Related Experiment Video
Updated: Jul 15, 2025
Using an Automated Hirschberg Test App to Evaluate Ocular Alignment
Published on: March 24, 2020
Development and validation of an artificial intelligence based screening tool for detection of retinopathy of
Divya Parthasarathy Rao1, Florian M Savoy2, Joshua Zhi En Tan2
1Artificial Intelligence Research and Development, Remidio Innovative Solutions Inc., Glen Allen, VA, United States.
Insights
A new AI algorithm effectively screens for retinopathy of prematurity (ROP) in infants, showing high accuracy. This tool could reduce specialist screening needs, improving efficiency for high-risk preterm infants.
Area of Science:
- Ophthalmology
- Artificial Intelligence
- Medical Imaging
Background:
- Retinopathy of prematurity (ROP) is a leading cause of childhood blindness.
- Early detection and treatment are crucial for preventing vision loss in preterm infants.
- Current screening methods can be resource-intensive and require specialized expertise.
Purpose of the Study:
- To develop and validate an artificial intelligence (AI) algorithm for screening retinopathy of prematurity (ROP).
- To assess the algorithm's performance as a diagnostic tool in a real-world setting.
Main Methods:
- A deep learning (DL) algorithm was developed using 227,326 wide-field retinal images from the KIDROP tele-ROP screening program in India.
- The dataset, comprising 37,477 temporal retina images, was split into training, validation, and independent test sets.
- The algorithm functions as a binary classifier to detect ROP (Stages 1-3) versus absence of ROP, with labels derived from expert ROP grader diagnoses.
Main Results:
- The AI algorithm achieved high sensitivity (91.46%) and specificity (91.22%) in detecting ROP on an independent test set of 7,489 images.
- The positive predictive value (PPV) was 81.72% and the negative predictive value (NPV) was 96.14%.
- The area under the receiver operating characteristic curve (AUROC) was 0.970, indicating excellent discriminatory performance.
Conclusions:
- The developed AI algorithm demonstrates significant potential as a screening tool for retinopathy of prematurity.
- Its high accuracy suggests it could streamline ROP screening processes.
- Prospective clinical validation on a tele-ROP platform is planned to further evaluate its real-world utility and workflow efficiency benefits.
Purpose:
The primary objective of this study was to develop and validate an AI algorithm as a screening tool for the detection of retinopathy of prematurity (ROP).
Participants:
Images were collected from infants enrolled in the KIDROP tele-ROP screening program.
Methods:
We developed a deep learning (DL) algorithm with 227,326 wide-field images from multiple camera systems obtained from the KIDROP tele-ROP screening program in India over an 11-year period. 37,477 temporal retina images were utilized with the dataset split into train (n = 25,982, 69.33%), validation (n = 4,006, 10.69%), and an independent test set (n = 7,489, 19.98%). The algorithm consists of a binary classifier that distinguishes between the presence of ROP (Stages 1-3) and the absence of ROP. The image labels were retrieved from the daily registers of the tele-ROP program. They consist of per-eye diagnoses provided by trained ROP graders based on all images captured during the screening session. Infants requiring treatment and a proportion of those not requiring urgent referral had an additional confirmatory diagnosis from an ROP specialist.
Results:
Of the 7,489 temporal images analyzed in the test set, 2,249 (30.0%) images showed the presence of ROP. The sensitivity and specificity to detect ROP was 91.46% (95% CI: 90.23%-92.59%) and 91.22% (95% CI: 90.42%-91.97%), respectively, while the positive predictive value (PPV) was 81.72% (95% CI: 80.37%-83.00%), negative predictive value (NPV) was 96.14% (95% CI: 95.60%-96.61%) and the AUROC was 0.970.
Conclusion:
The novel ROP screening algorithm demonstrated high sensitivity and specificity in detecting the presence of ROP. A prospective clinical validation in a real-world tele-ROP platform is under consideration. It has the potential to lower the number of screening sessions required to be conducted by a specialist for a high-risk preterm infant thus significantly improving workflow efficiency.
