Machine learning-driven prediction of cycloplegic refractive error in Chinese children

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.