Related Experiment Video
Updated: May 13, 2026
Oxygen-Induced Retinopathy Model for Ischemic Retinal Diseases in Rodents
Published on: September 16, 2020
Prediction models for retinopathy of prematurity occurrence based on artificial neural network
Rong Wu1, He Chen2, Yichen Bai1
1Department of Ophthalmology, Zhujiang Hospital, Southern Medical University, No.253 Gongyedadao Middle Road City, Guangzhou, Guangdong, 510282, China.
Insights
Predicting retinopathy of prematurity (ROP) is crucial for preventing blindness. Artificial neural networks, particularly the GA-BP model, show strong predictive capabilities for ROP occurrence in infants.
Area of Science:
- Ophthalmology
- Medical Informatics
- Artificial Intelligence
Background:
- Early detection of retinopathy of prematurity (ROP) is vital to prevent vision loss.
- ROP screening is a critical component of routine clinical care for premature infants.
Purpose of the Study:
- To develop artificial neural network (ANN) models for predicting ROP occurrence.
- To identify key perinatal risk factors associated with ROP.
Main Methods:
- A retrospective study of 591 infants analyzed ROP risk factors using univariate and multivariable logistic regression.
- Predictive models were created using backpropagation (BP) neural networks and optimized with a genetic algorithm (GA-BP).
- Model performance was evaluated using AUC, sensitivity, specificity, NPV, PPV, and accuracy.
Main Results:
- ROP was diagnosed in 32.7% of the infants (193 out of 591).
- Twelve significant ROP risk factors were identified.
- The GA-BP neural network model achieved a superior area under the curve (AUC) of 0.908 compared to the BP model (0.857) in prediction.
Conclusions:
- ANN models were successfully developed for ROP prediction.
- The GA-BP neural network demonstrated enhanced predictive performance for ROP, effectively handling non-linear clinical data.
Introduction:
Early prediction and timely treatment are essential for minimizing the risk of visual loss or blindness of retinopathy of prematurity, emphasizing the importance of ROP screening in clinical routine.
Objective:
To establish predictive models for ROP occurrence based on the risk factors using artificial neural network.
Methods:
A cohort of 591 infants was recruited in this retrospective study. The association between ROP and perinatal factors was analyzed by univariate analysis and multivariable logistic regression. We developed predictive models for ROP screening using back propagation neural network, which was further optimized by applying genetic algorithm method. To assess the predictive performance of the models, the areas under the curve, sensitivity, specificity, negative predictive value, positive predictive value and accuracy were used to show the performances of the prediction models.
Results:
ROP of any stage was found in 193 (32.7%) infants. Twelve risk factors of ROP were selected. Based on these factors, predictive models were built using BP neural network and genetic algorithm-back propagation (GA-BP) neural network. The areas under the curve for prediction models were 0.857, and 0.908 in test, respectively.
Conclusions:
We developed predictive models for ROP using artificial neural network. GA-BP neural network exhibited superior predictive ability for ROP when dealing with its non-linear clinical data.
