Ariel Many

Background: Artificial intelligence (AI), which spans machine learning (ML), deep learning (DL), computer vision, and natural language processing (NLP), is now used across obstetric care, including ultrasound interpretation (biometry, anomaly detection), fetal monitoring (cardiotocography), maternal risk stratification (preeclampsia, preterm birth, hemorrhage), labor and delivery decision support, genomic screening, and telehealth. Methods: We conducted a narrative (non-systematic) review of the literature published between 2016 and 2026, distinguishing the level of evidence supporting each application. Results: Reported performance is frequently high for image-based tasks such as fetal biometry and anomaly detection (accuracy and AUC often exceeding 0.85), whereas intrapartum CTG analysis remains modest (AUROC ~0.60–0.70, overlapping the inter-observer variability of clinicians). Most published evidence is retrospective and internally validated; comparatively few tools have undergone external or prospective validation, and only a small number have received regulatory clearance. Limitations: The evidence base is heterogeneous, external validation and calibration are often absent, and we did not perform a formal risk-of-bias appraisal. Conclusions: AI has real potential to improve prenatal diagnosis and individualized care, but claims that it is ready for the clinic are often premature. Prospective and external validation, calibration and clinical-utility assessment, transparent reporting, attention to bias and equity, and sustained clinician oversight are prerequisites for safe adoption.

Recent advances in artificial intelligence (AI), especially machine learning (ML), deep learning (DL), natural language processing (NLP) and computer vision have rapidly impacted obstetric care. Key applications include automated ultrasound interpretation (biometry, anomaly detection), AI-enhanced fetal monitoring (cardiotocography), risk stratification (preeclampsia, preterm birth, hemorrhage), labor management (delivery mode prediction), genomic screening (NIPT interpretation), and remote/telehealth tools for monitoring especially in underserved areas. For example, DL models now attain accuracy comparable to experts for fetal ultrasound biometry[1], and FDA-cleared AI tools have achieved >97% detection of congenital heart defects during prenatal screening[2]. However, clinical readiness varies: some technologies (e.g. ultrasound AI tools) are already FDA-cleared[2,3], whereas others remain at proof-of-concept. Across studies, performance metrics (AUC, R2, accuracy) are generally high (often >0.85) but depend on data quality and label definitions[4,5]. Crucial issues include dataset biases, lack of standardization, explainability, and regulatory oversight. This review synthesizes AI technologies, applications, validation (metrics, datasets), deployment (trials, approval, integration), and ethical considerations, and identifies knowledge gaps. Overall, AI shows promise to improve prenatal diagnosis and individualized care, but requires rigorous validation, transparent algorithms, and clinician oversight to ensure safety, equity and trust.

Objectives: To evaluate the association between antenatal betamethasone exposure and neonatal respiratory morbidity among late-preterm births. We further examined whether gestational age at delivery and the exposure-to-delivery interval modify this association. Methods: We conducted a retrospective cohort study of singleton live births at 34–36 + 6 weeks in a tertiary center (2011–2023). Betamethasone exposure was classified as none, early (7 days and evaluated separately at 34, 35, and 36 weeks. Primary outcomes were RDS and composite respiratory morbidity (RDS, TTN, or ≥3 days of respiratory support); neonatal hypoglycemia was secondary. Adjusted odds ratios were estimated using multivariable logistic regression including maternal age, parity, delivery mode, and birthweight. Results: The study included 2668 late-preterm infants, of whom 2356 (88.3%) were unexposed and 312 (11.7%) were exposed to antenatal corticosteroids (ACSs). Among exposed pregnancies, 138 (44.2%) received early ACS and 174 (55.8%) late ACS; 163 (52.2%) delivered ≤7 days and 149 (47.8%) >7 days after administration. Late ACS exposure was associated with lower odds of RDS (aOR 0.37, 95% CI 0.17–0.69) and composite respiratory morbidity (aOR 0.55, 95% CI 0.31–0.92), but with increased odds of neonatal hypoglycemia (aOR 2.72, 95% CI 1.26–5.31). Among pregnancies delivering at 34 weeks, exposure within ≤7 days was associated with a marked reduction in RDS (aOR 0.25, 95% CI 0.07–0.79; NNT ≈ 3), whereas no respiratory benefit was observed at 35 or 36 weeks or when the interval exceeded 7 days. Conclusions: Antenatal betamethasone exposure among late-preterm births was not uniformly associated with neonatal respiratory outcomes, with associations varying by gestational age at delivery and the exposure-to-delivery interval. These findings may be interpreted in the context of potential respiratory benefit alongside accompanying metabolic risk, with exploratory analyses suggesting a more pronounced signal among deliveries at 34 weeks within ≤7 days.

