Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

An Update on Retinal Diseases: From Diagnosis to Treatment.

Journal of clinical medicine·2026
Same author

Changes in antibody titers over time after infection in Bizen City, Japan.

Japanese journal of infectious diseases·2026
Same author

Bleeding Diathesis in Hypotrichosis-Lymphedema-Telangiectasia Syndrome due to Decreased von Willebrand Factor.

American journal of medical genetics. Part A·2026
Same author

A congenital infant-type hemispheric glioma case with EML4::ALK fusion.

Child's nervous system : ChNS : official journal of the International Society for Pediatric Neurosurgery·2026
Same author

PHOX2B deletion in congenital central hypoventilation syndrome: is this sufficient for pathogenesis?

Journal of human genetics·2025
Same author

Visual outcomes and anatomical biomarkers of Faricimab for diabetic macular edema in the J-CREST real-world comparison of naïve and treated eyes.

Scientific reports·2025

Related Experiment Video

Updated: May 16, 2025

Oxygen-Induced Retinopathy Model for Ischemic Retinal Diseases in Rodents
09:28

Oxygen-Induced Retinopathy Model for Ischemic Retinal Diseases in Rodents

Published on: September 16, 2020

8.3K

Prediction Models for Retinopathy of Prematurity Using Nonimaging Machine Learning Approaches: A Regional Multicenter

Yusuke Takeda1, Yutaka Kaneko1, Masahiko Sugimoto1

  • 1Department of Ophthalmology and Visual Sciences, Yamagata University Faculty of Medicine, Yamagata, Japan.

Ophthalmology Science
|April 4, 2025
PubMed
Summary

Machine learning models accurately predict retinopathy of prematurity (ROP) using only clinical data. These nonimaging approaches are valuable when fundus imaging is not feasible, aiding early ROP detection.

Keywords:
Machine learningMulticenter studyNonimagingRetinopathy of prematurity

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
12:28

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Published on: March 12, 2022

3.5K

Related Experiment Videos

Last Updated: May 16, 2025

Oxygen-Induced Retinopathy Model for Ischemic Retinal Diseases in Rodents
09:28

Oxygen-Induced Retinopathy Model for Ischemic Retinal Diseases in Rodents

Published on: September 16, 2020

8.3K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
12:28

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Published on: March 12, 2022

3.5K

Area of Science:

  • Neonatal Medicine
  • Machine Learning in Healthcare
  • Ophthalmology

Background:

  • Retinopathy of prematurity (ROP) is a significant cause of visual impairment in premature infants.
  • Early detection and management of ROP are crucial to prevent vision loss.
  • Predictive models can aid in identifying high-risk infants for timely intervention.

Purpose of the Study:

  • To develop and evaluate nonimaging machine learning models for predicting ROP occurrence.
  • Utilize readily available clinical data from the first screening of neonates.

Main Methods:

  • A multicenter study in Japan collected clinical data from 215 neonates.
  • Five machine learning models (decision tree, random forest, gradient-boosted tree, neural network, Naive Bayes) were developed using 35 variables.
  • 10-fold cross-validation and 200 iterations were used for parameter tuning and model evaluation.

Main Results:

  • 43 out of 215 neonates (20.0%) developed ROP.
  • The Naive Bayes model achieved a mean AUC-ROC of 0.94, accuracy of 90.6%, sensitivity of 94.6%, and specificity of 73.6%.
  • The Random Forest model showed comparable performance with a mean AUC-ROC of 0.93 and accuracy of 90.1%.

Conclusions:

  • Nonimaging machine learning models demonstrate high performance in predicting ROP.
  • These models offer a valuable alternative when fundus imaging is challenging due to factors like eye opacity.
  • The study highlights the potential of AI in neonatal eye care, especially in resource-limited settings.