Predicting Early Keratoconus Progression Using Biomechanics via Multi‐Machine Learning: A Multicenter 2‐Year Prospective Cohort Study
The machine learning-based index BEPI derived from corneal biomechanics enabled the accurate prediction of early keratoconus progression at the first visit, with an accuracy of 0.941. BEPI provides clinicians with a novel index for the accurate evaluation of early keratoconus progression, facilitating personalised clinical decision-making to preserve vision and improve prognosis.
Authors
- Haohan Zou (ORCID: https://orcid.org/0000-0003-0588-9753)
- Xiaona Li (ORCID: https://orcid.org/0000-0001-9578-8416)
- Jin Li (ORCID: https://orcid.org/0000-0002-6131-456X)
- Zepeng Qu (ORCID: https://orcid.org/0000-0003-1208-0557)
- Ruisi Xie (ORCID: https://orcid.org/0009-0009-4835-045X)
- Yan Huo
- Yan Wang
- Shufan Wang
- Yutong Li
- Jie Hou
Institutions
- Shanxi Medical University (CN)
- Nankai University (CN)
- Shaanxi Provincial People's Hospital (CN)
- Taiyuan Institute of Technology (CN)
- Xi’an Children’s Hospital (CN)
- Tianjin Medical University Eye Hospital (CN)
- Shandong Eye Hospital (CN)
- Shanxi Provincial People’s Hospital (CN)
- Tianjin Medical University (CN)
Publication Details
- Journal
- Clinical and Experimental Ophthalmology
- Published
- 2026-02-11
- DOI
- https://doi.org/10.1111/ceo.70076
- Primary Topic
- Corneal surgery and disorders
- Type
- article
- Field-Weighted Citation Impact
- 0.00