Artificial Intelligence–Based Prediction of Subjective Refraction and Clinical Determinants of Prediction Error

TL;DR

This study shows that AI can accurately predict eye refraction using routine data, potentially aiding eye exams.

Contribution

The novel use of routine non-cycloplegic autorefraction and keratometry data for AI-based refraction prediction is presented.

Findings

The model achieved high accuracy for spherical and cylindrical prediction (R2 = 0.987 and 0.933; MAE = 0.126 D and 0.137 D).

Astigmatic axis prediction had a mean absolute angular error of 4.65° (median, 0.96°).

Factors like steeper keratometry and greater objective cylindrical power were linked to reduced prediction accuracy.

Abstract

Background/Objectives: Subjective refraction is the clinical gold standard but is time-consuming and examiner-dependent. Most artificial intelligence (AI)-based approaches rely on specialized imaging or biometric data not routinely available. This study aimed to predict subjective refraction using only routine, non-cycloplegic autorefraction and keratometric data and to identify factors associated with reduced prediction accuracy. Methods: This retrospective study included 1856 eyes from 1006 patients. A multi-output histogram gradient-boosting model predicted subjective spherical equivalent, cylindrical power, and astigmatic axis. Performance was evaluated on an independent test dataset using R2 and mean absolute error, with circular statistics for axis prediction. Prediction failure was assessed using clinically relevant tolerance thresholds (sphere/cylinder ≤ 0.50 D; axis ≤ 10°) and multivariable logistic regression. Results: The model achieved high accuracy for spherical and cylindrical prediction (R2 = 0.987 and 0.933; MAE = 0.126 D and 0.137 D). Astigmatic axis prediction demonstrated strong circular agreement (ρ = 0.898), with a mean absolute angular error of 4.65° (median, 0.96°). Axis errors were higher in eyes with low cylinder magnitude (<0.75 D) and oblique astigmatism. In multivariable analysis, steeper keratometry (K2; OR = 7.25, 95% CI 1.62–32.46, p = 0.010) and greater objective cylindrical power (OR = 2.79, 95% CI 1.87–8.94, p = 0.032) were independently associated with poor prediction. Conclusions: A machine-learning model based solely on routine, non-cycloplegic autorefractor and keratometric measurements can accurately estimate subjective refraction, supporting AI as a complementary decision-support tool rather than a replacement for conventional subjective refraction.

Figures