Objectives: To determine whether in a labor floor housed continuously by senior physicians the risk of adverse maternal and neonatal outcome is affected by time of delivery. Methods: This retrospective cohort study, conducted at a tertiary medical center, assessed singleton term deliveries from 1 January 2011 to 30 January 2020. Participants were categorized based on delivery timing, correlating with nursing shifts, to evaluate perinatal outcomes. The primary endpoint included adverse maternal outcomes such as emergency Cesarean section, anal sphincter injuries, blood product transfusions, and postpartum surgeries (laparotomy/laparoscopy). Secondary outcomes focused on neonatal health indicators, including low Apgar scores, ICU admissions, respiratory issues, extended hospital stays, and neurological complications. Results: 87,863 deliveries were available for analysis with equal distribution during the day. The risk of adverse composite maternal outcome was highest during the evening (aOR 1.25, 95% CI 1.18–1.32) and lowest during the night (aOR 0.94, 95% CI 0.88–0.99) compared to daytime deliveries. This difference was primarily driven by the highest rate of emergency CD in the evening. Neonatal outcomes were comparable, except for length of stay > 5 days, which was more frequent among newborns delivered during the evening and night shifts compared to the morning shift (aOR 1.19, 95% CI 1.07–1.33 and aOR 1.17, 95% CI 1.05–1.31, respectively). Conclusions: In term pregnancies, the evening shift is associated with the highest risk of adverse maternal and neonatal outcomes despite physician seniority.

The decision to postpone parenting has gained momentum in recent years, a shift driven by evolving social dynamics and improved access to fertility treatments. Despite their increasing prevalence, pregnancies at advanced maternal ages are associated with increased risks of adverse maternal and neonatal outcomes. This article addresses the association between advanced maternal age and hypertensive disorders of pregnancies (HDPs), which are more prevalent and a significant cause of maternal morbidity and mortality in this population. This review explores the biological mechanisms and age-related risk factors that underpin this increased susceptibility and offers practical management strategies that can be implemented prior to, as well as during, each stage of pregnancy to mitigate the incidence and severity of HDPs in this group. Lastly, this review acknowledges both the short-term and long-term postpartum implications of HDPs in women of advanced maternal age.

Objective: To determine and compare the safety and efficacy of different methods of induction of labor in twin gestations and their effect on maternal and neonatal outcomes. Methods: A retrospective observational cohort study was conducted at a single university-affiliated medical center. Patients with a twin gestation undergoing induction of labor at >32 + 0 weeks comprised the study group. Outcomes were compared to patients with a twin gestation at >32 + 0 weeks who went into labor spontaneously. The primary outcome was cesarean delivery. Secondary outcomes included operative vaginal delivery, postpartum hemorrhage, uterine rupture, 5 min APGAR < 7, and umbilical artery pH < 7.1. A subgroup analysis comparing outcomes for the induction of labor with oral prostaglandin E1 (PGE1), IV Oxytocin ± artificial rupture of membranes (AROM), and extra-amniotic balloon (EAB)+ IV Oxytocin was performed. Data were analyzed using Fisher’s exact test, ANOVA, and chi-square tests. Results: 268 patients who underwent induction of labor with a twin gestation comprised the study group. 450 patients with a twin gestation who went into labor spontaneously comprised the control group. There were no clinically significant differences between the groups for maternal age, gestational age, neonatal birthweight, birthweight discordancy, and non-vertex second twin. There were significantly more nulliparas in the study group compared to the control group (23.9% vs. 13.8% p < 0.001). The study group was significantly more likely to undergo a cesarean delivery of at least one twin (12.3% vs. 7.5% OR, 1.7 95% CI 1.04–2.85 p = 0.03). However, there was no significant difference in the rate of operative vaginal delivery (15.3% vs. 19.6% OR, 0.74, 95% CI 0.5–1.1 p = 0.16), PPH (5.2% vs. 6.9% OR, 0.75 95% CI 0.39–1.42 p = 0.37), 5-min APGAR scores < 7 (0% vs. 0.2% OR, 0.99 95%CI 0.99–1.00 p = 0.27), umbilical artery pH < 7.1 (1.5% vs. 1.3% OR, 1.12 95% CI 0.3–4.0), or combined adverse outcome (7.8% vs. 8.7% OR, 0.93 95% CI 0.6–1.4 p = 0.85). Furthermore, there were no significant differences in the rates of cesarean delivery or combined adverse outcomes in patients undergoing induction with oral PGE1 compared to IV Oxytocin ± AROM (13.3% vs. 12.5% OR, 1.1 95% CI 0.4–2.0 p = 1.0) (7% vs. 9.3% OR, 0.77 95% CI 0.5–3.5 p = 0.63 ) or EAB+ IV Oxytocin (13.3% vs. 6.9% OR, 2.1 95% CI 0.1–2.1 p = 0.53) (7% vs. 6.9% OR, 1.4 95% CI 0.15–3.5 p = 0.5) or between patients undergoing induction of labor with IV Oxytocin ± AROM and EAB+ IV Oxytocin (12.5% vs. 6.9% OR, 2.1 95% CI 0.1–2.4 p = 0.52) (9.3% vs. 6.9% OR, 0.98 95% CI 0.2–4.7 p = 0.54). There were no cases of uterine rupture in our study. Conclusions: Induction of labor in twin gestations is associated with a two-fold increased risk of cesarean delivery, although this is not associated with adverse maternal or neonatal outcomes. Furthermore, the method of induction of labor used does not affect the chances of success nor the rate of adverse maternal or neonatal outcomes.

