Related Experiment Video
Updated: Feb 18, 2026
Increasing Pulmonary Artery Pulsatile Flow Improves Hypoxic Pulmonary Hypertension in Piglets
Published on: May 11, 2015
Predicting pulmonary hypertension in infants with bronchopulmonary dysplasia
Henry P Foote1, Minghui Sun2, Benjamin Alan Goldstein2
1Department of Pediatrics, Duke University Medical Center, Durham, NC, USA.
Insights
Researchers developed predictive models for pulmonary hypertension (PH) in high-risk infants. These models, using clinical data, can identify infants at risk for PH at two key time points.
Area of Science:
- Neonatal Medicine
- Cardiology
- Data Science in Healthcare
Background:
- Pulmonary hypertension (PH) is a serious complication in high-risk infants.
- Early identification of PH is crucial for timely intervention and improved outcomes.
Purpose of the Study:
- To develop and validate predictive models for PH in infants born between 22-28 weeks gestational age.
- To identify infants at high risk for PH at two critical time points: 33 and 36 weeks post-menstrual age (PMA).
Main Methods:
- A multicenter cohort study included infants from 2008-2020.
- Logistic Regression (LR) and Long Short-Term Memory (LSTM) models were trained using clinical variables.
- Models were validated on a temporal cohort of infants discharged between 2021-2022.
Main Results:
- At 33 weeks PMA, fraction of inspired oxygen and birth weight were key predictors in the LR model.
- At 36 weeks PMA, respiratory support and birth weight were primary predictors in the LR model.
- Both LR and LSTM models demonstrated strong predictive performance in the validation cohort.
Conclusions:
- Validated predictive models using readily available clinical data can identify high-risk infants for PH.
- These models offer a potential tool for early PH risk stratification in neonatal intensive care unit (NICU) graduates.
- Further research can refine these models for clinical implementation.
Objective:
Develop and validate predictive models for pulmonary hypertension (PH) in high-risk infants.
Study Design:
We trained logistic regression (LR) and long short-term memory (LSTM) models using a multicenter cohort study of infants 22-28 weeks gestational age discharged from neonatal intensive care units from 2008 to 2020, at two timepoints: 33 weeks post-menstrual age (PMA) for infants receiving mechanical ventilation at that time, and 36 weeks PMA for infants receiving any respiratory support at that time.
Results:
At 33 weeks PMA (N = 2849), top LR model predictors were current fraction of inspired oxygen and birth weight. At 36 weeks (N = 20,173), top LR model predictors were current respiratory support and birth weight. Both LR and LSTM models had strong performance in the temporal validation cohort (infants discharged 2021-2022) for both timepoints.
Conclusion:
Using available clinical variables, we developed and validated predictive models that may identify infants most at risk for PH at two timepoints.
