To evaluate the role of maternal height in differentiating constitutionally small infants from pathologically growth-restricted infants who have not met their genetic growth potential by assessing risk of neonatal morbidity. Pregnancies complicated by fetal growth restriction (FGR) were identified within a large, NIH-funded database of pregnancies resulting in delivery of live, singleton, non-anomalous infants at a single center 2002-2013. Neonatal morbidity was defined as one or more of the following: 5-minute Apgar < 7, arterial cord pH < 7.0, sepsis, neonatal death, or need for respiratory support, chest compressions, phototherapy, exchange transfusion, or hypoglycemia treatment. Maternal heights were compared between infants who experienced neonatal morbidity and those who did not, using raw height and the ratio of maternal height to infant birth weight. Neonatal morbidity occurred in 174 of 575 eligible pregnancies (30%) and was associated with greater maternal height (160 vs 159cm, p = 0.03) and greater ratio of maternal height to infant birth weight (77 vs 66, p < 0.01) – an infant of a given birth weight was more likely to experience neonatal morbidity if delivered to a tall mother. Unadjusted odds ratio was 1.06 (95% confidence interval 1.04-1.08). Area under the received operating characteristic curve was 0.71 (Figure). This remained statistically significant after adjusting for umbilical artery Doppler findings, age, and insurance status (aOR 1.06, 95% CI 1.04-1.08, p < 0.01). There were no statistically significant differences in gestational age at delivery, ultrasound estimated fetal weight centile, or rates of diabetes, hypertension, renal disease, cardiac disease, smoking, or illicit substance use. Among pregnancies complicated by fetal growth restriction, neonatal morbidity occurred more frequently among infants delivered to taller mothers and in cases of a higher ratio of maternal height to infant birth weight. However, the effect size is modest and further study is needed.

INTRODUCTION:Chorionic villus sampling (CVS) remains essential for first-trimester genetic diagnosis, yet clinical volume may be insufficient to train new clinicians in the technique. Available simulation models are expensive, require animal parts or specialized resins, and cannot be stored for repeated use.METHODS:We present a model for trans-abdominal CVS (TA-CVS) which is constructed from readily available materials costing less than $10 and can be refrigerated and re-used to train maternal-fetal medicine fellows in CVS.RESULTS:All three attending physicians performing TA-CVS at our institution described the model as an accurate visual and tactile simulation, prompting its integration into our fellowship curriculum. To date, two senior fellows have achieved competency on the simulator and begun to perform clinical CVS under supervision, one of whom is an author on this paper. Both fellows and attendings indicated that the simulator provided a valuable tool for repeated practice prior to clinical CVS. Simulators are now maintained on the unit and have been re-used for 3 months and dozens of simulated procedures each without any apparent qualitative degradation in performance.DISCUSSION/CONCLUSION:We describe a low-cost easily constructed, durable, high-fidelity simulator for TA-CVS.

To develop and internally validate a predictive model for unplanned cesarean delivery (UCD) in pregnancies complicated by fetal growth restriction (FGR) using information available at the time of the decision to deliver.

Objective This study aimed to characterize the relationship between maternal obesity, fetal abdominal size, and neonatal morbidity in pregnancies complicated by fetal growth restriction (FGR). Study Design Pregnancies complicated by FGR, which resulted in delivery of a live, singleton, nonanomalous infant at a single center between 2002 and 2013 were identified in a large, National Institutes of Health–funded database of detailed pregnancy and delivery information extracted by trained research nurses. Pregnancies complicated by diabetes were excluded. Fetal biometry measurements from third trimester ultrasounds performed at the same institution were extracted from another institutional database. Pregnancies were divided into cohorts based on fetal abdominal circumference (AC) gestational age percentile (<10th centile, 10–29th centile, 30–49th centile, and ≥50th centile) at the ultrasound closes to the date of delivery. Obesity was defined by prepregnancy body mass index >30 kg/m2. The primary outcome was a composite of neonatal morbidity (CM) including 5-minute Apgar < 7, arterial cord pH <7.0, sepsis, respiratory support, chest compressions, phototherapy, exchange transfusion, hypoglycemia requiring treatment, or neonatal death. Outcomes were compared between women with versus without prepregnancy obesity overall and then stratified by AC cohort. Results A total of 379 pregnancies met criteria; CM occurred in 136 (36%). Overall, there was no difference in CM between infants born to women with versus without obesity (risk ratio (RR): 1.11, 95% confidence interval: 0.79–1.56). When stratified according to AC at ultrasound closest to delivery, there was higher prevalence of CM occurring among women with prepregnancy obesity than those without prepregnancy obesity when the fetal AC was >50th or 30 to 49th centile However, these differences did not reach statistical significance. Conclusion Our study identified no significant difference in risk of CM among growth-restricted infants of obese versus nonobese mothers, including among infants with very small AC. More research is needed to further examine the potential relationships postulated here. Key Points

