Fast and accurate visual acuity prediction based on optical aberrations and machine learning
A. Sierra, I. Baoud-Ould-Haddi, S. Fernández-Núñez, J. A. Gómez-Pedrero, M. García-Montero, N. Garzón, J. Alonso, E. Pascual, J. Vargas · 2025
Read Fast and accurate visual acuity prediction based on optical aberrations and machine learning by A. Sierra, I. Baoud-Ould-Haddi, S. Fernández-Núñez, J. A. Gómez-Pedrero, M. García-Montero, N. Garzón, J. Alonso, E. Pascual, J. Vargas (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12717265.txt.
Description
A Sierra and co-authors test machine learning methods that predict how sharply a person can see, from measurements of the eye's optical flaws, in this 2025 paper. Eye clinics measure those flaws as a set of coefficients, but turning them into a vision score normally needs the patient to read letters. A good predictor could speed exams and help design corrections.
Data came from 135 trial subjects, each with thirty-six flaw coefficients, focusing range, age, and a measured vision score. Two tree based methods and one neural network were compared. The boosting method called LSBoost was the most accurate, especially with focusing range included. A rival was faster on big data. The network read test letters well but predicted scores worse, and it was slow. Trees fit the task best.
Catalog record
| CREATOR | A. Sierra, I. Baoud-Ould-Haddi, S. Fernández-Núñez, J. A. Gómez-Pedrero, M. García-Montero, N. Garzón, J. Alonso, E. Pascual, J. Vargas |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |