Retinal features as predictive indicators for high myopia: insights from explainable multi-machine learning models
The XGBoost model outperformed other algorithms, and SHAP-derived cut-off values for critical risk factors enhanced clinical interpretability.
Authors
- Saiguang Ling
- Haohan Zou (ORCID: https://orcid.org/0000-0003-0588-9753)
- Yan Huo (ORCID: https://orcid.org/0000-0002-9379-6364)
- Shenda Shi
- Shengjin Wang (ORCID: https://orcid.org/0000-0002-3927-7918)
- Guoge Han (ORCID: https://orcid.org/0000-0003-0079-3023)
- Jing Liu (ORCID: https://orcid.org/0000-0003-4690-1886)
- Yan Wang (ORCID: https://orcid.org/0000-0001-5341-6040)
- Qian Fan (ORCID: https://orcid.org/0000-0001-7630-2353)
- Zhou Dong
Institutions
- Capital Medical University (CN)
- Nankai University (CN)
- InferVision (China) (CN)
- Tianjin Medical University Eye Hospital (CN)
- Beijing Friendship Hospital (CN)
- Tianjin Medical University (CN)
- Tsinghua University (CN)
Publication Details
- Journal
- Frontiers in Bioengineering and Biotechnology
- Published
- 2025-10-13
- DOI
- https://doi.org/10.3389/fbioe.2025.1609639
- Citations
- 1
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 1.36