Related Experiment Video
Updated: May 20, 2026
Comparison of Agreement and Accuracy using Binocular Wavefront Optometer with Autorefractor and Phoropter
Published on: September 16, 2025
Machine learning-driven prediction of cycloplegic refractive error in Chinese children
Bichi Chen1, Li Tian2, Fuyue Tian2
1Vision X Medical Technology Co., Ltd., Shanghai, China.
Insights
Machine learning models accurately predict cycloplegic spherical equivalent refraction (SER) using non-cycloplegic data in children. This offers a practical alternative for pediatric eye exams when cycloplegia is not feasible.
Area of Science:
- Ophthalmology
- Artificial Intelligence
- Biomedical Engineering
Background:
- Pediatric ophthalmic assessments often require cycloplegic refraction for accurate refractive error determination.
- Cycloplegia can be challenging in pediatric populations due to factors like patient cooperation and time constraints.
Purpose of the Study:
- To develop and validate machine learning (ML) models for predicting cycloplegic spherical equivalent refraction (SER) from non-cycloplegic parameters.
- To provide a practical alternative for pediatric refractive assessments.
Main Methods:
- Trained six ML models (linear regression, random forest, XGBoost, MLP, SVM, LGBM) on data from 2,274 Chinese children (ages 3-16).
- Utilized demographics, non-cycloplegic refractive error, and ocular biometrics for model training.
- Evaluated model performance using R², mean error (ME), mean absolute error (MAE), and clinical accuracy.
Main Results:
- ML models achieved high accuracy in predicting cycloplegic SER (R²: 0.920–0.934, MAE: 0.385–0.413 D).
- The multilayer perceptron model showed the best performance (R² = 0.934, MAE = 0.385 D), with 73.08% and 94.29% of predictions within ±0.50 D and ±1.00 D.
- Optimal performance was observed in children aged 7–10 years and those with low myopia.
Conclusions:
- Machine learning models can accurately estimate cycloplegic SER using non-cycloplegic measurements.
- These models offer a viable and practical alternative for pediatric refractive assessments, especially when cycloplegia is not feasible.
Objective:
To develop and validate machine learning (ML) models for predicting cycloplegic spherical equivalent refraction (SER) using non-cycloplegic parameters, addressing challenges in pediatric ophthalmic assessments.
Methods:
A prospective cohort of 2,274 Chinese children (4,548 eyes) aged 3∼16 years was stratified into development (n = 1819) and validation (n = 455) datasets. Six ML models (linear regression, random forest, extreme gradient boosting, multilayer perceptron, support vector machine, and light gradient boosting machine) were trained on demographics, non-cycloplegic refractive error, and ocular biometrics. Model performance was evaluated using R 2 , mean error (ME), mean absolute error (MAE), and clinical accuracy (proportions within ±0.50 D/±1.00 D).
Results:
In the validation dataset, ML models predicted cycloplegic SER with high R 2 (0.920∼0.934), low ME (-0.004∼0.015 D) and MAE (0.385∼0.413 D). The multilayer perceptron model achieved the highest accuracy (R 2 = 0.934, MAE = 0.385 D), with 73.08% and 94.29% of predictions within ±0.50 D and ±1.00 D, respectively. Performance was optimal in children aged 7∼10 years (77.17∼79.70% within ±0.50 D) and those with low myopia (-3.00 to -0.50 D; 83.09∼83.56% within ±0.50 D). Non-cycloplegic measurements systematically overestimated myopia (mean difference: -0.39 ± 0.71 D, P < 0.001), particularly in younger children and hyperopic eyes.
Conclusion:
ML models provide accurate estimates of cycloplegic SER using non-cycloplegic parameters, offering a practical alternative for pediatric refractive assessments when cycloplegia is infeasible.
