EUVIMEDEUVIMED entdecken
Open Access

The Pediatric Pulmonary Hypertension International Risk Score: A Prediction Model for Outcomes Using Machine Learning

Megan Griffiths iD, Bhargava K Chinni iD, Chantal Lokhorst iD, Johannes M Douwes iD, Lynn A Sleeper iD, Jennifer Tingo iD, Steven H Abman iD, Erika B Rosenzweig iD, Jennifer E Schramm iD, Eric D Austin iD, Mary P Mullen iD, Alba Torrent-Vernetta iD und 6 weitere

Circulation · 01.09.2026 · 154 (9) · 805-818

DOI: 10.1161/circulationaha.125.077391 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Circulation, erschienen am 01.09.2026. Verfasst von Megan Griffiths und 17 weiteren Autor:innen. Beteiligte Einrichtung: Heart Center, Children's Health, Division of Cardiology, Department of Pediatrics, UT Southwestern Medical Center, Dallas, TX (M.G.). Hauptthemen laut MEDLINE: Hypertension, Pulmonary, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Risk prediction is fundamental to pulmonary hypertension (PH) guideline-based care, yet pediatric-specific risk prediction models remain limited, relying primarily on single predictors, expert opinion, or application of adult models to children. The authors developed and externally validated a data-driven 1-year risk prediction model for pediatric PH. METHODS: Pediatric patients with PH (n=345; World Symposium on Pulmonary Hypertension groups 1 and 3) enrolled in the Pediatric Pulmonary Hypertension Network Registry (2014–2020; 50.4% male; median age, 4.9 years [interquartile range, 1.9–10.3]) were split into training (80%) and test cohorts (20%). The Dutch National Registry for Pulmonary Hypertension in Childhood (n=155 [1993–2020]) and the Spanish Registry of Pediatric Pulmonary Hypertension (n=327 [2009–2023]) were used for external validation. From 176 variables, BorutaSHAP feature selection with random forest identified 16 predictors for a 1-year outcome of time to death, transplant, Potts shunt, or atrial septostomy, modeled using extreme gradient boosting. Performance was assessed with the area under the receiver operating characteristic curve, confusion matrices, calibration, and Kaplan-Meier event-free survival. RESULTS: The final model achieved an area under the receiver operating characteristic curve of 0.90 (0.79–0.97) and 99% (96%–99%) negative predictive value in testing, dividing participants into 3 groups with strong outcome discrimination. External validation showed an area under the receiver operating characteristic curve of 0.76 (Dutch National Registry for Pulmonary Hypertension in Childhood, 0.70–0.81) and 0.77 (Spanish Registry of Pediatric Pulmonary Hypertension, 0.73–0.82) with negative predictive values of 93% (93%–97%) and 96% (93%–97%), respectively. Kaplan-Meier analysis significantly differentiated outcomes by risk group. CONCLUSIONS: This multicenter, validated model provides good 1-year risk prediction in pediatric PH across World Symposium on Pulmonary Hypertension groups 1 and 3, providing a robust tool for clinical risk stratification to guide therapy and addressing a gap in pediatric PH care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Hypertension, PulmonaryMachine LearningHumansChildFemaleChild, PreschoolMaleRegistriesPredictive Learning ModelsInfantRisk AssessmentRisk FactorsPredictive Value of TestsPrediction AlgorithmsPrognosisClassification Algorithms

Stichwörter der Autor:innen

boosting machine learning algorithmshypertensionmachine learningpediatricpulmonary

Autor:innen und Institutionen

  • Heart Center, Children's Health, Division of Cardiology, Department of Pediatrics, UT Southwestern Medical Center, Dallas, TX (M.G.).
  • Blalock-Taussig-Thomas Congenital Heart Center, Department of Pediatrics, Johns Hopkins University, Baltimore, MD (B.K.C., A.D.E.).
  • Center for Congenital Heart Diseases, Department of Pediatric Cardiology, Beatrix Children's Hospital, University Medical Center Groningen, University of Groningen, The Netherlands (C. Lokhorst, J.M.D., R.M.F.B.).
  • Department of Cardiology, Boston Children's Hospital and Department of Pediatrics, Harvard Medical School, MA (L.A.S., M.P.M.).
  • Division of Cardiology, Children's Hospital of Philadelphia, PA (J.T.).
  • Department of Pediatrics, University of Pennsylvania Perelman School of Medicine, Philadelphia (J.T.).

ORCID-Profile: Megan Griffiths, Bhargava K Chinni, Chantal Lokhorst, Johannes M Douwes, Lynn A Sleeper, Jennifer Tingo, Steven H Abman, Erika B Rosenzweig, Jennifer E Schramm, Eric D Austin, Mary P Mullen, Alba Torrent-Vernetta, Carlos Labrandero, Raymond Benza, Rolf M F Berger, Allen D Everett

Förderung

  • NHLBI NIH HHS

Zitieren

APA

Griffiths, M., Chinni, B. K., Lokhorst, C., Douwes, J. M., Sleeper, L. A., Tingo, J., Abman, S. H., Rosenzweig, E. B., Schramm, J. E., Austin, E. D., Mullen, M. P., Torrent-Vernetta, A., Labrandero, C., Benza, R., Jesus Del Cerro, M., Berger, R. M. F., Manlhiot, C., & Everett, A. D. (2026). The Pediatric Pulmonary Hypertension International Risk Score: A Prediction Model for Outcomes Using Machine Learning. Circulation, 154(9), 805-818. https://doi.org/10.1161/circulationaha.125.077391

Vancouver

Griffiths M, Chinni BK, Lokhorst C, Douwes JM, Sleeper LA, Tingo J, et al. The Pediatric Pulmonary Hypertension International Risk Score: A Prediction Model for Outcomes Using Machine Learning. Circulation. 2026;154(9):805-818. doi:10.1161/circulationaha.125.077391

BibTeX
@article{Griffiths2026,
  author = {Griffiths, Megan and Chinni, Bhargava K and Lokhorst, Chantal and Douwes, Johannes M and Sleeper, Lynn A and Tingo, Jennifer and Abman, Steven H and Rosenzweig, Erika B and Schramm, Jennifer E and Austin, Eric D and Mullen, Mary P and Torrent-Vernetta, Alba and Labrandero, Carlos and Benza, Raymond and Jesus Del Cerro, Maria and Berger, Rolf M F and Manlhiot, Cedric and Everett, Allen D},
  title = {The Pediatric Pulmonary Hypertension International Risk Score: A Prediction Model for Outcomes Using Machine Learning},
  journal = {Circulation},
  year = {2026},
  volume = {154},
  number = {9},
  pages = {805--818},
  doi = {10.1161/circulationaha.125.077391}
}
Kostenlos starten →