EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Prediction of Retinopathy of Prematurity and Treatment in Very Low Birth Weight Infants Using Machine Learning on Nationwide Non-Imaging Clinical Data

Jae Kyoon Hwang, Donggoo Jung, Hyun-Kyung Park, Daehyun Kim, Hyun Jeong Do, Seong Hee Oh, Seung Hyun Kim, Tae Hyun Kim, Hyunseung Jin

Neonatology · 2026

DOI: 10.1159/000550513 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neonatology, 2026. Verfasst von Jae Kyoon Hwang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatrics, Hanyang University College of Medicine, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Retinopathy of Prematurity, Infant, Very Low Birth Weight, Machine Learning. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Retinopathy of prematurity (ROP) remains a leading cause of preventable blindness in preterm infants. This study aimed to develop machine learning (ML) models using non-imaging clinical data to predict ROP, severe ROP (sROP), and treated ROP (tROP) in very low birth weight (VLBW) infants.

Methods

We utilized nationwide clinical data from the Korean Neonatal Network, including 44 perinatal and neonatal variables. Two deep learning models, Multilayer Perceptron (MLP) and Neural Oblivious Decision Ensembles (NODE), optimized for tabular data, were applied. Additionally, we developed simplified models using eight key variables selected through clinical and algorithmic relevance.

Results

MLP and NODE models demonstrated high predictive performance. For the full 44-variable models, the area under the receiver operating characteristic curve (AUROC) was as follows: ROP (0.853/0.855), sROP (0.888/0.890), and tROP (0.905/0.909). The reduced 8-variable models yielded comparable AUROCs: ROP (0.851/0.855), sROP (0.895/0.895), and tROP (0.910/0.909).

Conclusion

The proposed ML models based on nationwide non-imaging clinical data enable early risk identification and timely intervention for ROP in VLBW infants. This cost-effective and scalable approach may help improve outcomes, especially in resource-limited settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Retinopathy of PrematurityInfant, Very Low Birth WeightMachine LearningHumansInfant, NewbornPredictive Learning ModelsMultilayer PerceptronsFemaleRepublic of KoreaInfant, PrematureMaleROC CurveGestational AgePrediction AlgorithmsPredictive Value of Tests

Stichwörter der Autor:innen

Machine learningMultilayer PerceptronNeural Oblivious Decision EnsemblesRetinopathy of prematurityVery low birth weight infants

Autor:innen und Institutionen

  • Department of Pediatrics, Hanyang University College of Medicine, Seoul, Republic of Korea.
  • Department of Artificial Intelligence, Hanyang University, Seoul, Republic of Korea.
  • Department of Pediatrics, Gangneung Asan Hospital, University of Ulsan College of Medicine, Gangneung, Republic of Korea.
  • Department of Pediatrics, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea.
  • Department of Computer Science, Hanyang University, Seoul, Republic of Korea, taehyunkim@hanyang.ac.kr.
  • Department of Pediatrics, Gangneung Asan Hospital, University of Ulsan College of Medicine, Gangneung, Republic of Korea, solchani72@ulsan.ac.kr.

Zitieren

APA

Hwang, J. K., Jung, D., Park, H. K., Kim, D., Do, H. J., Oh, S. H., Kim, S. H., Kim, T. H., & Jin, H. (2026). Prediction of Retinopathy of Prematurity and Treatment in Very Low Birth Weight Infants Using Machine Learning on Nationwide Non-Imaging Clinical Data. Neonatology. https://doi.org/10.1159/000550513

Vancouver

Hwang JK, Jung D, Park HK, Kim D, Do HJ, Oh SH, et al. Prediction of Retinopathy of Prematurity and Treatment in Very Low Birth Weight Infants Using Machine Learning on Nationwide Non-Imaging Clinical Data. Neonatology. 2026. doi:10.1159/000550513

BibTeX
@article{Hwang2026,
  author = {Hwang, Jae Kyoon and Jung, Donggoo and Park, Hyun-Kyung and Kim, Daehyun and Do, Hyun Jeong and Oh, Seong Hee and Kim, Seung Hyun and Kim, Tae Hyun and Jin, Hyunseung},
  title = {Prediction of Retinopathy of Prematurity and Treatment in Very Low Birth Weight Infants Using Machine Learning on Nationwide Non-Imaging Clinical Data},
  journal = {Neonatology},
  year = {2026},
  doi = {10.1159/000550513}
}
Kostenlos starten →