Intrahepatic cholestasis of pregnancy (ICP) is characterized by elevated total bile acids (TBA). Although elevated maternal TBA is a major risk factors for fetal morbidity and mortality, it is unclear why some fetuses are more prone to the hazardous effect of bile acids (BA) over the others. It is unclear whether fetuses are protected by placental BA uptake, or it is the fetal BA metabolism that reduces fetal BA as compared to maternal levels. Therefore, we aimed to compared TBA levels in the umbilical vein and artery to maternal TBA in women with ICP. The study included 18 women who had TBA > 40 μmol/L and their 23 fetuses. We found that the TBA level in umbilical vein was significantly lower compared to maternal TBA level. The TBA levels in umbilical vein and umbilical artery were similar. No fetus had a serious neonatal complication. Importantly, since TBA level remains low even though maternal TBA level is high the fetuses are protected from the hazardous effects of maternal BA. Our findings suggest that there is no effective metabolism of BA in the fetus and the main decrease in TBA in the fetus is related to placental BA uptake.

Background and objectives: Accidental dural puncture (ADP) during epidural analgesia is a debilitating complication. Symptoms of ADP post-dural puncture headache (PDPH) are headache while rising from supine to upright position, nausea, and neck stiffness. While age, gender and needle characteristics are established risk factors for ADP, little is known about risk factors in laboring women. Methods: All cases of ADP during epidural analgesia treated with blood-patching during a 3-years period were retrospectively reviewed. Each case was matched to two controls according to delivery period. Results: Forty-nine cases of blood patches after ADP out 17 977 epidural anesthesia procedures were identified (0.27%). No differences were found between cases and controls with regards to body mass index, labor stage at time of epidural, length of second stage, location of epidural along the lumbar vertebrae, anesthesiologist’s experience or time when epidural was done. In cases of ADP, significantly lower doses of local anesthetics were injected (10.9 versus 13.5 cc, p < 0.001); anesthesiologists reported significantly more trials of epidurals (70 versus 2.8% more than one trial, p < 0.001), more patient movement during the procedure (13 versus 0%, p < 0.001), more intra-procedure suspicion of ADP (69 versus 0%, p < 0.001) and more cases where CSF/blood was drawn with the syringe (57 versus 2.4%, p < 0.001). Conclusion: ADP during labor is a rare but debilitating complication. Risk factors for this iatrogenic complication include patient movement and repeated epidural trials. Intra-procedure identification of ADP is common, allowing early intervention with blood patching where indicated.

Objective: To investigate prematurity rate in women aged ≥45 carrying a twin pregnancy. Other maternal and neonatal outcomes are also described. Design: Retrospective cohort study. Setting: Women delivering a twin pregnancy at a single tertiary medical center. Population: The study included all women aged 45 years and over carrying a twin pregnancy who delivered at 20 weeks gestation or beyond over a 9-year period from May 2000 to May 2009. Methods: Women aged 45 years and over were identified, all conceived by in vitro fertilization with ovum donation. The study group was compared to a control group of women Main outcome measure(s): Maternal complications during pregnancy and neonatal outcome. Results: During the study period 32 women ≥45 years delivered twins. The control group included 109 women. The rate of delivery before 37 weeks as well as before 32 weeks were very high in our study group (65% versus 40%, p = 0.01 and 15% versus 5.0%, p = 0.05, respectively). The rate of maternal life-threatening complications including blood product transfusion and maternal admission to the intensive care unit were also significantly higher in our study group compared to the control group (18% versus 2%, p = 0.018 and 6.3% versus none, p = 0.05). Conclusions: Women ≥45 years old with twin pregnancy carry a higher risk of maternal and perinatal complications.