Interpretable machine learning models for predicting childhood myopia from school-based screening data

This study assessed the efficacy of various diagnostic indicators and machine learning (ML) models in predicting childhood myopia. A total of 2,365 children aged 5–12 years were included in the study. The participants were exposed to non-cycloplegic and cycloplegic refraction tests, along with ocular biometric assessments. Cycloplegia was induced using 1% cyclopentolate eye drops, followed by cycloplegic refraction testing. Myopia prevalence was 11.2% (95% confidence interval: 9.9–12.5%). The spherical equivalent (SE) before and after cycloplegia varied with age, significantly differing by 0.5D in children < 10 years (P < 0.05). The most effective single-indicator screening diagnostic methods were axial length/ corneal curvature radius (AL/CCR) and screening myopia, with area under curve (AUC) of 0.919 (95% CI: 0.899 to 0.939) and 0.911 (95% CI: 0.890 to 0.932). In the multi-indicator joint diagnostic model, the best diagnostic model using non-cycloplegic SE, uncorrected distance visual acuity (UCDVA), AL, and age was the Extreme Gradient Boosting model, with an AUC of 0.983 and an accuracy of 0.970. The best diagnostic model using non-cycloplegic SE, AL/CCR, UCDVA, and age was the Random Forest model, with an AUC of 0.981 and an accuracy of 0.975. The AL/CCR demonstrated superior performance in predicting childhood myopia. The ML-based multi-indicator joint diagnostic predictive model enhances the accuracy of childhood myopia diagnosis, screening, and intervention.