Wyatt, Michelle A.

Abstract Objective To develop a comprehensive risk stratification model to identify patients at high risk of cesarean surgical site infection (cSSI) based on information available at the time of hospital discharge. Methods This is a retrospective cohort study based on datasets from two independent level IV academic medical centers to improve generalizability. The first study includes 2336 cesarean deliveries for analysis with 109 instances of cSSI (4.7%). The second study includes 2936 cesarean deliveries with 72 instances of cSSI (2.5%). The first study cohort was utilized for both model training and internal validation, using the 15 shared features present in both datasets. Random search with cross‐validation was used to choose the type of machine learning (ML) model and its hyperparameters, with area under the receiver operating characteristic curve (AUC) as the validation metric. The second study cohort was then used to evaluate testing accuracy (external validation) and generalization capability of this model. The predictive importance of each feature was evaluated using permutation importance applied to the second cohort. Risk stratification cutoff scores were defined based on centiles over the first patient cohort and evaluated on the second cohort. Results The ML model with the highest validation AUC was an XGBoost classifier. This trained model achieved an AUC of 0.78 on the training data and a 0.72 cross‐validated AUC. When tested on data from the second study cohort, it achieved an AUC of 0.69. The features showing the strongest predictive generalization, as measured by permutation importance, were length of hospital stay, primary indication for cesarean delivery, and estimated blood loss. Using the second cohort to test our model, the model shows a 22.7% positive predictive value (PPV) of cSSI among women in the highest risk group, and a 0.8% PPV among women in the bottom risk group, compared with 2.5% cSSI incidence for the study population at large. Conclusion We developed and validated a predictive ML model for cSSI with information available to healthcare professionals at the time of hospital discharge. This model suggests that the most predictive risk factors for cSSI include length of hospital stay, primary indication for cesarean delivery, and estimated blood loss. Additionally, the model provides reasonable risk stratifications for individual patients. This tool may be used for identifying subgroups at higher risk of cSSI and identifying those who may require closer surveillance or clinical intervention.

Pregnancy loss affects approximately 20% of couples. The lack of a clear cause complicates half of all miscarriages. Early evidence indicates the maternal immune system and angiogenesis regulation are both key players in implantation success or failure. Therefore, this prospective study recruited women in the first trimester with known viable intrauterine pregnancy and measured blood levels of immune tolerance proteins galectin-9 (Gal-9) and interleukin (IL)-4, and angiogenesis proteins (vascular endothelial growth factors (VEGF) A, C, and D) between 5 and 9 weeks gestation. Plasma concentrations were compared between groups defined based on (a) pregnancy outcome and (b) maternal history of miscarriage, respectively. In total, 56 women were recruited with 10 experiencing a miscarriage or pregnancy loss in the 2nd or 3rd trimester and 11 having a maternal history or miscarriage. VEGF-C was significantly lower among women with a miscarriage or pregnancy loss. Gal-9 and VEGF-A concentrations were decreased in women with a prior miscarriage. Identification of early changes in maternal immune and angiogenic factors during pregnancy may be a tool to improve patient counseling on pregnancy loss risk and future interventions to reduce miscarriage in a subset of women.

Objective The objective of this study was to evaluate length of induction and postdelivery complications before and after implementation of a standardized approach to second-trimester medical termination of pregnancy. Study Design This was a retrospective cohort study of all women undergoing medical termination of pregnancy between 130/7 and 266/7 weeks of gestation at a single, academic institution from July 1, 2012, through June 30, 2015. The primary outcome was the time from the start of induction of labor to delivery of the fetus. Postdelivery complications including the need for dilation and curettage (D&C), blood transfusion, and readmission to the hospital were secondary outcomes of interest. Results A total of 62 women met inclusion criteria; 38 before and 24 after the intervention. There were no differences in measured baseline characteristics (p > 0.05). There was a significant decrease in induction time after the intervention (12.3 compared with 8.6 hours, p = 0.031). There was no significant difference in rates of D&C or other measured complications (p > 0.05). Conclusion Implementation of a standardized clinical guideline for second-trimester medical termination was associated with a decrease in length of induction. There was no significant difference in need for D&C or postdelivery complications; however, we were underpowered for these secondary outcomes.