EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access

Machine Learning Risk Prediction for Treated Retinopathy of Prematurity in Infants

Henry P Foote, Yanchen J Ou, Suchir Bhatt, Matthew M Engelhard, Leonid Bederman, Matthew M Laughon, Kanecia O Zimmerman, Rishikesan Kamaleswaran, Rachel G Greenberg, Veeral N Tolia, Christoph P Hornik, Ricardo Henao und 1 weitere

Neonatology · 2025

DOI: 10.1159/000549574 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Neonatology, 2025. Verfasst von Henry P Foote und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatrics, Duke University, Durham, North Carolina, USA. Hauptthemen laut MEDLINE: Retinopathy of Prematurity, Machine Learning. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIMH NIH HHS, NHLBI NIH HHS, NIGMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Retinopathy of prematurity (ROP) is a leading cause of childhood blindness. However, current screening guidelines may be overly broad, necessitating better models to detect high-risk infants.

Methods

From a multicenter cohort of 103,701 infants (3,301 [3.2%] treated for ROP) discharged from 298 neonatal intensive care units from 2006 to 2017 with birth weight ≤1,500 grams or gestational age ≤30 weeks, we used clinically relevant variables to develop machine learning (ML) models at 2-week intervals from postnatal day 14 to 98 to stratify infants by ROP treatment timing. We assessed model performance by concordance index, area under the receiver operating characteristic curve (AUROC), and average precision (AP), validated performance in a cohort of 25,105 infants across 231 sites from 2018 to 2020, and compared model performance to a logistic regression (LR) model.

Results

In the validation cohort, the day 28 ML model outperformed the LR model by AUROC (0.916 [0.905–0.926] vs. 0.903 [0.892–0.914]; p < 0.001) and AP (0.190 [0.167–0.217] vs. 0.160 [0.140–0.183]; p < 0.001). Using the ML model at a 100% sensitivity threshold would have negative predictive value of >99.9% and could reduce the number of infants needing screening by 14% compared to current guidelines.

Conclusion

ML models can effectively predict the need for ROP treatment and stratify infants by risk, potentially reducing unneeded screening. Future work is needed to translate model-based ROP predictions to the clinical setting.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Retinopathy of PrematurityMachine LearningHumansInfant, NewbornRisk AssessmentFemaleMaleGestational AgeROC CurveInfantInfant, PrematureIntensive Care Units, NeonatalRisk FactorsLogistic ModelsPredictive Value of TestsInfant, Very Low Birth Weight

Stichwörter der Autor:innen

Machine learningPrediction modelPrematurityRetinopathy of prematurityVery low birth weight

Autor:innen und Institutionen

  • Department of Pediatrics, Duke University, Durham, North Carolina, USA.
  • Department of Computer Science, Duke University, Durham, North Carolina, USA.
  • Department of Biostatistics and Bioinformatics, Duke University, Durham, North Carolina, USA.
  • Department of Pediatrics, Emory University, Atlanta, Georgia, USA.
  • Department of Pediatrics, School of Medicine, University of North Carolina Chapel Hill, Chapel Hill, North Carolina, USA.
  • Duke Clinical Research Institute, Durham, North Carolina, USA.

Förderung

  • NIMH NIH HHS
  • NHLBI NIH HHS
  • NIGMS NIH HHS
  • NICHD NIH HHS

Zitieren

APA

Foote, H. P., Ou, Y. J., Bhatt, S., Engelhard, M. M., Bederman, L., Laughon, M. M., Zimmerman, K. O., Kamaleswaran, R., Greenberg, R. G., Tolia, V. N., Hornik, C. P., Henao, R., & Kumar, K. R. (2025). Machine Learning Risk Prediction for Treated Retinopathy of Prematurity in Infants. Neonatology. https://doi.org/10.1159/000549574

Vancouver

Foote HP, Ou YJ, Bhatt S, Engelhard MM, Bederman L, Laughon MM, et al. Machine Learning Risk Prediction for Treated Retinopathy of Prematurity in Infants. Neonatology. 2025. doi:10.1159/000549574

BibTeX
@article{Foote2025,
  author = {Foote, Henry P and Ou, Yanchen J and Bhatt, Suchir and Engelhard, Matthew M and Bederman, Leonid and Laughon, Matthew M and Zimmerman, Kanecia O and Kamaleswaran, Rishikesan and Greenberg, Rachel G and Tolia, Veeral N and Hornik, Christoph P and Henao, Ricardo and Kumar, Karan R},
  title = {Machine Learning Risk Prediction for Treated Retinopathy of Prematurity in Infants},
  journal = {Neonatology},
  year = {2025},
  doi = {10.1159/000549574}
}
Kostenlos starten →