# Myopia Prediction Using Machine Learning: An External Validation Study

## TL;DR

This study validates machine learning models for predicting eye conditions using non-cycloplegic data across different clinical settings.

## Contribution

The study demonstrates the generalizability of ML models for predicting myopia and cycloplegic refraction across varying clinical protocols.

## Key findings

- XGBoost model predicted cycloplegic SER with high accuracy (R2 = 0.95, MAE = 0.32 D).
- Random forest and XGBoost models accurately predicted myopia with high sensitivity and specificity.
- ML models accurately estimated myopia prevalence despite differences in cycloplegia and biometry methods.

## Abstract

We previously developed machine learning (ML) models for predicting cycloplegic spherical equivalent refraction (SER) and myopia using non-cycloplegic data and following a standardized protocol (cycloplegia with 0.5% tropicamide and biometry using NIDEK A-scan), but the models’ performance may not be generalizable to other settings. This study evaluated the performance of ML models in an independent cohort using a different cycloplegic agent and biometer. Chinese students (N = 614) aged 8–13 years underwent autorefraction before and after cycloplegia with 0.5% tropicamide (n = 505) or 1% cyclopentolate (n = 109). Biometric measures were obtained using an IOLMaster 700 (n = 207) or Optical Biometer SW-9000 (n = 407). ML models were evaluated using R2, mean absolute error (MAE), sensitivity, specificity, and area under the ROC curve (AUC). The XGBoost model predicted cycloplegic SER very well (R2 = 0.95, MAE (SD) = 0.32 (0.30) D). Both ML models predicted myopia well (random forest: AUC 0.99, sensitivity 93.7%, specificity 96.4%; XGBoost: sensitivity 90.1%, specificity 96.8%) and accurately predicted the myopia rate (observed 62.9%; random forest: 60.6%; XGBoost: 58.8%) despite heterogeneous cycloplegia and biometry factors. In this independent cohort of students, XGBoost and random forest performed very well for predicting cycloplegic SER and myopia status using non-cycloplegic data. This external validation study demonstrated that ML may provide a useful tool for estimating cycloplegic SER and myopia prevalence with heterogeneous clinical parameters, and study in additional populations is warranted.