Related Experiment Videos
The Pediatric Pulmonary Hypertension International Risk Score: A Prediction Model for Outcomes Using Machine Learning
Megan Griffiths1, Bhargava K Chinni2, Chantal Lokhorst3
1Heart Center, Children's Health, Division of Cardiology, Department of Pediatrics, UT Southwestern Medical Center, Dallas, TX (M.G.).
Circulation
|August 11, 2026
Summary
A new data-driven model accurately predicts 1-year risk in pediatric pulmonary hypertension (PH). This tool aids clinical decisions for children with PH, improving care by stratifying risk effectively.
Area of Science:
- Pediatric Cardiology
- Pulmonary Hypertension Research
- Biostatistics and Predictive Modeling
Background:
- Pediatric pulmonary hypertension (PH) care lacks specific risk prediction models, often relying on adult data or expert opinion.
- Current models are limited, hindering effective risk stratification and treatment guidance for pediatric PH patients.
- A need exists for validated, data-driven tools tailored to the unique characteristics of pediatric PH.
Purpose of the Study:
- To develop and externally validate a data-driven 1-year risk prediction model for pediatric pulmonary hypertension (PH).
- To identify key predictors for a 1-year composite outcome including death, transplant, or specific surgical interventions.
- To provide a robust tool for clinical risk stratification in pediatric PH.
Main Methods:
- A cohort of 345 pediatric PH patients (World Symposium on Pulmonary Hypertension groups 1 and 3) was used for model development (80% training, 20% testing).
- BorutaSHAP and random forest identified 16 predictors from 176 variables; extreme gradient boosting modeled the 1-year outcome.
- External validation was performed using the Dutch National Registry for Pulmonary Hypertension in Childhood (n=155) and the Spanish Registry of Pediatric Pulmonary Hypertension (n=327).
Main Results:
- The model achieved an area under the receiver operating characteristic curve (AUC) of 0.90 in the test cohort, with a 99% negative predictive value.
- External validation demonstrated good performance with AUCs of 0.76 and 0.77 in the Dutch and Spanish registries, respectively.
- Kaplan-Meier analysis confirmed significant differentiation of outcomes among risk groups defined by the model.
Conclusions:
- A multicenter, validated model offers reliable 1-year risk prediction for pediatric PH (World Symposium on Pulmonary Hypertension groups 1 and 3).
- This data-driven tool addresses a critical gap in pediatric PH care by enabling accurate clinical risk stratification.
- The model serves as a robust instrument to guide therapy decisions and improve outcomes for children with PH.