|
KMID : 1159320230250030293
|
|
Korean Journal of Vision Science
2023 Volume.25 No. 3 p.293 ~ p.300
|
|
|
Development of a Machine Learning Algorithm for Optimum Eyeglasses Prescription Based on Objective Refraction
|
|
Lee Min-Ji
Hong Joo-Wan
Yoon Song-Hui
Leem Hyun-Sung
|
|
|
Abstract
|
|
|
Purpose : As the Fourth Industrial Revolution progresses, to develop machine learning to draw subjective prescription values by using objective refraction, ocular aberrations, and pupil size.
Methods : Myopic subjects (1000 eyes) with no ocular or systemic diseases that could affect vision and no history of ocular surgery were participated. I-Profilerplus (Zeiss, Berlin, Germany) was used to measure objective refraction, ocular wavefront-aberration, and pupil size. For subjective-refraction, spherical refraction (S, diopters), astigmatic refraction (C, diopters), and astigmatic axis (Ax, °) were measured using a Visuphor500 (Zeiss, Berlin, Germany). After the measurements, the machine learning model was developed using Python (version 3.10) and checked its prediction performance.
Results : In the subjective refraction, the factors affecting the spherical refractive power were the highest in the order of objective spherical refractive errors, defocus aberration, spherical aberration, and trefoil aberration had the highest impact on spherical refractive power, while objective cylindrical refractive errors, defocus aberration, coma aberration, and trefoil aberration had the highest impact on cylindrical refractive power. However, the astigmatic axis was affected only by objective astigmatic axis. There was no difference between subjective refractive errors and machine learning predicted refractive errors for spherical refraction, cylindrical refraction, and astigmatic axis(p=0.976, 0.948, and 0.349, respectively).
Conclusion : A machine learning model that predicts the subjective refractive errors was developed, and the prediction accuracy was confirmed through there was no significant difference between the predicted refractive errors and the subjective refractive errors. Therefore, it is thought that it can be used as basic data to derive accurate eyeglass prescription for personalized prescriptions in the future.
|
|
|
KEYWORD
|
|
|
Machine learning, Subjective Refractive Errors Prediction
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|
|