Related Experiment Video
Updated: Jun 26, 2025
Intratracheal Instillation of Stem Cells in Term Neonatal Rats
Published on: May 4, 2020
A comprehensive study on machine learning models combining with oversampling for bronchopulmonary
Dan Wang1,2,3, Shuwei Huang4, Jingke Cao1,2
1Newborn Intensive Care Unit, Faculty of Pediatrics, the Seventh Medical Center of PLA General Hospital, Beiing, China.
Insights
Machine learning models can predict bronchopulmonary dysplasia-associated pulmonary hypertension (BPD-PH) in infants. Early identification of BPD-PH risk improves diagnosis and treatment planning for better outcomes.
Area of Science:
- Neonatal Medicine
- Artificial Intelligence in Healthcare
- Pulmonary Hypertension Research
Background:
- Bronchopulmonary dysplasia-associated pulmonary hypertension (BPD-PH) significantly impacts preterm infant outcomes.
- Early detection of BPD-PH is crucial for reducing morbidity and improving prognosis.
- Machine learning offers a promising approach for identifying infants at risk of BPD-PH.
Purpose of the Study:
- To develop and validate machine learning models for early prediction of BPD-PH in infants.
- To identify key clinical features associated with the development of BPD-PH.
- To provide clinicians with a tool for timely diagnosis and treatment planning.
Main Methods:
- Utilized clinical data from 761 neonatology patients across four tertiary hospitals in China.
- Applied Synthetic Minority Over-sampling Technique (SMOTE) to address imbalanced data.
- Selected 5 key features including respiratory support duration, BPD severity, VAP, pulmonary hemorrhage, and early-onset PH for model development.
Main Results:
- Four machine learning models were evaluated, with a selected model achieving 93.8% sensitivity, 85.0% accuracy, and 0.933 AUC.
- A logistic regression formula score greater than 0 was identified as a significant warning sign for BPD-PH.
- The developed model demonstrates high predictive performance for identifying infants at risk.
Conclusions:
- The study successfully developed a robust machine learning model for predicting BPD-PH in infants.
- This predictive model can aid pediatric clinicians in early diagnosis and personalized treatment strategies.
- The findings support the integration of AI in neonatal care for improved management of BPD-PH.
Background:
Bronchopulmonary dysplasia-associated pulmonary hypertension (BPD-PH) remains a devastating clinical complication seriously affecting the therapeutic outcome of preterm infants. Hence, early prevention and timely diagnosis prior to pathological change is the key to reducing morbidity and improving prognosis. Our primary objective is to utilize machine learning techniques to build predictive models that could accurately identify BPD infants at risk of developing PH.
Methods:
The data utilized in this study were collected from neonatology departments of four tertiary-level hospitals in China. To address the issue of imbalanced data, oversampling algorithms synthetic minority over-sampling technique (SMOTE) was applied to improve the model.
Results:
Seven hundred sixty one clinical records were collected in our study. Following data pre-processing and feature selection, 5 of the 46 features were used to build models, including duration of invasive respiratory support (day), the severity of BPD, ventilator-associated pneumonia, pulmonary hemorrhage, and early-onset PH. Four machine learning models were applied to predictive learning, and after comprehensive selection a model was ultimately selected. The model achieved 93.8% sensitivity, 85.0% accuracy, and 0.933 AUC. A score of the logistic regression formula greater than 0 was identified as a warning sign of BPD-PH.
Conclusions:
We comprehensively compared different machine learning models and ultimately obtained a good prognosis model which was sufficient to support pediatric clinicians to make early diagnosis and formulate a better treatment plan for pediatric patients with BPD-PH.
