Related Experiment Video
Updated: Nov 16, 2025
Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System
Published on: March 17, 2023
Applications of Artificial Intelligence for Retinopathy of Prematurity Screening
J Peter Campbell1,2, Praveer Singh3,2, Travis K Redd4
1Department of Ophthalmology, Casey Eye Institute and campbelp@ohsu.edu.
Insights
Artificial intelligence (AI) effectively screens for retinopathy of prematurity (ROP) in India. AI identified higher ROP severity in neonatal care units lacking advanced oxygen monitoring, suggesting a link between care quality and infant eye disease.
Area of Science:
- Ophthalmology
- Neonatology
- Artificial Intelligence
Background:
- Childhood blindness due to retinopathy of prematurity (ROP) is rising globally.
- Improvements in neonatal care have increased survival rates of premature infants, leading to more ROP cases.
Purpose of the Study:
- To evaluate the effectiveness of an AI-based screening tool for ROP in an Indian telemedicine program.
- To determine if AI-identified ROP severity differences in neonatal care units (NCUs) correlate with oxygen management capabilities.
Main Methods:
- External validation of an AI-based ROP severity scale using images from an Indian telemedicine program.
- AI assigned ROP severity scores (1-9); performance metrics (AUC, sensitivity, specificity) were calculated for treatment-requiring ROP.
- Multivariable linear regression analyzed ROP severity in relation to birth weight, gestational age, and oxygen monitoring equipment (blenders, pulse oximetry).
Main Results:
- The AI tool achieved an area under the ROC curve of 0.98, with 100% sensitivity and 78% specificity for detecting treatment-requiring ROP.
- NCUs without oxygen blenders and pulse oximetry monitors showed higher median ROP severity, particularly in larger infants (>1500g, 31 weeks' gestation).
- This difference in ROP severity was statistically significant (P = .007) after adjusting for birth weight and gestational age.
Conclusions:
- AI integration in ROP screening can enhance access to care for secondary prevention.
- AI facilitates the assessment of ROP epidemiology and the evaluation of NCU resources.
- AI tools show promise in identifying disparities in neonatal care quality related to ROP outcomes.
Objectives:
Childhood blindness from retinopathy of prematurity (ROP) is increasing as a result of improvements in neonatal care worldwide. We evaluate the effectiveness of artificial intelligence (AI)-based screening in an Indian ROP telemedicine program and whether differences in ROP severity between neonatal care units (NCUs) identified by using AI are related to differences in oxygen-titrating capability.
Methods:
External validation study of an existing AI-based quantitative severity scale for ROP on a data set of images from the Retinopathy of Prematurity Eradication Save Our Sight ROP telemedicine program in India. All images were assigned an ROP severity score (1-9) by using the Imaging and Informatics in Retinopathy of Prematurity Deep Learning system. We calculated the area under the receiver operating characteristic curve and sensitivity and specificity for treatment-requiring retinopathy of prematurity. Using multivariable linear regression, we evaluated the mean and median ROP severity in each NCU as a function of mean birth weight, gestational age, and the presence of oxygen blenders and pulse oxygenation monitors.
Results:
The area under the receiver operating characteristic curve for detection of treatment-requiring retinopathy of prematurity was 0.98, with 100% sensitivity and 78% specificity. We found higher median (interquartile range) ROP severity in NCUs without oxygen blenders and pulse oxygenation monitors, most apparent in bigger infants (>1500 g and 31 weeks' gestation: 2.7 [2.5-3.0] vs 3.1 [2.4-3.8]; P = .007, with adjustment for birth weight and gestational age).
Conclusions:
Integration of AI into ROP screening programs may lead to improved access to care for secondary prevention of ROP and may facilitate assessment of disease epidemiology and NCU resources.
