Deep Learning Prediction of Childhood Myopia Progression Using Fundus Image and Refraction Data
In this cohort study, a deep learning model, using minimal baseline data, provided highly accurate prediction of myopia and high myopia risk. This deep learning approach suggests the utility of large-scale screening and early-intervention efforts in resource-limited settings.
Authors
- Hubin Zhao
- Shi-Ming Li (ORCID: https://orcid.org/0000-0001-8083-2381)
- Yansong Hu
- Arokia Nathan (ORCID: https://orcid.org/0000-0003-4430-6143)
- Xuhang Chen (ORCID: https://orcid.org/0009-0003-1757-9303)
- Xuemeng Li
- Hongbei Meng
- Yanning Dai
- Ningli Wang
- Shengbo Wang
- Wei Wang
- Meng-Tian Kang
- Yuanyuan Liu
- Guohua Hu
- Peter Smielewski
- Ankang Zhou
- Shuo Gao
- Jing Fu
Institutions
- Beijing Tongren Hospital (CN)
- Accenture (Switzerland) (CH)
- Chinese University of Hong Kong (HK)
- University of Cambridge (GB)
- Stanmore College (GB)
- University College London (GB)
- King Abdullah University of Science and Technology (SA)
- Beihang University (CN)
Publication Details
- Journal
- JAMA Network Open
- Published
- 2026-01-26
- DOI
- https://doi.org/10.1001/jamanetworkopen.2025.53543
- Citations
- 2
- Primary Topic
- Ophthalmology and Visual Impairment Studies
- Type
- article
- Field-Weighted Citation Impact
- 63.04
Funders
- National Natural Science Foundation of China
- Capital Medical University
- Fundamental Research Funds for the Central Universities