To evaluate a novel ultrasound-based metric, the Fetal Abdominal Adiposity Score (FAAS), in comparison to standard fetal biometry measurements (estimated fetal weight [EFW] and abdominal circumference [AC] percentiles) for prediction of large for gestational age (LGA) newborns in patients with diabetes (DM) in pregnancy. Patients with gestational (GDM) or preexisting DM who underwent delivery of a live singleton non-anomalous fetus at a single tertiary care center between 2002 and 2013 were identified within a large, NIH-funded database of detailed pregnancy and delivery information extracted by trained research nurses. The FAAS was calculated as the biparietal diameter (BPD) minus fetal abdominal diameter (abdominal circumference/pi), normed to the gestational week for the last ultrasound prior to delivery for each patient. LGA was defined as a birth weight of ≥90th percentile for gestational age. The primary outcome was the ability of the calculated FAAS to predict LGA compared to EFW percentile and AC percentile. Predictive characteristics and the area under the receiver operating characteristic curve (AUC) were compared. Of the 1,051 eligible pregnancies evaluated, 192 (18.6%) resulted in an LGA newborn. The AUC was higher for EFW percentile (AUC 0.79 [95% CI 0.76-0.83]) vs the FAAS (AUC 0.65 [95% CI 0.60-0.69]) for prediction of LGA (p< 0.001) (Figure 1). Among 592 pregnancies for whom AC percentile was available, the AUC was highest for EFW percentile (AUC 0.80 [95% CI 0.76-0.84]) followed by AC percentile (AUC 0.75, [95% CI 0.70-0.79]), then FAAS (AUC 0.66 [95% CI 0.60-0.71]) for prediction of LGA (p< 0.001). Among pregnancies complicated by diabetes, the FAAS was less predictive of LGA infants compared with EFW percentile or AC percentile alone on third trimester ultrasound.

Despite advances in hemorrhage detection and management, postpartum hemorrhage remains the single leading cause of maternal death worldwide. Within the United States, hemorrhage is the leading cause of maternal death on the day of delivery and within the first week after delivery. Blood transfusion after hemorrhage represents a large proportion of severe maternal morbidity during and after delivery. Blood loss during delivery has historically been assessed visually by inspecting soiled pads, linens, and laparotomy sponges. These methods underestimate the volume of blood loss by as much as 40%, becoming increasingly inaccurate as blood loss increases. Young, healthy obstetrical patients compensate for blood loss via peripheral vasoconstriction, maintaining heart rate and blood pressure in a normal range until over 1 L of blood has been lost. A significant decrease in blood pressure along with marked tachycardia (>120 bpm) may not be seen until 30% to 40% of blood volume has been lost, or 2.0 to 2.6 L in a healthy term pregnant patient, after which the patient may rapidly decompensate. In resource-poor settings especially, the narrow window between the emergence of significant vital sign abnormalities and clinical decompensation may prove catastrophic. Once hemorrhage is detected, decisions regarding blood product transfusion are routinely made on the basis of inaccurate estimates of blood loss, placing patients at risk of underresuscitation (increasing the risk of hemorrhagic shock and end-organ damage) or overresuscitation (increasing the risk of transfusion reaction, fluid overload, and alloimmunization). We will review novel technologies that have emerged to assist both in the early and accurate detection of postpartum hemorrhage and in decisions regarding blood product transfusion.

Abstract Objectives During obstetric hemorrhage, peripheral vasoconstriction maintains heart rate and blood pressure until compensatory mechanisms are overwhelmed and patients deteriorate rapidly. Real-time perfusion measurements could quantify vasoconstriction, improving early recognition of hemorrhage and facilitating early intervention to reduce morbidity and mortality. The AccuFlow device makes rapid, non-invasive, quantitative measurements of perfusion, but has not been studied for hemorrhage detection or used in surgical settings. This study evaluated feasibility, tolerability, and preliminary efficacy of the AccuFlow for assessment of blood loss at cesarean delivery (CD). Methods In this pilot study, sensors were applied to the wrist, forearm, bicep, and chest wall of 25 patients undergoing scheduled CD. Postoperatively, sensors were removed and patients rated the AccuFlow and the standard anesthesia monitoring equipment on a validated comfort rating scale for wearable computers (CRS). Blood loss was estimated by the surgical team (EBL) and calculated from change in hematocrit, weight, and height (CBL). CRS scores were compared via Wilcoxon signed ranks tests. Coefficients of correlation between sensor readings and CBL, and between EBL and CBL, were compared using Fisher’s R-to-z transformation. Results There were no safety events; no participants requested device removal. CRS ratings of the AccuFlow and the standard monitoring equipment were similar (7.2 vs. 8.8, p=0.25). Change in wrist perfusion from delivery to dressing placement was more strongly correlated with CBL than was EBL (R=−0.48 vs. R=0.087, p=0.03). Conclusions The AccuFlow sensor is well-tolerated and shows promise in detecting intrapartum hemorrhage, though larger studies are needed.

To evaluate the relationship between fetal biparietal diameter (BPD) greater than 10 cm on prenatal ultrasound and likelihood of successful vaginal delivery. This was a secondary analysis of a retrospective cohort of pregnancies resulting in delivery of live singleton fetuses at a single tertiary-care hospital 2007-2019, from which mode of delivery and biometry measurements from ultrasounds performed at 28-42 weeks' gestation were available. Delivery outcomes of patients with fetal BPD >10cm in the third trimester were compared to those with BPD < 10cm. Generalized linear models were used to evaluate risk of vaginal delivery, adjusting for estimated fetal weight (EFW) percentile and gestational age at the time of ultrasound assessment. 17,402 pregnancies met inclusion criteria, of which 155 (0.89%) had a BPD >10.0 cm on ultrasound at 28-42 weeks and a known mode of delivery. Vaginal delivery occurred less often (33.93%) in pregnancies with a BPD >10.0 cm compared to those with BPD measurements < 10.0 cm (67.52%, p = < 0.01). However, after controlling for gestational age at ultrasound assessment and calculated EFW percentile, the relationship between vaginal delivery and BPD >10.0 cm was no longer statistically significant (RR 0.71 [95% CI 0.50-1.01], p=0.059). After adjusting for gestational age at ultrasound assessment and EFW percentile, Pregnancies with an increased fetal BPD >10 cm on third trimester ultrasound were as likely to achieve vaginal birth as those with a BPD < 10cm. This suggests that pregnancies with elevated fetal biparietal diameters should not be discouraged from attempting vaginal birth in absence of other contraindications to a trial of labor.

As the global burden of disease shifts from "diseases of poverty" such as diarrhea to "diseases of affluence" like diabetes and heart disease, a parallel shift is underway in maternal health. Maternal death from hemorrhage is decreasing, while deaths resulting from exacerbation of underlying chronic disease are on the rise.

BACKGROUND: Prediction models have shown promise in helping clinicians and patients engage in shared decision-making by providing quantitative estimates of individual risk of important clinical outcomes. Gestational diabetes mellitus is a common complication of pregnancy, which places patients at higher risk of primary CD. Suspected fetal macrosomia diagnosed on prenatal ultrasound is a well-known risk factor for primary CD in patients with gestational diabetes mellitus, but tools incorporating multiple risk factors to provide more accurate CD risk are lacking. Such tools could help facilitate shared decision-making and risk reduction by identifying patients with both high and low chances of intrapartum primary CD.OBJECTIVE: This study aimed to develop and internally validate a multi-variable model to estimate the risk of intrapartum primary CD in pregnancies complicated by gestational diabetes mellitus undergoing a trial of labor.STUDY DESIGN: This study identified a cohort of patients with gestational diabetes mellitus derived from a large, National Institutes of Health-funded medical record abstraction study who delivered singleton live-born infants at >= 34 weeks of gestation at a large tertiary care center between January 2002 and March 2013. The exclusion criteria included previous CD, contraindications to vaginal delivery, scheduled primary CD, and known fetal anomalies. Candidate predictors were clinical variables routinely available to a practitioner in the third trimester of pregnancy found to be associated with an increased risk of CD in gestational diabetes mellitus. Stepwise backward elimination was used to build the logistic regression model. The Hosmer-Lemeshow test was used to demonstrate goodness of fit. Model discrimination was evaluated via the concordance index and displayed as the area under the receiver operating characteristic curve. Internal model validation was performed with bootstrapping of the original dataset. Random resampling with replacement was performed for 1000 replications to assess predictive ability. An additional analysis was performed in which the population was stratified by parity to evaluate the model's predictive ability among nulliparous and multiparous individuals.RESULTS: Of the 3570 pregnancies meeting the study criteria, 987 (28%) had a primary CD. Of note, 8 variables were included in the final model, all significantly associated with CD. They included large for gestational age, polyhydramnios, older maternal age, early pregnancy body mass index, first hemoglobin A1C recorded in pregnancy, nulliparity, insulin treatment, and preeclampsia. Model calibration and discrimination were satisfactory with the Hosmer-Lemeshow test (P1/4.862) and an area under the receiver operating characteristic curve of 0.75 (95% confidence interval, 0.74-0.77). Internal validation demonstrated similar discriminatory ability. Stratification by parity demonstrated that the model worked well among both nulliparous and multiparous patients.CONCLUSION: Using information routinely available in the third trimester of pregnancy, a clinically pragmatic model can predict intra-partum primary CD risk with reasonable reliability in pregnancies complicated by gestational diabetes mellitus and may provide quantitative data to guide patients in understanding their individual primary CD risk based on preexisting and acquired risk factors.

Objective This study aimed to assess the positive predictive value (PPV) of a 1-hour, 50-g glucose challenge test (GCT) result >= 200 mg/dL for the diagnosis of gestational diabetes mellitus (GDM) on a 3-hour, 100-g glucose tolerance test (GTT). Study Design Pregnancies between 2008 and 2016 with a GCT result >= 200 mg/dL were identified retrospectively. GCT and GTT dates and results, demographics, and working due date (EDD) were extracted. Gestational age at testing was calculated from test date and EDD. As some clinicians presumptively diagnose GDM in such cases, if a GTT result was not available, clinic notes were reviewed to determine whether a GTT was ordered. Positive predictive values (PPV) were calculated at GCT cut-offs at and beyond 200 mg/dL. Subgroups were compared including early GCT (<16 weeks) versus routine GCT (24-28 weeks), GTT result normal versus GTT diagnostic of GDM, and GTT ordered versus GTT not ordered. Rates of use of medication for glycemic control were assessed among these groups. Results Of 236 pregnant women with a GCT result >= 200 mg/dL, 115 (48%) GTT was ordered for 115 (49%), whereas 123 (52%) were managed as presumed GDM. Of 100 (87%) who completed the test, 81 (81%) were diagnosed with GDM with a median intertest interval of 14 days. No statistically significant differences were found between groups stratified by GTT result. Use of rates of metformin, glyburide, and insulin were similar between those diagnosed with GDM by GTT and those diagnosed with GDM by GCT alone. Conclusion A GCT result of >= 200 mg/dL has a PPV of 81% for diagnosis of GDM by GTT in a contemporary U.S. population, with a median intertest interval of 14 days between GCT and GTT. However, those diagnosed by GCT alone were as likely as those diagnosed by GTT to require medication for glycemic control, including insulin, suggesting that requiring a GTT may result in underdiagnosis and delayed treatment of GDM.

has declined, although it is still significantly higher than national rates.In our study no statistical difference was noted in adolescent pregnancy rates or outcomes.Marijuana use starkly increased in this population.The full effects of the COVID-19 pandemic on pregnancy rates and birth outcomes are still unknown but this study suggests that the teenage birth rate in our population did not change.

INTRODUCTION: To compare the rate of Cesarean delivery in pregnancies complicated by large for gestational age (LGA) fetuses in non-Hispanic White (NHW) patients to patients who identified as non-White and/or Hispanic. METHODS: This secondary analysis of a large institutional review board-approved retrospective cohort study included deliveries of live singleton fetuses at a tertiary-care hospital from 2007-2019. Deliveries of LGA fetuses, defined by an estimated fetal weight at 90th percentile or greater for gestational age on third trimester ultrasound, were identified and maternal characteristics and mode of delivery extracted. The primary outcome was Cesarean delivery for any indication. RESULTS: Of 3,593 eligible patients, 1,314 self-identified as NHW and 1,913 as non-White and/or Hispanic. NHW patients were older, taller, more likely to have type 1 diabetes and/or commercial insurance, and less likely to have gestational diabetes (P<.01 for all). Rates of type 2 diabetes were similar between groups (P=0.41). Overall, 48.1% of LGA pregnancies delivered by Cesarean, with a higher rate of Cesarean among NHW patients (50.88% vs. 45.32%; relative risk [RR] 1.11; 95% CI, 1.05–1.18). This relationship persisted after adjusting for differences in maternal age (adjusted RR [aRR] 1.10; 95% CI, 1.03–1.17), height (aRR 1.16; 95% CI, 1.07–1.26), payor status (aRR 1.08; 95% CI, 1.003–1.16]), and prevalence of diabetes (aRR 1.13; 95% CI, 1.05–1.22]) between groups. CONCLUSION: Among LGA pregnancies, NHW patients were more likely to undergo Cesarean delivery than patients who identified as non-White and/or Hispanic. This stands in contrast to existing data showing that NHW patients are less likely to deliver by Cesarean overall.

To identify predictors of primary cesarean delivery (PCD) in patients with gestational diabetes mellitus (GDM) and to develop and validate a clinically relevant prediction model to assist in patient counseling. We studied a retrospective cohort of patients with GDM derived from a large, NIH funded medical record abstraction study who delivered singleton liveborn infants at ≥34 weeks' gestation at a large tertiary care center between January 2002 and March 2014. Exclusion criteria included prior cesarean delivery, contraindications to vaginal delivery, scheduled primary cesarean delivery, and known fetal anomalies. Candidate predictors were limited to clinical variables routinely available to a practitioner in the third trimester. Stepwise backward logistic regression was used to build the model. Hosmer-Lemeshow test was used to demonstrate goodness-of-fit. Model discrimination was evaluated via the concordance index and displayed via area under the receiver operator curve (AUC). Internal model validation was performed with bootstrapping of the original dataset. Random resampling with replacement was performed for 1000 replications to assess predictive ability. Of the 3,631 patients meeting study criteria, 1,011 (27.8%) had a primary cesarean delivery. Eight variables were significantly associated with cesarean delivery including macrosomia, polyhydramnios, advanced maternal age, early pregnancy BMI, hemoglobin A1C, nulliparity, lack of insulin treatment, and preeclampsia. Model calibration and discrimination were satisfactory with Hosmer-Lemeshow test of p=0.64 and an AUC of 0.76 (95% CI, 0.74 , 0.78). Internal validation demonstrated similar discriminatory ability. Using information available in the third trimester, a clinically pragmatic model can predict PCD risk with reasonable reliability in pregnancies complicated by GDM and may provide quantitative data to guide patients in understanding their individual PCD risk based on both GDM and preexisting risk factors.View Large Image Figure ViewerDownload Hi-res image Download (PPT)

To compare the risk of unplanned cesarean by abdominal circumference percentile ( < 10th, 10-19th, 30-49th, and ≥50th) in singleton pregnancies with fetal growth restriction (FGR). Patients with FGR, defined as estimated fetal weight (EFW) below the 10th percentile, who delivered a live, singleton fetus at a single tertiary care center between 2002 and 2013 were identified within a large, NIH-funded database containing detailed pregnancy, ultrasound, and delivery information extracted by trained research nurses. Unplanned cesarean was defined as cesarean for one of the following indications: arrest of dilation, arrest of descent, non-reassuring fetal heart rate status, bleeding, worsening preeclampsia. Cesarean was considered planned if the primary indication was any of the following: malpresentation, placenta previa, fetal anomaly, prior uterine surgery (including cesarean), or elective. All-cause cesarean included both planned and unplanned cesarean. Rates of unplanned cesarean were calculated as unplanned cesarean / (unplanned cesarean + vaginal delivery). These rates were calculated for the following groups stratified by fetal abdominal circumference percentile for gestational age: < 10th centile, 10-19th centile, 30-49th centile, and ≥50th centile). Unadjusted relative risk of unplanned cesarean section was calculated for each group with AC≥50th centile as the reference (Table). Of 408 eligible pregnancies, unplanned cesarean occurred in 69 pregnancies (16.9%), planned cesarean in 61 (15.0%), and vaginal delivery in 278 (68.1%). Higher rates of unplanned CD were identified among fetuses with AC < 10th centile compared to those with AC ≥50th centile (26% vs 11%, p< 0.05). There was no statistically significant relationship between abdominal circumference and all-cause cesarean (p=0.17). Among infants with fetal growth restriction, fetal abdominal circumference < 10th centile is associated with an increased risk of unplanned cesarean section.

Mass drug administration (MDA) programs are a critical component of efforts to treat and eliminate trachoma, a leading cause of blindness worldwide. Despite the importance of these programs for individual and community health, pregnant and breastfeeding women have historically been excluded from treatment in these programs. Countries with active MDA programs also tend to have high fertility rates, and thus women may be left untreated for years at a time. Not only do these women suffer from the symptoms of disease (pain and eventual blindness), but also failure to include the entire population in drug administration programs leaves pockets of infection in the community, risking outright failure of eradication efforts. The medication used most commonly, azithromycin, appears to be safe for use in pregnancy and breastfeeding. The time has come to include pregnant and breastfeeding women in MDA programs, not just for them, but also for their communities.

INTRODUCTION: We aimed to characterize the relationship between fetal abdominal circumference and neonatal morbidity in pregnancies complicated by diabetes. METHODS: After institutional review board approval, patients with gestational diabetes (GDM) or preexisting diabetes type 1 or type 2 (T1DM, T2DM) who delivered a live, singleton, non-anomalous infant at a single center 2002–2013 were identified within a large, National Institutes of Health-funded database of detailed pregnancy and delivery information extracted by trained research nurses. Neonatal morbidity (NM) was defined as one or more of the following: 5-minute Apgar <7, arterial cord pH <7.0, sepsis, neonatal death, or need for respiratory support, chest compressions, phototherapy, exchange transfusion, or hypoglycemia treatment. Rates of morbidity were calculated for the following groups stratified by fetal abdominal circumference (AC) percentile for gestational age: below the 20th percentile, 20th–39th percentile, 40th–59th percentile, 60th–79th percentile, and 80th percentile or greater. Unadjusted relative risk (RR) of neonatal morbidity was calculated for each group, with AC 40th–59th percentile as the reference. RESULTS: A total of 721 eligible pregnancies were identified (643 GDM, 35 T1DM, 43 T2DM). Neonatal morbidity occurred in 261 (36%). The lowest rate of neonatal morbidity (22%) occurred in pregnancies with a fetal AC below the 20th percentile (RR, 0.55; 95% CI, 0.31–0.98). The highest rate of neonatal morbidity (42%) occurred in those with an AC at or above the 80th percentile, but this was not a statistically significant increase in risk compared to the reference group (RR, 1.05; 95% CI, 0.82–1.33). CONCLUSION: Among pregnancies complicated by diabetes, fetal abdominal circumference below the 20th percentile was associated with decreased risk of neonatal morbidity.

To develop and internally validate a predictive model for neonatal morbidity (NM) in pregnancies complicated by diabetes mellitus (DM) using information available prior to delivery, to aid in decisions regarding site of delivery. Patients with gestational (GDM) or preexisting DM who delivered a live, singleton, non-anomalous infant at a single center between 2002 and 2013 were identified within a large, NIH-funded database of detailed pregnancy and delivery information extracted by trained research nurses. Candidate predictors were determined from the literature. Neonatal morbidity (NM) was defined as one or more of the following: 5-minute Apgar < 5, arterial cord pH < 7.0, sepsis, neonatal death, or need for any of the following: respiratory support, chest compressions, phototherapy, exchange transfusion, hypoglycemia treatment. Forward selection with p = 0.20 was used to add candidate predictors. Internal validation was performed via bootstrapping, with Hosmer-Lemeshow testing for goodness-of-fit. 1299 pregnancies were included (1142 GDM, 57 type 1 DM, 66 type 2 DM, 34 unknown type). NM occurred in 424 (32.6%). The final model included 9 predictors. Higher risk of NM was seen in primigravidas, deliveries at an earlier gestational age, prelabor cesarean or labor induction (vs admission in spontaneous labor), chronic hypertension, new onset hypertension after 20 weeks' gestation, need for medication for glycemic control, type 1 diabetes, and non-reassuring fetal testing as the indication for delivery. The area under the curve (AUC) was 0.70 (95% CI 0.67-0.73). Bootstrapping yielded AUC 0.72 (0.67-0.75). Hosmer-Lemeshow test yielded p=0.45. 92% of pregnancies with a predicted NM risk ≥80% experienced NM (likelihood ratio 22.45, 2.92-173.2) vs. 19% of pregnancies with a predicted NM risk < 25% (likelihood ratio 0.50, 0.40-0.58). After further validation, this model may help identify pregnancies at particularly high risk of neonatal morbidity, aiding in decisions regarding site of delivery and need for antepartum maternal transfer.