Machine learning models for orthokeratology lens fitting and axial length prediction
Ophthalmic and Physiological Optics · 2023
DOI: 10.1111/opo.13212 ↗Kurz gefasst
Fachartikel in der Zeitschrift Ophthalmic and Physiological Optics, 2023. Verfasst von Shuai Xu und 8 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Weak-Light Nonlinear Photonics, Ministry of Education, School of Physics and TEDA Applied Physics, Nankai University, Tianjin, Chin…. Hauptthemen laut MEDLINE: Machine Learning, Orthokeratologic Procedures, Myopia, Axial Length, Eye. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: The Science and Technology Project of Tianjin Municipal Health Bureau, The Tianjin Municipal Science and Technology Program.
Abstract (Originalsprache)
Purpose
In order to improve the efficiency of orthokeratology (OK) lens fitting and predict the axial length after 1 year of OK lens wear, machine learning models were proposed.
Methods
Clinical data from 1302 myopic subjects were collected retrospectively, and two machine learning models were implemented. Demographic and corneal topographic data were collected as input variables. The output variables were the parameters of the OK lens and the axial length after 1 year. Eighty percent of input variables was used as the training set and the remaining 20% was used as the validation set. The first alignment curve (AC1) of the OK lenses, deduced using machine learning models and formula calculation, were compared. Multiple regression models (support vector machine, Gaussian process, decision tree and random forest) were used to predict the axial length after 1 year. In addition, we classified data based on lens brand, and carried out more detailed parameter fitting and analysis for spherical and toric OK lenses.
Results
The OK lens fitting model showed higher ( R 2 = 0.93) and lower errors (mean absolute error [MAE] = 0.19, mean square error [MSE] = 0.09) when predicting AC1, compared with the formula calculation ( R 2 = 0.66, MAE = 0.44, MSE = 0.25). The machine learning model still had high R 2 values ranging from 0.91 to 0.96 when considering the brand and design of the OK lenses. Further, the R 2 value for the axial length prediction model was 0.94, which indicated that the machine learning model had high accuracy and good robustness.
Conclusion
The OK lens fitting model and the axial length prediction model played an important role in guiding OK lens fitting, with high accuracy and robustness in prediction performance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory of Weak-Light Nonlinear Photonics, Ministry of Education, School of Physics and TEDA Applied Physics, Nankai University, Tianjin, China.
- Tianjin Eye Hospital Optometric Center, Tianjin, China.
- Tianjin Eye Hospital, Tianjin, China.
- Nankai University Affiliated Eye Hospital, Nankai University, Tianjin, China.
- School of Medicine, Nankai University, Tianjin, China.
ORCID-Profile: Hanyu Zhang, Lihua Li
Förderung
- The Science and Technology Project of Tianjin Municipal Health Bureau
- The Tianjin Municipal Science and Technology Program
Zitieren
APA
Xu, S., Yang, X., Zhang, S., Zheng, X., Zheng, F., Liu, Y., Zhang, H., Ye, Q., & Li, L. (2023). Machine learning models for orthokeratology lens fitting and axial length prediction. Ophthalmic and Physiological Optics. https://doi.org/10.1111/opo.13212
Vancouver
Xu S, Yang X, Zhang S, Zheng X, Zheng F, Liu Y, et al. Machine learning models for orthokeratology lens fitting and axial length prediction. Ophthalmic and Physiological Optics. 2023. doi:10.1111/opo.13212
BibTeX
@article{Xu2023,
author = {Xu, Shuai and Yang, Xiaoyan and Zhang, Shuxian and Zheng, Xuan and Zheng, Fang and Liu, Yin and Zhang, Hanyu and Ye, Qing and Li, Lihua},
title = {Machine learning models for orthokeratology lens fitting and axial length prediction},
journal = {Ophthalmic and Physiological Optics},
year = {2023},
doi = {10.1111/opo.13212}
}
EUVIMED