Predicting peripartum blood transfusion: focusing on pre-pregnancy characteristics

Development of a machine learning approach for prediction of red blood cell transfusion in patients undergoing Cesarean section at a single institution

Despite recent advances in surgical techniques and perinatal management in obstetrics for reducing intraoperative bleeding, blood transfusion may occur during a cesarean section (CS). This study aims to identify machine learning models with an optimal diagnostic performance for intraoperative transfusion prediction in parturients undergoing a CS. Additionally, to address model performance degradation due to data imbalance, this study further investigated the variation in predictive model performance depending on the ratio of event to non-event data (1:1, 1:2, 1:3, and 1:4 model datasets and raw data).The area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) were evaluated to compare the predictive accuracy of different machine learning algorithms, including XGBoost, K-nearest neighbor, decision tree, support vector machine, multilayer perceptron, logistic regression, random forest, and deep neural network. We compared the predictive performance of eight prediction algorithms that were applied to five types of datasets. The intraoperative transfusion in maternal CS was 7.2% (1020/14,254). XGBoost showed the highest AUROC (0.8257) and AUPRC (0.4825) among the models. The most significant predictors for transfusion in maternal CS as per machine learning models were placenta previa totalis, haemoglobin, placenta previa partialis, and platelets. In all eight prediction algorithms, the change in predictive performance based on the AUROC and AUPRC according to the resampling ratio was insignificant. The XGBoost algorithm exhibited optimal performance for predicting intraoperative transfusion. Data balancing techniques employed to alter the event data composition ratio of the training data failed to improve the performance of the prediction model.

Endometriosis, pregnancy and delivery complications: Evidence from the US nationwide inpatient sample 2005-2018

OBJECTIVE

Endometriosis is associated with higher risk of ectopic pregnancy, premature delivery, miscarriage, and other adverse maternal and fetal complications. This study aimed to assess the impact of endometriosis on maternal and fetal outcomes of singleton pregnancies in a large nationally representative database.

MATERIALS AND METHODS

This population-based, retrospective observational study extracted the data of women aged 20-49 years with singleton, spontaneously conceived pregnancies from the US Nationwide Inpatient Sample (NIS) database from 2005 to 2018. Included subjects were divided into those with ICD codes for endometriosis and those without (non-endometriosis group). Data of maternal and fetal outcomes were compared between groups and analyzed using regression analysis.

RESULTS

After excluding 17,124 women who conceived with assisted reproductive technology (ART), 162,155 women with multiple pregnancies, and 27,847 with abnormal trend weight values (TRENDWT), a total of 8,584,269 women were eligible. After propensity score matching (PMS) case-control 1:4 by age, 45,560 remained (9112 (0.1%) with endometriosis, 36,448 without) and were included in the analysis. The mean age of women before matching was 28.7 years, and 30.5 years after matching. The most common comorbidity was chronic pulmonary disease (3.6%). Smoking frequency was higher in women with endometriosis compared to those without (4.8% vs. 2.4%). Multivariable analysis adjusted for confounders revealed that endometriosis was associated with significantly higher risk of maternal complications, including pre-eclampsia and eclampsia, antepartum hemorrhage, placenta previa, Cesarean delivery, post-partum hemorrhage, disseminated intravascular coagulation (DIC), transfusion, hemoperitoneum, and hospital stays ≥6 days. For fetal outcomes, endometriosis was associated with higher risk of intrauterine growth restriction (IUGR), premature birth, birth defects and abortion.

CONCLUSION

Endometriosis during pregnancy is associated with maternal and fetal complications. Study findings may serve as a benchmark for expanding medical assistance for endometriosis-affected pregnant women.

Risk of recurrent red-cell transfusion in delivery: A nationwide longitudinal study

OBJECTIVE

To investigate the risk of recurrent maternal red-cell transfusion in delivery.

DESIGN

Nationwide long-standing retrospective cohort study.

SETTING

Swedish medical birth register.

POPULATION

All registered births from 2000 to 2017 in Sweden.

METHODS

We included all women with between one and three consecutive registered births from 22 weeks of gestation onwards and all maternal red-cell transfusions in the peripartum period within the defined period of study. Information on gestational and non-gestational comorbidity was collected and we identified any female siblings. In our analyses we compared the risk of red-cell transfusion in delivery in relation to transfusion history and gestational and non-gestational comorbidity.

MAIN OUTCOME MEASURES

Maternal peripartum red-cell transfusion, defined as a recorded transfusion in the period from 1 day before and 7 days after delivery.

RESULTS

We included 825 451 women with a total 1 419 909 deliveries, including 786 097 (55.4%) first, 511 398 (36.0%) second and 122 414 (8.6%) third deliveries. Of women with previous obestric transfusion, 8.7% were transfused in a second delivery, compared with 1.7% of women without transfusion or diagnosis of haemorrhage. A previous diagnosis of haemorrhage did not affect the odds ratio of transfusion recurrence. Among women who were transfused in their first two deliveries, 15.5% were transfused in third delivery, corresponding to an 11-fold increase, compared with non-transfused women (adjusted odds ratio aOR 11.5, 95% CI 7.9-16.6). Women with a sister transfused in delivery were at increased risk of transfusion in a second delivery (aOR 1.8, 95% CI 1.6-2.1).

CONCLUSIONS

Women with previous red-cell transfusion are at an increased risk of red-cell transfusion in a subsequent delivery, compared with women without a history of red-cell transfusion.

Association between visceral obesity and tumor recurrence in hepatocellular carcinoma recipients undergoing liver transplantation

BACKGROUND

Excessive visceral obesity in recipients of living donor liver transplantation (LDLT) is associated with mortality, and a recent study reported the correlation between visceral adiposity of male LDLT recipients and hepatocellular carcinoma (HCC) recurrence. However, there is no study on the relationship between the donor's visceral adiposity and surgical outcomes in LDLT recipients. We investigated the association of the visceral-to-subcutaneous fat area ratio (VSR) in donors and recipients with HCC recurrence and mortality in LDLT.

METHODS

We analyzed 1386 sets of donors and recipients who underwent LDLT between January 2008 and January 2018. The maximal chi-square method was used to determine the optimal cutoff values for VSR for predicting overall HCC recurrence and mortality. Cox regression analyses were performed to evaluate the association of donor VSR and recipient VSR with overall HCC recurrence and mortality in recipients.

RESULTS

The cutoff values of VSR was determined as 0.73 in males and 0.31 in females. High donor VSR was significantly associated with overall HCC recurrence (adjusted hazard ratio [HR]: 1.43, 95% confidence interval [CI]: 1.06-1.93, p = 0.019) and mortality (HR: 1.35, 95% CI: 1.03-1.76, p = 0.030). High recipient VSR was significantly associated with overall HCC recurrence (HR: 1.40, 95% CI: 1.04-1.88, p = 0.027) and mortality (HR: 1.50, 95% CI: 1.14-1.96, p = 0.003).

CONCLUSIONS

Both recipient VSR and donor VSR were significant risk factors for HCC recurrence and mortality in LDLT recipients. Preoperative donor VSR and recipient VSR may be strong predictors of the surgical outcomes of LDLT recipients with HCC.

Patient blood management to minimize transfusions during the postpartum period

Patient blood management is an evidence-based concept that seeks to minimize blood loss by maintaining adequate hemoglobin levels and optimizing hemostasis during surgery. Since the coronavirus disease 2019 pandemic, patient blood management has gained significance due to fewer blood donations and reduced amounts of blood stored for transfusion. Recently, the prevalence of postpartum hemorrhage (PPH), as well as the frequency of PPH-associated transfusions, has steadily increased. Therefore, proper blood transfusion is required to minimize PPH-associated complications while saving the patient's life. Several guidelines have attempted to apply this concept to minimize anemia during pregnancy and bleeding during delivery, prevent bleeding after delivery, and optimize recovery methods from anemia. This study systematically reviewed various guidelines to determine blood loss management in pregnant women.

Risk factors for severe postpartum hemorrhage requiring blood transfusion after cesarean delivery for twin pregnancy: a nationwide cohort study

BACKGROUND

Postpartum hemorrhage (PPH) is a leading cause of maternal morbidity and mortality. Twin pregnancy and cesarean delivery are well-known risk factors for PPH. However, few studies have investigated PPH risk factors in mothers who have undergone cesarean delivery for twin pregnancies. Therefore, this study investigated the risk factors associated with severe PPH after cesarean delivery for twin pregnancies.

METHODS

We searched and reviewed the Korean Health Insurance Review and Assessment Service's claims data from July 2008 to June 2021 using the code corresponding to cesarean delivery for twin pregnancy. Severe PPH was defined as hemorrhage requiring red blood cell (RBC) transfusion during the peripartum period. The risk factors associated with severe PPH were identified among the procedure and diagnosis code variables and analyzed using univariate and multivariate logistic regressions.

RESULTS

We analyzed 31,074 cesarean deliveries for twin pregnancies, and 4,892 patients who underwent cesarean deliveries for twin pregnancies and received RBC transfusions for severe PPH were included. According to the multivariate analysis, placental disorders (odds ratio, 4.50; 95% confidence interval, 4.09- 4.95; P < 0.001), general anesthesia (2.33, 2.18-2.49; P < 0.001), preeclampsia (2.20, 1.99-2.43; P < 0.001), hemolysis, elevated liver enzymes, low platelets (HELLP) syndrome (2.12, 1.22-3.68; P = 0.008), induction failure (1.37, 1.07-1.76; P = 0.014), and hypertension (1.31, 1.18-1.44; P < 0.001) predicted severe PPH.

CONCLUSIONS

Placental disorders, hypertensive disorders such as preeclampsia and HELLP syndrome, and induction failure increased the risk of severe PPH after cesarean delivery for twin pregnancy.

Critical Assessment of Transfusional Practices in the Obstetrics and Gynecology Department At the University Hospital of Kinshasa

Introduction

Gynecology and obstetrics are among the specialties where blood transfusion is most practiced. This situation requires the use of good transfusion practices. The objective of this study was to assess the quality of transfusion practice in the Gynecology and Obstetrics Department of the University Hospital of Kinshasa (UHK).

Methods

This is a prospective, evaluative and descriptive study performed at the Department of Gyneco-Obstetrics of the University Hospital of Kinshasa from February 25 to June 25, 2020; which dealt with patients who received at least one blood transfusion.

Results

About 498 patients, 54 patients were transfused and their average age was 36.4 years, with the extremes of 14 and 60 years, the transfusion rate was 10.8%. Most of patients (n=36: 2/3) were transfused during weekend days, sachets were used as delivery materials of blood product in 57.4% of cases (n = 31). Among the prescribers of blood products, 70.4% were nurses. All transfusions were carried out in type-specific and cross-matched Rh. All the transfused patients were not aware of the disadvantages of transfusion. Compatibility tests at the patient's bedside were not performed in 61.1% of cases and the concordance control between the patient and the blood component to be transfused was not performed in 70.4% of cases. Close monitoring of blood transfusion in the first ten minutes was not performed in 59.3% of cases.

Conclusion

Transfusion encounters real practical problems in the gyneco-obstetrical environment of countries with limited resources. However, an assessment and multidisciplinary collaboration would be necessary to improve transfusion practice in medical field.

Low-dose aspirin in the prevention of pre-eclampsia in China: postpartum hemorrhage in subgroups of women according to their characteristics and potential bleeding risk

BACKGROUND

The APPEC study is a large-population randomized controlled trial in China evaluating the role of low-dose aspirin prophylactic treatment for pre-eclampsia. There was no statistically significant difference in postpartum hemorrhage (PPH) incidence between the aspirin and control groups. This study aimed to evaluate the potential bleeding risk of 100 mg aspirin in high-risk pregnant women and the difference in the incidence of PPH according to maternal characteristics.

METHODS

This is a secondary data analysis of the APPEC study. Platelet counts and coagulation test results were collected at five follow-up visits. Subgroups defined by maternal age (<35 years and ≥35 years), pre-pregnancy body mass index (pre-BMI, <28 kg/m 2 and ≥28 kg/m 2 ), parity, gestational age at enrollment, and medical history, including pre-eclampsia, chronic hypertension, and diabetes mellitus, were analyzed. Logistic regression analysis was used to determine the statistical significance of the difference in the incidence of PPH after aspirin administration in pregnant women in each subgroup. Adjustment using multiple logistic regression models followed these analyses. Binary logistic regression was used to determine the relationship between pre-BMI and PPH.

RESULTS

There was no significant difference between the aspirin and control groups in bleeding risk (3.4% [16/464] vs. 3.0% [13/434], T = 0.147, P  = 0.701). No significant difference was found in the incidence of PPH in total (relative risk  = 1.220, 95% confidence interval [CI] = 0.720-2.067, P  = 0.459; aspirin group vs. control group, 6.5% [30/464] vs. 5.3% [23/434], P  = 0.459) or in subgroup analysis. A significant correlation between pre-BMI and PPH was found in the aspirin group, while in the control group there was no significant correlation (aspirin group, odds ratio [OR] = 1.086, 95% CI = 1.004-1.175, P  = 0.040; control group, OR = 1.060, 95% CI = 0.968-1.161, P  = 0.209).

CONCLUSIONS

A dosage of 100 mg of aspirin per day, initiated from 12 to 20 gestational weeks until 34 weeks of gestation, did not increase the risk of potential bleeding and PPH regardless of the maternal characteristic. In the aspirin group, the positive correlation between BMI and PPH was significant.

TRIAL REGISTRATION

ClinicalTrials.gov, NCT01979627.

Adverse Maternal and Infant Outcomes of Women Who Differ in Smoking Status: E-Cigarette and Tobacco Cigarette Users

The electronic cigarette (e-cigarette) became commercially available around 2004, yet the characteristics of pregnant women who use these devices and their effects on maternal and infant health remain largely unknown. This study aimed to investigate maternal characteristics and pregnancy outcomes according to maternal smoking status. We conducted a cross-sectional study of Dutch women with reported pregnancies between February 2019 and May 2022, using an online questionnaire to collect data on smoking status and demographic, lifestyle, pregnancy, and infant characteristics. Smoking status is compared among non-smokers, tobacco cigarette users, e-cigarette users, and dual users (tobacco and e-cigarette). We report descriptive statistics and calculate differences in smoking status between women with the chi-square or Fisher (Freeman-Halton) test. Of the 1937 included women, 88.1% were non-smokers, 10.8% were tobacco cigarette users, 0.5% were e-cigarette users, and 0.6% were dual users. Compared with tobacco users, e-cigarette users more often reported higher education, having a partner, primiparity, and miscarriages. Notably, women who used e-cigarettes more often had small infants for gestational age. Despite including few women in the e-cigarette subgroup, these exploratory results indicate the need for more research to examine the impact of e-cigarettes on pregnancy outcomes.

Association of Preterm Birth with Inflammatory Bowel Disease and Salivary Gland Disease: Machine Learning Analysis Using National Health Insurance Data

This study employs machine learning and population data for testing the associations of preterm birth with inflammatory bowel disease (IBD), salivary gland disease, socioeconomic status and medication history, including proton pump inhibitors. The source of population-based retrospective cohort data was the Korea National Health Insurance Service claims data for all women aged 25–40 years and who experience their first childbirths as singleton pregnancy during 2015 to 2017 (402,092 women). These participants were divided into the Ulcerative Colitis (UC) Group (1782 women), the Crohn Group (1954 women) and the Non-IBD Group (398,219 women). For each group, the dependent variable was preterm birth during 2015–2017, and 51 independent variables were included. Random forest variable importance was employed for investigating the main factors of preterm birth and testing its associations with salivary gland disease, socioeconomic status and medication history for each group. The proportion of preterm birth was higher for the UC Group and the Non-IBD Group than for the Crohn Group: 7.86%, 7.17% vs. 6.76%. Based on random forest variable importance, salivary gland disease was a top 10 determinant for the prediction of preterm birth for the UC Group, but this was not the case for the Crohn Group or the Non-IBD Group. The top 5 variables of preterm birth for the UC Group during 2015–2017 were socioeconomic status (8.58), age (8.00), proton pump inhibitors (2.35), progesterone (2.13) and salivary gland disease in 2014 (1.72). In conclusion, preterm birth has strong associations with ulcerative colitis, salivary gland disease, socioeconomic status and medication history including proton pump inhibitors.

Association of preterm birth with medications: machine learning analysis using national health insurance data

PURPOSE

To use machine learning and population data for testing the associations of preterm birth with socioeconomic status, gastroesophageal reflux disease (GERD) and medication history including proton pump inhibitors, sleeping pills and antidepressants.

METHODS

Population-based retrospective cohort data came from Korea National Health Insurance Service claims data for all women who aged 25-40 years and gave births for the first time as singleton pregnancy during 2015-2017 (405,586 women). The dependent variable was preterm birth during 2015-2017 and 65 independent variables were included (demographic/socioeconomic determinants, disease information, medication history, obstetric information). Random forest variable importance (outcome measure) was used for identifying major determinants of preterm birth and testing its associations with socioeconomic status, GERD and medication history including proton pump inhibitors, sleeping pills and antidepressants.

RESULTS

Based on random forest variable importance, major determinants of preterm birth during 2015-2017 were socioeconomic status (645.34), age (556.86), proton pump inhibitors (107.61), GERD for the years 2014, 2012 and 2013 (106.78, 105.87 and 104.96), sleeping pills (97.23), GERD for the years 2010, 2011 and 2009 (95.56, 94.84 and 93.81), and antidepressants (90.13).

CONCLUSION

Preterm birth has strong associations with low socioeconomic status, GERD and medication history such as proton pump inhibitors, sleeping pills and antidepressants. For preventing preterm birth, appropriate medication would be needed alongside preventive measures for GERD and the promotion of socioeconomic status for pregnant women.

Poor uterine contractility and postpartum hemorrhage among low-risk women: A case-control study of a large-scale database from Japan

OBJECTIVE

To examine the association between the risk of postpartum hemorrhage (PPH) and poor uterine contractility, which is suggested by the characteristics of labor.

METHODS

This case-control study used cases recorded in the Japan Perinatal Registry database during the period 2013-2016. After exclusion of women with specified known risk factors for PPH, we enrolled 174 082 primiparas who had a full-term live singleton vaginal birth. Participants were classified into four classes according to the diagnosis of abnormal labor patterns and use of uterotonics. χ² tests were used to compare PPH cases with controls, and odds ratios (OR) were calculated by univariate and multivariate analyses.

RESULTS

Among the enrolled women, 10 508 (6.0%) had PPH. Abnormal labor patterns were significantly associated with an increased risk of PPH. Compared with women without any abnormal labor patterns who had not used uterotonics, women with abnormal labor patterns were at a significantly increased risk for PPH regardless of whether they had used uterotonics (adjusted OR 1.23, 95% confidence interval [CI] 1.10-1.37) or not (adjusted OR 1.30, 95% CI 1.23-1.37).

CONCLUSION

Our study suggests that among low-risk women with PPH, poor uterine contractility in labor could be a significant predisposing risk factor for PPH.