Prediction of postpartum hemorrhage using traditional statistical analysis and a machine learning approach
Vahid Mehrnoush1,2, Amene Ranjbar3, Mohammadsadegh Vahidi Farashah4
1Mother and Child Welfare Research Center, Hormozgan University of Medical Sciences, Bandar Abbas, Iran (Drs Mehrnoush and Darsareh and Mses Shekari and Jahromi).
AJOG Global Reports
|March 20, 2023
Summary
This study compared traditional analysis and machine learning to predict postpartum hemorrhage (PPH). Machine learning, particularly XGBoost classification, demonstrated superior accuracy in identifying PPH risk factors, offering a promising tool for early detection and prevention.
Area of Science:
- Obstetrics and Gynecology
- Data Science in Healthcare
- Predictive Analytics
Background:
- Postpartum hemorrhage (PPH) is a significant maternal health concern.
- Early identification of PPH risk factors is crucial for timely intervention.
- Developing accurate prediction models for PPH is essential for improving patient outcomes.
Purpose of the Study:
- To compare traditional analytical methods with machine learning models for predicting postpartum hemorrhage.
- To identify key risk factors associated with PPH using both approaches.
- To evaluate the accuracy and effectiveness of different machine learning algorithms in PPH prediction.
Main Methods:
- Retrospective analysis of 8888 deliveries between January 2020 and January 2022.
- Comparison of demographic, maternal comorbidity, and obstetrical factors between PPH and non-PPH groups.
- Application of traditional bivariate logistic regression and various machine learning algorithms (XGBoost, LightGBM, Random Forest, Linear Regression) for prediction.
Main Results:
- The incidence of PPH was 1.8% (163 out of 8888 deliveries).
- Traditional analysis identified factors like rural living, primiparity, anemia, abnormal placentation, fetal macrosomia, shoulder dystocia, and operative delivery as significant risk factors.
- Machine learning models showed high predictive power, with XGBoost classification achieving an area under the receiver operating characteristic curve of 98%, outperforming traditional methods.
Conclusions:
- Both traditional statistical analysis and machine learning can identify postpartum hemorrhage risk factors.
- Machine learning models, especially XGBoost classification, offer a highly accurate and credible approach for improving PPH prediction.
- Further research is needed to refine variables and utilize big data for optimal PPH predictive modeling.
Related Concept Videos
01:18Steps in Outbreak Investigation
158
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
158
01:52Regression Toward the Mean
6.3K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.3K
01:25Statistical Methods for Analyzing Epidemiological Data
442
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
442