Twin Growth Discordance and Risk of Postpartum Hemorrhage: A Retrospective Cohort Study

Artificial Intelligence in Predicting Postpartum Hemorrhage in Twin Pregnancies Undergoing Cesarean Section

This study aimed to create a risk prediction model with artificial intelligence (AI) to identify patients at higher risk of postpartum hemorrhage using perinatal characteristics that may be associated with later postpartum hemorrhage (PPH) in twin pregnancies that underwent cesarean section. The study was planned as a retrospective cohort study at University Hospital. All twin cesarean deliveries were categorized into two groups: those with and without PPH. Using the perinatal characteristics of the cases, four different machine learning classifiers were created: Logistic regression (LR), support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP). LR, RF, and SVM models were created a second time by including class weights to manage the underlying imbalances in the data. A total of 615 twin pregnancies were included in the study. There were 150 twin pregnancies with PPH and 465 without PPH. Dichorionity, PAS, and placenta previa were significantly higher in the PPH-positive group (p = .045, p = .004, p = .001 respectively). In our model, LR with class weight was the best model with the highest negative predictive value. The AUC in our LR with class weight model was %75.12 with an accuracy of 70.73%, a PPV of 47.92%, and an NPV of 85.33% in our data. Although the application of machine learning to create predictive models using clinical risk factors and our model's 70% accuracy rate are encouraging, it is not sufficient. Machine learning modeling needs further study and validation before being incorporated into clinical use.

Twin pregnancy and postpartum haemorrhage: a systematic review and meta-analysis

BACKGROUND

Postpartum haemorrhage (PPH) continues to stand as the primary cause of maternal morbidity and mortality post-delivery, with twin pregnancies carrying a heightened risk of PPH compared to singleton deliveries.

OBJECTIVES

To investigate the incidence of primary PPH among twin pregnancies and report on maternal and peripartum characteristics within this population.

METHODS

A literature search was conducted using data from PubMed, EMBASE, Cochrane, Scopus, and Web of Science. The search aimed to identify studies concerning mothers with twin pregnancies and postpartum haemorrhage (PPH) from the inception of each respective database to June 8th, 2023. Pooled means and proportions were analyzed using the generic inverse variance method. This review was registered prospectively with PROSPERO (CRD42023427192).

RESULTS

A total of 21 studies involving 23,330 twin pregnant patients were included. Incidence of PPH for vaginal delivery and Caesarean delivery (CS) was found to be 10.9% (95% CI: -0.017, 0.235, I2 = 96%) and 27.0% (95% CI: 0.180, 0.359, I2 = 99%) respectively. In vitro fertilization (IVF) was the most common conception method at 62.0% (95% CI: 0.448, 0.792, I2 = 100%) with 81.1% (95% CI: 0.708, 0.915, I2 = 100%) of twins being dichorionic diamniotic.

CONCLUSION

This meta-analysis demonstrated more than one in ten vaginal deliveries and over one in four cesarean sections result in PPH for twin pregnancies. IVF is the predominant method of conception in this patient group and seems to contribute to subsequent PPH risk in specific mothers. While preliminary, these findings underscore the necessity for further well-designed and high-quality studies to validate these results.

Risk Factors for Postpartum Hemorrhage in Severe Pre-Eclampsia: A Retrospective Single-Centre Study of 1953 Cases

BACKGROUND Severe pre-eclampsia (sPE) and postpartum hemorrhage (PPH) in pregnancy have serious impact on maternal and fetal health and life. Co-occurrence of sPE and PPH often leads to poor pregnancy outcomes. We explored risk factors associated with PPH in women with sPE. MATERIAL AND METHODS This retrospective study included 1953 women with sPE who delivered at the Women's Hospital of Nanjing Medical University between April 2015 and April 2023. Risk factors for developing PPH in sPE were analyzed, and subgroups were analyzed by delivery mode (cesarean and vaginal). RESULTS A total of 197 women with PPH and 1756 women without PPH were included. Binary logistic regression results showed twin pregnancy (P<0.001), placenta accreta spectrum disorders (P=0.045), and placenta previa (P<0.001) were independent risk factors for PPH in women with sPE. Subgroup analysis showed risk factors for PPH in cesarean delivery group were the same as in the total population, but vaginal delivery did not reduce risk of PPH. Spinal anesthesia reduced risk of PPH relative to general anesthesia (P=0.034). Vaginal delivery group had no independent risk factors for PPH; however, magnesium sulfate (P=0.041) reduced PPH incidence. CONCLUSIONS Women with twin pregnancy, placenta accreta spectrum disorders, placenta previa, and assisted reproduction with sPE should be alerted to the risk of PPH, and spinal anesthesia should be preferred in cesarean delivery. Magnesium sulfate should be used aggressively in women with sPE; however, the relationship between magnesium sulfate and PPH risk needs further investigation.