Development of machine learning predictive model for type 2 diabetic retinopathy using the triglyceride-glucose index explained by SHAP method
LR and SVM demonstrated the best performance. To our knowledge, this is the first machine learning-based DR prediction model integrating the triglyceride-glucose index (TyG) as a core predictor, overcoming limitations of insulin resistance (IR) assessment in resource-limited settings. TyG provides a cost-effective alternative to conventional IR biomarkers (e.g., HOMA-IR), enabling practical DR risk stratification in primary care.
Authors
- Rihui Liu
- Ling Qin (ORCID: https://orcid.org/0000-0001-8717-3833)
- Shuying Wu (ORCID: https://orcid.org/0000-0002-6584-0452)
- Fei Li (ORCID: https://orcid.org/0000-0001-9822-7526)
- Yue Yang (ORCID: https://orcid.org/0000-0001-5266-2573)
- Yang Li (ORCID: https://orcid.org/0000-0003-1590-4718)
- Xiaoqin Liu (ORCID: https://orcid.org/0009-0005-4527-7681)
- Xinting Zhang (ORCID: https://orcid.org/0009-0006-5285-8588)
Institutions
- Jilin University (CN)
- First Hospital of Jilin University (CN)
- Guangdong Academy of Medical Sciences (CN)
- Meiho University (TW)
Publication Details
- Journal
- Frontiers in Endocrinology
- Published
- 2025-11-10
- DOI
- https://doi.org/10.3389/fendo.2025.1631647
- Citations
- 1
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 1.36
Funders
- Jilin University
- First Hospital of Jilin University