Objectives: To improve PPH prediction and to compare machine learning and traditional statistical methods. Design: Cross-sectional Setting: Deliveries across US hospitals Population: Deliveries across 12 US hospitals from the 2002-2008 Consortium for Safe Labor dataset Method: We developed models using the Consortium for Safe Labor dataset. Fifty antepartum and intrapartum characteristics and hospital characteristics were included. Logistic regression, support vector machines, multi-layer perceptron, random forest, and gradient boosting were used to generate prediction models. Receiver operating characteristic area under the curve (ROC-AUC) and precision/recall area under the curve (PR-AUC) were used to compare performance. Main Outcome Measure: The primary outcome was transfusion of blood products or PPH (estimated blood loss ≥1,000mL). The secondary outcome was transfusion of any blood products. Results: Among 228,438 births, 5,760 women (3.1%) had a postpartum hemorrhage, 5,170 women (2.8%) had a transfusion, and 10,344 women (5.6%) met criteria for the transfusion-PPH composite. Models predicting transfusion-PPH composite using antepartum and intrapartum features had the best positive predictive values with the gradient boosting machine learning model performing best overall (ROC-AUC=0.833, 95% CI [0.828-0.838]; PR-AUC=0.210 95% CI [0.201-0.220]). The most predictive features in the gradient boosting model predicting transfusion-PPH composite were mode of delivery, oxytocin incremental dose for labor(mU/min), intrapartum tocolytic use, presence of anesthesia nurse, and hospital type. Conclusion: Machine learning offers higher discrimination than logistic regression in predicting PPH. The CSL dataset may not be optimal for analyzing risk due to strong subgroup effects, which decreases accuracy and limits generalizability.

There is paucity of evidence to support clinical decision making and counseling related to medication use in pregnancy. Despite multiple efforts from legislative bodies and advocacy groups, the inclusion of pregnant women in clinical drug trials assessing efficacy and safety remains scarce. Pregnancy can be complicated by multiple co-morbidities that require pharmacological intervention; these interventions primarily target the pregnant women but also sometimes have secondary effects for the fetus. The U.S. Food and Drug Administration has issued multiple guidance documents on incorporating pregnant women in clinical trials to aid pharmaceutical companies in designing a protocol to ensure safety and adherence to ethical standards. Advances in pediatric pharmacology studies provide lessons for researchers on the best practice of designing clinical trials with inclusion of patients from special populations. In this review, we present the status of pregnant women in clinical trials, highlighting the ethical stigma and possible future directives.

Objectives: To estimate the cost-effectiveness of alternative risk-dictated strategies utilizing prophylactic tranexamic acid (TXA) for the prevention of postpartum hemorrhage (PPH).Study Design: We constructed a microsimulation-based Markov decision-analytic model estimating the cost-effectiveness of three alternative risk-dictated strategies for TXA prophylaxis versus the status quo (no TXA) in a cohort of 3.8 million pregnant women delivering in the United States. Each strategy differentially modified risk-specific hemorrhage probabilities by preliminary estimates of TXA’s prophylactic efficacy. Outcome measures included incremental costs, quality-adjusted life-years (QALYs), and adverse maternal outcomes averted. Costs and benefits were considered from the healthcare system and societal perspectives over a lifetime time horizon.   Results: All TXA strategies were dominant versus the status quo, implying that they were more effective while also being cost-saving. Providing TXA to all delivering women irrespective of hemorrhage risk produced the most favorable results overall, with estimated cost savings greater than $670 million and up to 149,505 PPH cases, 2,933 hysterectomies, and 70 maternal deaths averted, per annual cohort. Threshold analysis suggested that TXA is likely to be cost-saving for health systems at costs below $184 per gram.   Conclusions: Our findings suggest that routine prophylaxis with TXA would likely result in substantial cost-savings and reductions in adverse maternal outcomes in this context. The integrity of this conclusion is maintained across all risk-dictated strategies, even when the cost of TXA is significantly higher than what is supported in the literature.