Related Experiment Video
Updated: Jun 5, 2025
Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System
Published on: March 17, 2023
Prediction of preterm birth using machine learning: a comprehensive analysis based on large-scale preschool children
Liwen Ding1, Xiaona Yin2, Guomin Wen2
1Department of Epidemiology and Health Statistics, School of Public Health, Sun Yat-Sen University, Guangzhou, 510080, China.
Insights
Machine learning models, especially XGBoost, show promise for predicting preterm birth (PTB) and identifying key risk factors like multiple pregnancies. This can improve prenatal care and public health strategies.
Area of Science:
- Computational biology and bioinformatics
- Reproductive health and obstetrics
- Data science and machine learning
Background:
- Preterm birth (PTB) is a leading cause of neonatal mortality and long-term health issues.
- Accurate PTB prediction is crucial for reducing child mortality and morbidity.
- Traditional methods struggle with complex, interacting risk factors.
Purpose of the Study:
- To develop and evaluate six machine learning (ML) models for PTB prediction.
- To identify key predictors of PTB using large-scale survey data.
- To utilize Shapley Additive Explanations (SHAP) for model interpretability.
Main Methods:
- Utilized data from 84,050 mother-child pairs (2021-2022).
- Tested six ML models: L1-LR, LightGBM, Naive Bayes, RF, SVM, and XGBoost.
- Evaluated models on discrimination, calibration, and clinical utility, with SHAP for feature importance.
Main Results:
- XGBoost achieved the best performance (AUC 0.752 validation, 0.757 test).
- Key predictors identified: multiple pregnancies, threatened abortion, maternal age.
- SHAP analysis confirmed positive impacts of multiple pregnancies/threatened abortion and negative impact of micronutrient supplementation.
Conclusions:
- Machine learning models, particularly XGBoost, demonstrate significant potential for accurate PTB prediction.
- Identified key risk factors can inform personalized prenatal care strategies.
- Findings support the use of ML in enhancing clinical interventions and public health initiatives for PTB prevention.
Background:
Preterm birth (PTB) is a significant cause of neonatal mortality and long-term health issues. Accurate prediction and timely prevention of PTB are essential for reducing associated child mortality and morbidity. Traditional predictive methods face challenges due to heterogeneous risk factors and their interaction effects. This study aims to develop and evaluate six machine learning (ML) models to predict PTB using large-scale children survey data from Shenzhen, China, and to identify key predictors through Shapley Additive Explanations (SHAP) analysis.
Methods:
Data from 84,050 mother-child pairs, collected in 2021 and 2022, were processed and divided into training, validation, and test sets. Six ML models were tested: L1-Regularised Logistic Regression, Light Gradient Boosting Machine (LightGBM), Naive Bayes, Random Forests, Support Vector Machine, and Extreme Gradient Boosting (XGBoost). Model performance was evaluated based on discrimination, calibration and clinical utility. SHAP analysis was used to interpret the importance and impact of individual features on PTB prediction.
Results:
The XGBoost model demonstrated the best overall performance, with the area under the receiver operating characteristic curve (AUC) scores of 0.752 and 0.757 in the validation and test sets, respectively, along with favorable calibration and clinical utility. Key predictors identified were multiple pregnancies, threatened abortion, and maternal age of conception. SHAP analysis highlighted the positive impacts of multiple pregnancies and threatened abortion, as well as the negative impact of micronutrient supplementation on PTB.
Conclusion:
Our study found that ML models, particularly XGBoost, show promise in accurately predicting PTB and identifying key risk factors. These findings provide the potential of ML for enhancing clinical interventions, personalizing prenatal care, and informing public health initiatives.
