Optimal parity cut-off values for predicting postpartum hemorrhage in vaginal deliveries and cesarean sections

Prediction of postpartum hemorrhage using traditional statistical analysis and a machine learning approach

BACKGROUND

Early detection of postpartum hemorrhage risk factors by healthcare providers during pregnancy and the postpartum period may allow healthcare providers to act to prevent it. Developing a prediction model that incorporates several risk factors and accurately calculates the overall risk for postpartum hemorrhage is necessary.

OBJECTIVE

This study used a traditional analytical approach and a machine learning model to predict postpartum hemorrhage.

STUDY DESIGN

Women who gave birth at the Khaleej-e-Fars Hospital in Bandar Abbas, Iran, were evaluated retrospectively between January 1, 2020, and January 1, 2022. These pregnant women were divided into 2 groups, namely those who had postpartum hemorrhage and those who did not. We used 2 approaches for the analysis. At the first level, we used the traditional analysis methods. Demographic factors, maternal comorbidities, and obstetrical factors were compared between the 2 groups. A bivariate logistic regression analysis of the risk factors for postpartum hemorrhage was done to estimate the crude odds ratios and their 95% confidence intervals. In the second level, we used machine learning approaches to predict postpartum hemorrhage.

RESULTS

Of the 8888 deliveries, we identified 163 women with recorded postpartum hemorrhage, giving a frequency of 1.8%. According to a traditional analysis, factors associated with an increased risk for postpartum hemorrhage in a bivariate logistic regression analysis were living in a rural area (odds ratio, 1.41; 95% confidence interval, 1.08-1.98); primiparity (odds ratio, 3.16; 95% confidence interval, 1.90-4.75); mild to moderate anemia (odds ratio, 5.94; 95% confidence interval 2.81-8.34); severe anemia (odds ratio, 6.01; 95% confidence interval 3.89-11.09); abnormal placentation (odds ratio, 7.66; 95% confidence interval, 2.81-17.34); fetal macrosomia (odds ratio, 8.14; 95% confidence interval, 1.02-14.47); shoulder dystocia (odds ratio, 7.88; 95% confidence interval, 1.07-13.99); vacuum delivery (odds ratio, 2.01; 95% confidence interval, 1.15-5.98); cesarean delivery (odds ratio, 1.86; 95% confidence interval, 1.12-3.79); and general anesthesia during cesarean delivery (odds ratio, 7.66; 95 % confidence interval, 3.11-9.36). According to machine learning analysis, the top 5 algorithms were XGBoost regression (area under the receiver operating characteristic curve of 99%), XGBoost classification (area under the receiver operating characteristic curve of 98%), LightGBM (area under the receiver operating characteristic curve of 94%), random forest regression (area under the receiver operating characteristic curve of 86%), and linear regression (area under the receiver operating characteristic curve of 78%). However, after considering all performance parameters, the XGBoost classification was found to be the best model to predict postpartum hemorrhage. The importance of the variables in the linear regression model, similar to traditional analysis methods, revealed that macrosomia, general anesthesia, anemia, shoulder dystocia, and abnormal placentation were considered to be weighted factors, whereas XGBoost classification considered living residency, parity, cesarean delivery, education, and induced labor to be weighted factors.

CONCLUSION

Risk factors for postpartum hemorrhage can be identified using traditional statistical analysis and a machine learning model. Machine learning models were a credible approach for improving postpartum hemorrhage prediction with high accuracy. More research should be conducted to analyze appropriate variables and prepare big data to determine the best model.

Comparison of Fetomaternal Complications in Women of High Parity with Women of Low Parity among Saudi Women

High parity is associated with the risk of fetomaternal complications such as gestational diabetes mellitus, hypertensive disorders, maternal anemia, preterm labor, miscarriage, postpartum hemorrhage, and perinatal and preterm mortality. The objective of the study was to compare fetomaternal complications in women of high parity with women of low parity. This involved a cohort study on a sample size of 500 women who had singleton births. Data were collected from the Maternity and Child Hospital, Ha’il, Kingdom of Saudi Arabia. Participants were classified into two groups according to parity, i.e., women of low parity and women of high parity. Socio-demographic data and pregnancy complications, such as gestational diabetes, hypertension, preeclampsia, intrauterine growth restriction, etc., were retrieved from participants’ files. Participants were followed in the postnatal ward until their discharge. The results revealed that women of high parity mostly (49%) were married before 20 years of age, less educated, obese, and were of un-booked cases. Premature babies and fetal mortality are significantly high (0.000) in this group. There is a significant difference between the two groups with respect to maternal anemia, gestational diabetes mellitus, joint pain, perineal tear, miscarriage, postpartum hemorrhage, preeclampsia, vaginal tear, and cesarean section. Determinants responsible for high parity should be identified via evidence-based medicine. Public health education programs targeting couples, weight control, nutrition, and contraception would be a cost-effective strategy for reducing the risk of possible fetomaternal complications.

Disparities in Adverse Maternal Outcomes Among Five Race and Ethnicity Groups

Background: Racial/ethnic disparities are evident in adverse maternal health outcomes, but they are shifting due to interventions, initiatives, changing demographics, and the prevalence of preexisting conditions. This study examined the current racial/ethnic disparities in adverse maternal outcomes. Materials and Methods: In a cross-sectional study, the International Classification of Diseases-10 codes for the principal diagnosis and secondary diagnoses were retrieved from the National Inpatient Sample database (2016-2018). A weighted multiple logistic regression model assessed disparities in seven adverse maternal outcomes, including preterm labor, gestational hypertension (GHTN) and diabetes, premature rupture of membranes (PRM), infection of the amniotic cavity (INFAC), placental abruption, and postpartum hemorrhage (PPH). A weighted linear regression model assessed disparities in a composite variable of maternal outcomes. A maternal-specific comorbidity index assessed risk adjustment, and other clinical, sociodemographic, and hospital factors were considered. Results: A total of 2,211,345 pregnancies were included. Preterm labor, GHTN, and placental abruption had the highest raw rate among Black women compared to all races. After adjusting for control variables in the regression analysis, these adverse outcomes also showed the highest odds ratio (OR) among Black women compared to White women (the reference group). Gestational diabetes, PRM, and INFAC had the highest raw rate among Asians/Pacific Islanders (PIs). After adjusting for control variables, these adverse outcomes also showed the highest OR among Asians/PIs compared to White women. The OR for PPH was the highest for Native Americans compared to White women. Furthermore, results of the composite outcome variable indicated that all minority groups experienced the overall poorer maternal outcome than White women. Conclusions: Overall, all four minority women had higher raw rates and also odds of experiencing the studied adverse outcomes than White women. Existing efforts should be strengthened to continue reducing racial/ethnic disparities in adverse maternal outcomes.

Type of occupation and early antenatal care visit among women in sub-Saharan Africa

Background

Type of occupation has been linked to early antenatal care visits whereby women in different occupation categories tend to have different timing for antenatal care visits. Different occupations require varying levels of commitment, remuneration and energy requirements. This study, therefore, sought to investigate the association between the type of occupation and early antenatal care visits in sub-Saharan Africa.

Methods

This is a secondary analysis of Demographic and Health Survey data from 29 countries in sub-Saharan Africa conducted between 2010 and 2018. The study included 131,912 working women. We employed binary logistic regression models to assess the association between type of occupation and timely initiation of antenatal care visits.

Results

The overall prevalence of early initiation of antenatal care visits was 39.9%. Early antenatal care visit was high in Liberia (70.1%) but low in DR Congo (18.6%). We noted that compared to managerial workers, women in all other work categories had lower odds of early antenatal care visit and this was prominent among agricultural workers [aOR = 0.74, CI = 0.69, 0.79]. Women from Liberia [aOR = 3.14, CI = 2.84, 3.48] and Senegal [aOR = 2.55, CI = 2.31, 2.81] had higher tendency of early antenatal care visits compared with those from Angola.

Conclusion

The findings bring to bear some essential elements worth considering to enhance early antenatal care visits within sub-Saharan Africa irrespective of the type of occupation. Women in the agricultural industry need much attention in order to bridge the early antenatal care visit gap between them and workers of other sectors. A critical review of the maternal health service delivery in DR Congo is needed considering the low rate of early antenatal care visits.