Early prediction of low birth weight using boosting ensemble machine learning: A retrospective cohort study
Ya-Ling Hu1, Kung-Liahng Wang2,3, Jerry Cheng-Yen Lai4,5
1Department of Nursing, College of Nursing, National Yang Ming Chiao Tung University, Yangming Campus, Taipei, Taiwan.
Insights
This study developed a machine learning model to predict low birth weight (LBW) using early pregnancy data. The model achieved high accuracy, enabling early risk assessment and intervention for newborns.
Area of Science:
- Maternal and child health
- Medical informatics
- Machine learning in healthcare
Background:
- Low birth weight (LBW) is a significant risk factor for neonatal mortality and future chronic diseases.
- Early identification of LBW risk is critical for timely intervention and improved outcomes.
- Predictive modeling using early pregnancy data offers a promising approach to LBW risk assessment.
Purpose of the Study:
- To develop and evaluate boosting ensemble machine learning models for predicting low birth weight (LBW).
- To identify key predictive features available during early pregnancy for LBW.
- To create a tool for early LBW risk assessment in clinical practice.
Main Methods:
- Retrospective cohort study utilizing electronic medical records from four Taiwanese hospitals (January 2016 - July 2019).
- Inclusion of 6719 pregnant women, with data preprocessing including normalization, one-hot encoding, and synthetic minority oversampling technique (SMOTE).
- Application of boosting ensemble methods, including Lightweight Gradient Boosting Machine, to build predictive models.
Main Results:
- The Lightweight Gradient Boosting Machine model demonstrated superior performance with an Area Under the Curve (AUC) of 0.96 and 93.4% accuracy.
- Key predictors for LBW included early pregnancy diastolic blood pressure (DBP), maternal height, and abortion history.
- Prevalence data indicated 8.7% LBW deliveries, 12.2% pre-pregnancy overweight/obesity, and 18.3% elevated/stage I hypertension before 20 weeks.
Conclusions:
- The developed LBW prediction model is effective and can be utilized by nurses for early risk assessment.
- Clinical interventions can be targeted based on model predictions, focusing on blood pressure management, nutritional support, and self-care for high-risk pregnancies.
- Early pregnancy data, particularly DBP and maternal characteristics, are crucial for accurate LBW prediction.
Background:
Low birth weight (LBW) is a leading cause of death for newborns and increases chronic disease risks later in life. Early identification of LBW risk is crucial.
Aim:
The objective of this study was to develop predictive models for LBW using boosting ensemble machine learning, with a focus on features available during early pregnancy, such as pre-pregnancy body mass index, body height, and blood pressure before 20 weeks of pregnancy.
Methods:
This is a retrospective cohort study. We used electronic medical records in four hospitals in Taiwan where pregnant women received prenatal care from January 2016 to July 2019, including 6719 pregnant women. Data preprocessing involved normalization, one-hot encoding, and a synthetic minority oversampling technique for class imbalance. Boosting ensemble methods were used to build the LBW predictive models.
Results:
The mean diastolic blood pressure (DBP) in early pregnancy (<20 weeks) was 66.5 mmHg, 29.6% had experienced abortion, 8.7% delivered LBW, 12.2% were overweight or obese before pregnancy, and 18.3% had elevated or stage I hypertension before 20 weeks of pregnancy. Lightweight Gradient Boosting Machine was the best-performing LBW model, with an area under curve of 0.96 and an accuracy of 93.4%. Early pregnancy DBP, maternal height, and number of abortions were the most important features.
Conclusions:
The LBW prediction model performed well. Nurses could use the model to assess LBW risk and intervene early. Preventive efforts could be directed to blood pressure management starting early pregnancy, nutritional support for short mothers, and self-care for women with a history of abortions.
More Related Videos
Related Concept Videos
01:22Birth Control Methods
00:57Weighted Mean
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
01:19Machines
A free-body diagram of the...
02:27Predicting Molecular Geometry
01:25Atomic Weight
01:19Mass and Weight