disclosure choices were dependent on the magnitude of risk: approximately 70% supported disclosure of either full or 40% penetrance, 53% supported disclosure at a 20% risk threshold, and 40% supported disclosure at 10% or less. Although most women supported, rejected or were indecisive about disclosure consistently across all risk levels, nearly one-quarter (24%) varied their responses based on penetrance, and this was associated with religiosity, education, parity and concern about fetal health (p-values <0.04). Among those who varied their choices, the risk threshold was lower among secular women (20%) than among ultraorthodox women (40%). In a multivariable analysis, ultraorthodox women were much less likely to vary their choices on ASD disclosure compared with secular women (aOR = 0.37, p < 0.001). CONCLUSION: Women's attitudes toward disclosure are influenced by the level of risk and their individual characteristics. We therefore encourage engaging women/couples in disclosure decisions regarding uncertain and probabilistic results from prenatal genomic tests.

Timing of midstream urine culture before endourological procedure-can we do better?-A comparative study.

Endourological procedures are the mainstay of treatment for stone disease in the upper urinary system. Infection is a common complication, and urine cultures (UC) are often obtained preoperatively. In this study, we sought to investigate the role of positive UC in the 90 days prior to surgery (90PreOp) in predicting postoperative infectious complications in comparison to a single positive preoperative UC (PreOP). We compared the correlation between positive PreOp UCs and positive 90PreOp UCs with postoperative urosepsis, and a positive UC obtain proximal to obstruction (Prox UC) during percutaneous nephrolithotomy, ureteroscopy and a placement of nephrostomy tube or ureteral stent. Data from 140 consecutive patients were collected. PreOp UCs were positive in 15 (11%) of patients versus 31 of 140 (22%) positive 90PreOp UCs. All six sepsis events had a positive 90PreOp UC, and five had a positive PreOp UC. Fourteen (93.3%) out of 15 positive Prox UC had a positive 90PreOp UC, whereas only 7 (38.9%) had a positive 90PreOp UC. Positive 90PreOp UC outperformed PreOp UC in predicting positive Prox UC, OR = 12.8 (95% CI 3.70-44.30, p < 0.001), versus OR of 88.9 (95% CI 11.0-720.7, p < 0.001); sensitivity 93%(95% CI 68-100%) versus 47%(95% CI 21-73%); as well as area under the ROC curve(AUC), 0.90 (CI 0.80-0.95) for 90PreOp versus 0.70 (CI 0.56-0.82) for positive Prox UC. Uropathogen persistence was better identified when using 90PreOp UC (27%) than using PreOp UC (12%). We suggest reviewing UCs taken within 90 days preoperatively as this was found superior to a single preoperative midstream UCs in predicting postoperative infectious sequela after stone procedure.

The effectiveness of vaginal progesterone in reducing preterm birth in high-risk patients diagnosed with short cervical length after 24 weeks: A retrospective cohort study.

Objective: To assess the impact of progesterone treatment on maternal and neonatal outcomes in women with a history of preterm birth and short cervical length diagnosed after 24 weeks of gestation. Methods: A retrospective cohort study included women with a history of preterm birth and a transvaginal sonographic cervical length measurement of ≤ 25 mm, diagnosed between 24+0 and 33+6 weeks of gestation. Exclusion criteria included prior progesterone treatment, cervical cerclage, or pessary. The study population was divided into the progesterone treatment group and the non-treatment group. Results: The study included 104 women, with 46.2% (48/104) receiving progesterone treatment and 53.8% (56/104) not receiving treatment. The rate of spontaneous preterm birth before 37 weeks of gestation was 43% (24/56) in the non-treatment group and 31% (15/48) in the progesterone treatment group (P = 0.14); the rate of spontaneous preterm birth before 34 weeks was 7% (4/56) in the non-treatment group and 0% (0/48) in the progesterone treatment group (P = 0.05). Progesterone treatment was associated with a significant decrease in neonatal intensive care unit admissions (OR 0.20, 95% CI 0.05-0.74) and in the neonatal hospitalization period (mean difference in days 2.43, 95% CI 0.44-4.42). The risk of recurrent spontaneous preterm birth was highest (71%) among women with two or more previous preterm deliveries who did not receive progesterone treatment, and lowest (24%) among women with one previous preterm delivery who received progesterone treatment. Conclusion: Progesterone treatment was associated with a reduction in rates of spontaneous preterm birth before 34 weeks of gestation, neonatal intensive care unit admission, and neonatal length of stay in high-risk patients, even when initiated after 24 weeks of gestation.

Maternal third dose of BNT162b2 mRNA vaccine and risk of infant COVID-19 hospitalization.

Infants are at a higher risk of Coronavirus Disease 2019 (COVID-19)-related hospitalizations compared to older children. In this study, we investigated the effect of the recommended third maternal dose of BNT162b2 COVID-19 vaccine during pregnancy on rates of infant COVID-19-related hospitalizations. We conducted a nationwide cohort study of all live-born infants delivered in Israel between 24 August 2021 and 15 March 2022 to estimate the effectiveness of the third booster dose versus the second dose against infant COVID-19-related hospitalizations. Data were analyzed for the overall study period, and the Delta and Omicron periods were analyzed separately. Cox proportional hazard regression models estimated hazard ratios and 95% confidence intervals (CIs) for infant hospitalizations according to maternal vaccination status at delivery. Among 48,868 live-born infants included in the analysis, rates of COVID-19 hospitalization were 0.4%, 0.6% and 0.7% in the third-dose, second-dose and unvaccinated groups, respectively. Compared to the second dose, the third dose was associated with reduced infant hospitalization with estimated effectiveness of 53% (95% CI: 36-65%). Greater protection was associated with a shorter interval between vaccination and delivery. A third maternal dose during pregnancy reduced the risk of infant hospitalization for COVID-19 during the first 4 months of life, supporting clinical and public health guidance for maternal booster vaccination to prevent infant COVID-19 hospitalization.

Effectiveness of a third BNT162b2 mRNA COVID-19 vaccination during pregnancy: a national observational study in Israel.

The Centers for Disease Control (CDC) recommend a third dose of COVID-19 vaccine for pregnant women, although data regarding effectiveness during pregnancy are lacking. This national, population-based, historical cohort study of pregnant women in Israel, delivering between August 1, 2021 and March 22, 2022, aims to analyze and compare the third and second doses' vaccine effectiveness in preventing COVID-19-related hospitalizations during pregnancy during two COVID-19 waves (Delta variant in the summer of 2021 and Omicron, BA.1, variant in the winter of 2022). Time-dependent Cox proportional-hazards regression models estimate the hazard ratios (HR) and 95% confidence intervals (CI) for COVID-related outcomes according to vaccine dose, and vaccine effectiveness as 1-HR. Study includes 82,659 and 33,303 pregnant women from the Delta and Omicron waves, respectively. Compared with the second dose, the third dose effectively prevents overall hospitalizations with SARS-CoV-2 infections, with estimated effectiveness of 92% (95% CI 83-96%) during Delta, and enhances protection against significant disease during Omicron, with effectiveness of 92% (95% CI 26-99%), and 48% (95% CI 37-57%) effectiveness against hospitalization overall. A third dose of the BNT162b2 mRNA COVID-19 vaccine during pregnancy, given at least 5 months after the second vaccine dose, enhances protection against adverse COVID-19-related outcomes.

Postpartum women's attitudes to disclosure of adult-onset conditions in pregnancy.

BACKGROUND: Advanced prenatal genomic technologies can identify risks for adult-onset (AO) conditions in the fetus, challenging the traditional purpose of prenatal testing. Professional guidelines commonly support disclosure of high-penetrance AO actionable conditions, yet attitudes of women/parents to these findings and factors affecting their attitudes are understudied. METHODS: We explored 941 (77% response rate) postpartum women's attitudes towards receiving prenatal genetic information, and associations of sociodemographic, medical and psychological characteristics with their choices, focusing on AO conditions. RESULTS: Women largely support the disclosure of actionable AO findings (58.4%), in line with professional guidelines. A third of the women also supported the disclosure of non-actionable AO conditions. Stronger religious observance (p < 0.001) and higher psychological distress (p = 0.024) were associated with decreased interest in receiving actionable AO conditions, whereas higher concern for fetal health yielded increased interest (p = 0.032). Attitudes towards disclosure were strongly associated with women's perceived benefit of such information for their own, partner's, and future child's health. Termination of pregnancy based on such information received very little support. CONCLUSION: In-light of the demonstrated understanding of nuanced genetic information and the observed diversity in attitudes, a culturally competent opt-in/out policy could be considered. If full-disclosure is practiced, support should be provided to those expressing higher levels of distress.