Related Experiment Video
Updated: Sep 5, 2025
Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System
Published on: March 17, 2023
External Validation of a Retinopathy of Prematurity Screening Model Using Artificial Intelligence in 3 Low- and
Aaron S Coyner1, Minn A Oh1, Parag K Shah2
1Casey Eye Institute, Oregon Health & Science University, Portland.
Insights
An AI-driven risk model accurately identifies infants at risk for retinopathy of prematurity (ROP), reducing unnecessary screenings and enabling early monitoring for high-risk infants in telemedicine programs.
Area of Science:
- Ophthalmology
- Artificial Intelligence
- Public Health
Background:
- Retinopathy of prematurity (ROP) is a major cause of preventable childhood blindness, particularly in low- and middle-income countries (LMICs).
- Implementing effective ROP screening in LMICs is hindered by a high number of at-risk infants and a shortage of trained ophthalmologists.
- Telemedicine offers a potential solution but requires efficient risk stratification tools.
Purpose of the Study:
- To develop and validate an artificial intelligence (AI) risk model for predicting treatment-requiring (TR)-ROP using retinal images.
- To assess the model's ability to identify infants needing close monitoring and reduce the number of examinations for low-risk infants within LMIC telemedicine programs.
Main Methods:
- A diagnostic study collected retinal fundus images from infants in an Indian ROP telemedicine program.
- An AI-derived vascular severity score (VSS) was calculated from baseline images.
- Logistic regression models, incorporating gestational age and VSS, were trained and externally validated across India, Nepal, and Mongolia to predict TR-ROP.
Main Results:
- The AI risk model demonstrated high sensitivity (100.0%) across all datasets for predicting TR-ROP.
- The model identified infants with TR-ROP earlier than clinical diagnosis (median 0-2 weeks prior).
- Implementing the model could reduce the number of required screenings by 38.4% to 51.3% across the study populations.
Conclusions:
- The AI-based risk model effectively identifies infants at risk for TR-ROP, enabling targeted screening.
- This approach significantly reduces the need for routine examinations in low-risk infants, optimizing resource allocation in LMIC telemedicine settings.
- Early identification of high-risk infants allows for timely intervention, preventing severe vision impairment or blindness.
Importance:
Retinopathy of prematurity (ROP) is a leading cause of preventable blindness that disproportionately affects children born in low- and middle-income countries (LMICs). In-person and telemedical screening examinations can reduce this risk but are challenging to implement in LMICs owing to the multitude of at-risk infants and lack of trained ophthalmologists.
Objective:
To implement an ROP risk model using retinal images from a single baseline examination to identify infants who will develop treatment-requiring (TR)-ROP in LMIC telemedicine programs.
Design, Setting, And Participants:
In this diagnostic study conducted from February 1, 2019, to June 30, 2021, retinal fundus images were collected from infants as part of an Indian ROP telemedicine screening program. An artificial intelligence (AI)-derived vascular severity score (VSS) was obtained from images from the first examination after 30 weeks' postmenstrual age. Using 5-fold cross-validation, logistic regression models were trained on 2 variables (gestational age and VSS) for prediction of TR-ROP. The model was externally validated on test data sets from India, Nepal, and Mongolia. Data were analyzed from October 20, 2021, to April 20, 2022.
Main Outcomes And Measures:
Primary outcome measures included sensitivity, specificity, positive predictive value, and negative predictive value for predictions of future occurrences of TR-ROP; the number of weeks before clinical diagnosis when a prediction was made; and the potential reduction in number of examinations required.
Results:
A total of 3760 infants (median [IQR] postmenstrual age, 37 [5] weeks; 1950 male infants [51.9%]) were included in the study. The diagnostic model had a sensitivity and specificity, respectively, for each of the data sets as follows: India, 100.0% (95% CI, 87.2%-100.0%) and 63.3% (95% CI, 59.7%-66.8%); Nepal, 100.0% (95% CI, 54.1%-100.0%) and 77.8% (95% CI, 72.9%-82.2%); and Mongolia, 100.0% (95% CI, 93.3%-100.0%) and 45.8% (95% CI, 39.7%-52.1%). With the AI model, infants with TR-ROP were identified a median (IQR) of 2.0 (0-11) weeks before TR-ROP diagnosis in India, 0.5 (0-2.0) weeks before TR-ROP diagnosis in Nepal, and 0 (0-5.0) weeks before TR-ROP diagnosis in Mongolia. If low-risk infants were never screened again, the population could be effectively screened with 45.0% (India, 664/1476), 38.4% (Nepal, 151/393), and 51.3% (Mongolia, 266/519) fewer examinations required.
Conclusions And Relevance:
Results of this diagnostic study suggest that there were 2 advantages to implementation of this risk model: (1) the number of examinations for low-risk infants could be reduced without missing cases of TR-ROP, and (2) high-risk infants could be identified and closely monitored before development of TR-ROP.
