Related Experiment Video
Updated: Oct 21, 2025
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
Risk Identification of Bronchopulmonary Dysplasia in Premature Infants Based on Machine Learning
Jintao Lei1, Tiankai Sun1, Yongjiang Jiang2
1School of Science, Guangxi University of Science and Technology, Liuzhou, China.
Insights
Machine learning accurately predicts bronchopulmonary dysplasia (BPD) in premature infants. This approach identifies key risk factors, enabling clinicians to develop optimal treatment plans for better infant lung health.
Area of Science:
- Neonatal Medicine
- Computational Biology
- Data Science
Background:
- Bronchopulmonary dysplasia (BPD) is a frequent complication in premature infants, often linked to prolonged oxygen therapy.
- BPD significantly impairs lung function, creating substantial burdens for families and healthcare systems.
Purpose of the Study:
- To identify predictors of BPD in premature infants using machine learning.
- To develop a predictive model for optimal clinical treatment planning.
Main Methods:
- Ensemble learning combining Boruta and random forest algorithms.
- Feature selection using the Boruta algorithm and 10-fold cross-validation.
- Model development using data from 648 premature infants.
Main Results:
- Six key predictive variables were identified from an initial set of 26.
- The random forest model achieved an excellent Area Under the Curve (AUC) of 0.929.
- The model demonstrated high predictive performance for BPD.
Conclusions:
- Machine learning, specifically ensemble methods, offers a powerful tool for predicting BPD in premature infants.
- Accurate prediction facilitates personalized treatment strategies, potentially improving outcomes.
- This approach supports clinical decision-making in neonatal care.
Abstract:
Bronchopulmonary dysplasia (BPD) is one of the most common complications in premature infants. This disease is caused by long-time use of supplemental oxygen, which seriously affects the lung function of the child and imposes a heavy burden on the family and society. This research aims to adopt the method of ensemble learning in machine learning, combining the Boruta algorithm and the random forest algorithm to determine the predictors of premature infants with BPD and establish a predictive model to help clinicians to conduct an optimal treatment plan. Data were collected from clinical records of 996 premature infants treated in the neonatology department of Liuzhou Maternal and Child Health Hospital in Western China. In this study, premature infants with congenital anomaly, premature infants who died, and premature infants with incomplete data before the diagnosis of BPD were excluded from the data set. After exclusion, we included 648 premature infants in the study. The Boruta algorithm and 10-fold cross-validation were used for feature selection in this study. Six variables were finally selected from the 26 variables, and the random forest model was established. The area under the curve (AUC) of the model was as high as 0.929 with excellent predictive performance. The use of machine learning methods can help clinicians predict the disease so as to formulate the best treatment plan.
