Prediction of Childbirth Mortality Using Machine Learning
Oleg Metsker1, Georgy Kopanitsa2, Ekaterina Bolgova2
1Almazov National Medical Research Centre, Saint-Petersburg, Russia.
Insights
Predictive models using unstructured pregnancy data improve adverse childbirth event prediction. This approach enhances accuracy, aiding clinicians in early risk identification and preventive care for better maternal and child outcomes.
Area of Science:
- Perinatal Medicine
- Medical Informatics
- Predictive Analytics
Background:
- Adverse perinatal outcomes pose risks to mothers and infants.
- Early identification and management of pregnancy risk factors are crucial for mitigation.
- Current predictive models may not fully leverage available clinical data.
Purpose of the Study:
- To develop and evaluate predictive models for adverse childbirth events.
- To assess the impact of unstructured clinical data on prediction accuracy.
- To identify key risk factors for adverse perinatal outcomes.
Main Methods:
- Retrospective analysis of electronic health records from a perinatal center.
- Utilized Pearson correlation coefficient for predictor selection.
- Compared prediction models with and without unstructured anamnesis data.
- Employed APGAR scores to define childbirth outcomes (≤5 as negative).
Main Results:
- Predictive models incorporating unstructured medical data achieved 0.92 precision.
- Unstructured data significantly improved the accuracy of adverse childbirth event prediction.
- Feature importance analysis identified key risk factors for complications.
Conclusions:
- Integrating unstructured clinical data enhances predictive model performance for adverse childbirth events.
- Early identification of risk factors through advanced analytics supports timely preventive interventions.
- This approach can lead to improved maternal and child health outcomes.
Abstract:
Timely identification of risk factors in the early stages of pregnancy, risk management and mitigation, prevention, adherence management can reduce the number of adverse perinatal outcomes and complications for both mother and a child. We have retrospectively analyzed electronic health records from the perinatal Center of the Almazov specialized medical center in Saint-Petersburg, Russia. Correlation analysis was performed using Pearson correlation coefficient to select the most relevant predictors. We used APGAR score as a metrics for the childbirth outcomes. Score of 5 and less was considered as a negative outcome. To analyze the influence of the unstructured anamnesis data on the prediction accuracy we have run two prediction experiments for every classification task: 1. Without unstructured data and 2. With unstructured data. This study presents implementation of predictive models for adverse childbirth events that provides higher precision than state of the art models. This is due to the use of unstructured medical data in addition to the structured dataset that allowed to reach 0.92 precision. Identification of main risk factors using the results of the features importance analysis can support clinicians in early identification of possible complications and planning and execution preventive measures.
Related Concept Videos
01:52Regression Toward the Mean
01:22Applications of Life Tables
01:18Steps in Outbreak Investigation
01:19Survival Tree
Building a Survival Tree
Constructing a...
01:03Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
01:24Kaplan-Meier Approach