Combining structural and microvascular parameters via machine learning for enhanced diagnosis of normal-tension glaucoma among highly myopic eyes: a prospective cross-sectional diagnostic accuracy study
Chang-Zhu He, Qin Qiu, Heng Lai, Chun-Yan Lai, Yu He, Lin Jing · 2026
Read Combining structural and microvascular parameters via machine learning for enhanced diagnosis of normal-tension glaucoma among highly myopic eyes: a prospective cross-sectional diagnostic accuracy study by Chang-Zhu He, Qin Qiu, Heng Lai, Chun-Yan Lai, Yu He, Lin Jing (2026) 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/PMC13576206.txt.
Description
Chang-Zhu He and five colleagues test whether combining structural and blood flow eye scans improves spotting normal-tension glaucoma in very short-sighted eyes, in a 2026 diagnostic study. High myopia and this glaucoma type can look alike, making diagnosis tricky. Structural scans map tissue layers, while a related scan maps tiny vessels.
The study enrolled 87 patients, 42 with high myopia alone and 45 with glaucoma added. Structural measures beat vessel measures overall. One layer measure at the lower macula scored best, at 0.85 on the ranking accuracy scale, while the best vessel measure sat lower. Machine learning and standard regression models were built from the chosen features and checked with resampling and calibration tests. Explanation tools showed how each feature pushed individual predictions. The authors see combined data as useful support for a hard distinction.
Catalog record
| CREATOR | Chang-Zhu He, Qin Qiu, Heng Lai, Chun-Yan Lai, Yu He, Lin Jing |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 78136 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |