Risk Prediction Model for Postpartum Hemorrhage

Overseen By Tracie Baker, CCRP

Age: Any Age

Sex: Female

Trial Phase: Academic

Sponsor: Holly Ende

Disqualifiers: Pre-delivery hysterectomy, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

10000 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial aims to make childbirth safer by using a new computer model to predict postpartum hemorrhage (PPH), which is heavy bleeding after delivery. The study will compare the Novel PPH Risk Prediction Model with the current method to determine if it better assists doctors in preventing PPH. The new model updates automatically with 21 factors during labor, providing doctors with timely advice. Women giving birth at Vanderbilt University Medical Center, either vaginally or via cesarean, are eligible to participate. As an unphased trial, this study offers participants the chance to contribute to groundbreaking research that could enhance childbirth safety for future mothers.

Do I need to stop my current medications for this trial?

The trial information does not specify whether you need to stop taking your current medications. It's best to discuss this with the trial coordinators or your healthcare provider.

What prior data suggests that this risk prediction model is safe for use in childbirth?

Research has shown that a new tool can help predict heavy bleeding after childbirth, known as postpartum hemorrhage (PPH). This tool uses advanced computer methods to identify potential risks. Studies have demonstrated its ability to successfully predict PPH by constantly updating with new information during labor.

This tool does not involve any medication or physical procedures. Instead, it provides healthcare providers with helpful advice based on calculated risks, minimizing safety concerns for patients. The main goal is to assist doctors and nurses in making better decisions for safer deliveries.

Designed to improve care during childbirth, the tool offers real-time insights. While still under testing, early findings suggest it could better manage risks without introducing new risks to the mother or baby. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about this trial because it aims to improve how we predict the risk of postpartum hemorrhage (PPH), a serious complication after childbirth. Unlike standard care, which uses a basic category-based risk assessment tool, the novel PPH risk prediction model offers a more precise and personalized approach by integrating recent advancements in data analysis. This new model could help healthcare providers identify high-risk patients more accurately, leading to better preventative care and potentially reducing the incidence of PPH.

What evidence suggests that this novel PPH risk prediction model is effective for improving perinatal outcomes?

This trial will compare a novel postpartum hemorrhage (PPH) risk prediction model with standard care. Studies have shown that the new model can identify over 80% of severe cases. It uses advanced computer techniques to analyze 21 different factors that change during labor. The model updates instantly and alerts doctors and nurses, enabling quicker action. Although it identifies most severe cases, it may also alert for some women who don't need extra care. Overall, the model aims to make childbirth safer by better predicting and managing bleeding risks. ^{3 4 6 7 8}

Who Is on the Research Team?

Holly Ende, MD

Principal Investigator

Vanderbilt University Medical Center

Are You a Good Fit for This Trial?

This trial is for pregnant individuals at risk of postpartum hemorrhage (PPH). Participants should be giving birth where the study is being conducted. There are no specific inclusion or exclusion criteria provided, but typically participants would need to be of childbearing age and not have conditions that could interfere with the study.

Inclusion Criteria

All vaginal and cesarean deliveries occurring at Vanderbilt University Medical Center

Exclusion Criteria

Patients who are discharged prior to delivery will be excluded from subsequent analysis

I am not planning a hysterectomy before delivery for placenta issues.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Intervention

Participants are assigned to either the standard care arm or the novel PPH risk prediction model arm. The intervention arm includes additional risk prediction and Best Practice Advisory (BPA) for elevated risk cases.

Duration of labor and delivery

Postpartum Monitoring

Participants are monitored for postpartum outcomes, including morbidity and mortality, up to 30 days postpartum.

30 days

Follow-up

Participants are monitored for safety and effectiveness after treatment, including postpartum hospital discharge outcomes.

2-4 days

What Are the Treatments Tested in This Trial?

Interventions

• Novel PPH Risk Prediction Model

Trial Overview The trial tests a new computer model predicting PPH against current basic tools. It uses 21 factors to assess risk in real-time during labor, providing instant recommendations if there's an increased risk.

How Is the Trial Designed?

Group I: Novel PPH Risk Prediction Model - Comparator Arm B Active Control 1 Intervention

Standard Care with addition of a recently developed, novel PPH risk prediction model.

Group II: Standard Care - Comparator Arm A Active Control 1 Intervention

Standard Care, which includes a category-based risk assessment tool as part of nursing admission workflow. The prophylactic interventions in the intervention are recommended by the tool but not specifically tied to provider-facing clinical decision support.

Who Is Running the Clinical Trial?

Holly Ende

Lead Sponsor

Trials

1

Recruited

10,000+

Vanderbilt University Medical Center

Collaborator

Trials

922

Recruited

939,000+

Published Research Related to This Trial

Using machine learning and statistical models, researchers successfully predicted the risk of postpartum hemorrhage in women at labor admission, analyzing data from 152,279 births, with 7,279 cases (4.8%) of postpartum hemorrhage identified.

The extreme gradient boosting model showed the highest accuracy in predicting postpartum hemorrhage (C statistic: 0.93), indicating its potential to help healthcare providers prepare for and manage at-risk patients effectively.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Machine Learning and Statistical Models to Predict Postpartum Hemorrhage. Venkatesh, KK., Strauss, RA., Grotegut, CA., et al.[2022]

A nationwide study involving 432 pregnant women with immune thrombocytopenia (ITP) developed the MONITOR prediction model, which accurately identifies the risk of postpartum hemorrhage (PPH) using seven key clinical factors.

The MONITOR model demonstrated high accuracy in predicting PPH, with an area under the curve (AUC) of 0.868 in internal validation, indicating it can significantly improve clinical care and resource allocation for at-risk patients.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Prediction of postpartum hemorrhage in pregnant women with immune thrombocytopenia: Development and validation of the MONITOR model in a nationwide multicenter study. Huang, QS., Zhu, XL., Qu, QY., et al.[2021]

A prediction model for postpartum hemorrhage (PPH) was developed using data from 5,807 singleton pregnancies, identifying four key risk factors: nulliparity, fetal macrosomia, mode of delivery, and history of PPH.

The model demonstrated good predictive performance with a C-statistic of 0.751, and external validation confirmed its reliability, suggesting that the nomogram could help clinicians assess individual PPH risk and improve management strategies.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Predicting risk of postpartum haemorrhage during the intrapartum period in a general obstetric population. Maher, GM., McKernan, J., O'Byrne, L., et al.[2022]

A study of 43,657 deliveries identified four levels of postpartum hemorrhage based on treatment interventions, showing that higher levels of hemorrhage were linked to greater drops in hematocrit, indicating more severe blood loss.

The use of uterotonics to manage postpartum hemorrhage increased significantly over the study period, and while severe maternal morbidity remained stable, the risk of hysterectomy decreased, suggesting improved management strategies.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A Framework for Improving Characterization of Obstetric Hemorrhage Using Informatics Data. Goffman, D., Friedman, AM., Sheen, JJ., et al.[2023]

A new nomogram was developed to predict the risk of postpartum hemorrhage (PPH) in twin pregnancies undergoing cesarean delivery, based on a study of 372 matched cases (186 with PPH and 186 without) from January 2014 to July 2021.

The nomogram demonstrated good predictive ability with an area under the curve of 0.778, which can help clinicians optimize surgical plans and treatments to reduce maternal morbidity and mortality associated with PPH.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Nomogram to predict postpartum hemorrhage in cesarean delivery for twin pregnancies: a retrospective cohort study in China. Zhang, Y., Chen, L., Zhou, W., et al.[2023]

A predictive model for postpartum hemorrhage (PPH) was developed using data from 2742 vaginal deliveries, identifying eight key risk factors, including pre-eclampsia and antepartum bleeding, which can help healthcare providers assess risk.

The model demonstrated good discriminant power in both the derivation cohort (AUROC 0.69) and an external validation cohort (AUROC 0.66), suggesting it can effectively identify women at risk for PPH and improve preventive care strategies.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Development and Validation of a Predictive Tool for Postpartum Hemorrhage after Vaginal Delivery: A Prospective Cohort Study. Bihan, L., Nowak, E., Anouilh, F., et al.[2023]

In a study of 270 women who delivered vaginally, the average blood loss within 2 hours postpartum was 427.49 mL, with 31% experiencing blood loss greater than 500 mL, indicating a significant risk of postpartum hemorrhage (PPH).

The use of forceps during delivery was strongly associated with increased blood loss (odds ratio of 9.5), while factors like previous anemia and episiotomy were linked to even higher blood loss (>1,000 mL), highlighting the need for careful monitoring and prompt intervention in these cases.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Risk Factors for Postpartum Hemorrhage and its Severe Forms with Blood Loss Evaluated Objectively - A Prospective Cohort Study. Borovac-Pinheiro, A., Ribeiro, FM., Pacagnella, RC.[2023]

In a study of 7236 women with post-partum hemorrhage (PPH), severe cases were identified in 18.5% of participants, with several clinical factors like parity and labor induction linked to increased risk.

A prediction model developed to identify severe PPH had a moderate performance (ROC area of 0.63), but its sensitivity (49%) and specificity (70%) were insufficient for routine clinical use, indicating a need for additional data, such as laboratory results, to improve accuracy.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Severity of post-partum hemorrhage after vaginal delivery is not predictable from clinical variables available at the time post-partum hemorrhage is diagnosed. Cortet, M., Maucort-Boulch, D., Deneux-Tharaux, C., et al.[2022]

In a study of over 3 million births in Norway from 1967 to 2017, postpartum hemorrhage (PPH) occurred in 9.3% of cases, with retained placenta being the most common cause of severe PPH (29.3%).

The study found that the sex of the newborn affects PPH risk, with male infants associated with a lower risk of PPH, particularly for retained placenta and uterine atony, while a history of cesarean section significantly increased the risk of PPH due to dystocia.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Risk factors and recurrence of cause-specific postpartum hemorrhage: A population-based study. Linde, LE., Rasmussen, S., Moster, D., et al.[2022]

Citations

1. sciencedirect.com sciencedirect.com/science/article/abs/pii/S1746809425005841

A novel framework for enhancing postpartum hemorrhage ... A novel PPH prediction framework uses neural networks with three sampling strategies. Enhanced preprocessing and feature extraction improve data quality and ...

2. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC10020099/

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

3. obstetanesthesia.com obstetanesthesia.com/article/S0959-289X(25)00286-9/fulltext

Artificial intelligence in prediction of postpartum hemorrhage The purpose of this review is to describe the current state of AI-based PPH risk assessment, including the application of logistic regression and machine ...

4. academic.oup.com academic.oup.com/jamia/article/29/2/296/6354090

Improving postpartum hemorrhage risk prediction using ... We developed a novel approach for predicting PPH and identified clinical feature thresholds that can guide intrapartum monitoring for PPH risk.

5. imrpress.com imrpress.com/journal/CEOG/51/3/10.31083/j.ceog5103060/htm

Postpartum Haemorrhage Risk Prediction Model ... The results show that although the tool correctly identified more than 80% of severe PPH patients, more than 40% of nonbleeding women were ...

6. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC8757294/

Improving postpartum hemorrhage risk prediction using ... We developed a novel approach for predicting PPH and identified clinical feature thresholds that can guide intrapartum monitoring for PPH risk.

7. sciencedirect.com sciencedirect.com/science/article/pii/S0959289X25002869

Artificial intelligence in prediction of postpartum hemorrhage Postpartum hemorrhage risk predictions can be accomplished via checklist tools completed manually by healthcare providers or via machine-assisted calculations ...

8. withpower.com withpower.com/trial/phase-postpartum-hemorrhage-9-2024-5c152

Risk Prediction Model for Postpartum Hemorrhage This research project aims to enhance the safety of childbirth by using advanced computer models to predict the risk of postpartum hemorrhage (PPH).PPH is a ...