Identification and risk-factor analysis for individuals at high risk for keratoconus via machine learning and logistic regression
Kaiyue Du, Rongmei Peng, Yueguo Chen, Bowei Yuan, Wei Chen, Liang Han, Gege Xiao, Yi Qu · 2026
Read Identification and risk-factor analysis for individuals at high risk for keratoconus via machine learning and logistic regression by Kaiyue Du, Rongmei Peng, Yueguo Chen, Bowei Yuan, Wei Chen, Liang Han, Gege Xiao, Yi Qu (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/plos-pone-0354924.txt.
Description
Kaiyue Du and colleagues built lifestyle-based risk models for keratoconus, a disease that thins and bulges the cornea. They used records from 711 patients at a Chinese eye center, 275 of them with the disease. Their 2026 study combined standard regression with seven machine learning models. The models were fed demographic and habit data. The team then asked the models to explain which factors mattered most.
Seven risk factors stood out. They included male sex, higher body mass, and less schooling. A more distant childhood home and allergic conjunctivitis counted too. Above all stood rubbing the eyes, harder and more often. The best model sorted patients with fair accuracy. Because eye rubbing is changeable, the authors see a practical opening. Flag high-risk patients early, and coach the habit away before corneas deform.
Catalog record
| CREATOR | Kaiyue Du, Rongmei Peng, Yueguo Chen, Bowei Yuan, Wei Chen, Liang Han, Gege Xiao, Yi Qu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40068 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |