Related Experiment Video
Updated: Sep 7, 2025
Oxygen-Induced Retinopathy Model for Ischemic Retinal Diseases in Rodents
Published on: September 16, 2020
Development and Validation of a Deep Learning Model to Predict the Occurrence and Severity of Retinopathy of
Qiaowei Wu1,2, Yijun Hu1, Zhenyao Mo3
1Guangdong Eye Institute, Department of Ophthalmology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China.
Insights
A deep learning system shows promise in predicting retinopathy of prematurity (ROP) and its severity. This AI tool can help identify infants at high risk, potentially reducing childhood blindness caused by ROP.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence
Background:
- Retinopathy of prematurity (ROP) is a leading cause of childhood blindness globally.
- Early prediction of ROP is crucial for timely intervention and preventing vision loss.
Purpose of the Study:
- To develop and validate a deep learning (DL) system for predicting the occurrence and severity of ROP.
- The system aims to predict ROP before 45 weeks' postmenstrual age.
Main Methods:
- A retrospective study utilized 7033 retinal images from 725 infants for training and 763 images from 90 infants for external validation.
- Two DL models, OC-Net for occurrence and SE-Net for severity, were developed using retinal photographs and infant clinical characteristics.
- Internal validation used five-fold cross-validation; performance was evaluated using AUC, accuracy, sensitivity, and specificity.
Main Results:
- Internal validation showed mean AUCs of 0.90 for OC-Net and 0.87 for SE-Net.
- External validation yielded AUCs of 0.94 for OC-Net and 0.88 for SE-Net.
- Both models demonstrated high sensitivity (100%) in predicting ROP occurrence and severity.
Conclusions:
- The developed DL system demonstrated promising accuracy in predicting ROP.
- This AI tool has the potential to identify high-risk infants, aiding in the prevention of ROP-related blindness.
Importance:
Retinopathy of prematurity (ROP) is the leading cause of childhood blindness worldwide. Prediction of ROP before onset holds great promise for reducing the risk of blindness.
Objective:
To develop and validate a deep learning (DL) system to predict the occurrence and severity of ROP before 45 weeks' postmenstrual age.
Design, Setting, And Participants:
This retrospective prognostic study included 7033 retinal photographs of 725 infants in the training set and 763 retinal photographs of 90 infants in the external validation set, along with 46 characteristics for each infant. All images of both eyes from the same infant taken at the first screening were labeled according to the final diagnosis made between the first screening and 45 weeks' postmenstrual age. The DL system was developed using retinal photographs from the first ROP screening and clinical characteristics before or at the first screening in infants born between June 3, 2017, and August 28, 2019.
Exposures:
Two models were specifically designed for predictions of the occurrence (occurrence network [OC-Net]) and severity (severity network [SE-Net]) of ROP. Five-fold cross-validation was applied for internal validation.
Main Outcomes And Measures:
Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity to evaluate the performance in ROP prediction.
Results:
This study included 815 infants (450 [55.2%] boys) with mean birth weight of 1.91 kg (95% CI, 1.87-1.95 kg) and mean gestational age of 33.1 weeks (95% CI, 32.9-33.3 weeks). In internal validation, mean AUC, accuracy, sensitivity, and specificity were 0.90 (95% CI, 0.88-0.92), 52.8% (95% CI, 49.2%-56.4%), 100% (95% CI, 97.4%-100%), and 37.8% (95% CI, 33.7%-42.1%), respectively, for OC-Net to predict ROP occurrence and 0.87 (95% CI, 0.82-0.91), 68.0% (95% CI, 61.2%-74.8%), 100% (95% CI, 93.2%-100%), and 46.6% (95% CI, 37.3%-56.0%), respectively, for SE-Net to predict severe ROP. In external validation, the AUC, accuracy, sensitivity, and specificity were 0.94, 33.3%, 100%, and 7.5%, respectively, for OC-Net, and 0.88, 56.0%, 100%, and 35.3%, respectively, for SE-Net.
Conclusions And Relevance:
In this study, the DL system achieved promising accuracy in ROP prediction. This DL system is potentially useful in identifying infants with high risk of developing ROP.
