Time and person sensitive foundation model for disease prediction and risk stratification
Foundation models (FMs) enable generalizable medical AI, but existing retinal FMs perform best on cross-sectional classification and detection and are less effective for predicting disease incidence and progression. We present RETFound Plus, a CFP-based FM trained with temporal modeling on 1,304,292 fundus photographs from 304,345 participants across multiple visits to learn progression-aware representations. Compared with RETFound, RETFound Plus improved calibration and 5-year risk prediction across systemic and ocular diseases, with larger gains for systemic outcomes (stroke, myocardial infarction, diabetes and hypertension; +4-10% c-index) than ocular outcomes (diabetic retinopathy and glaucoma; +3-7% c-index), and improved risk stratification for systemic diseases (1.2-2.1-fold higher hazard-ratio trend). Results were consistent across external multi-regional, multi-ethnic datasets from the UK, US, Singapore, Hong Kong, and Denmark.
Authors
- Zhouyu Guan (ORCID: https://orcid.org/0009-0008-5102-0067)
- Jocelyn Hui Lin Goh (ORCID: https://orcid.org/0000-0002-5052-6081)
- Charumathi Sabanayagam (ORCID: https://orcid.org/0000-0002-4042-4719)
- Carol Y. Cheung (ORCID: https://orcid.org/0000-0002-9672-1819)
- Zhi Da Soh (ORCID: https://orcid.org/0000-0002-1182-3489)
- Can Can Xue (ORCID: https://orcid.org/0000-0002-2747-6215)
- Yibing Chen (ORCID: https://orcid.org/0000-0002-7444-3088)
- Ke Zou (ORCID: https://orcid.org/0000-0002-1181-1779)
- Guang Yang (ORCID: https://orcid.org/0000-0001-5271-7079)
- Tingyao Li
- Samantha Min Er Yew
- Jia Shu (ORCID: https://orcid.org/0009-0008-9470-7133)
- Yih-Chung Tham
- Miao Li Chee
- Yilan Wu
- Yukun Zhou
- An Ran Ran
- Yixiao Jin
- Xiangning Wang
- Xujia Liu
- Zheyuan Wang
- Tien Yin Wong
- Qiang WU
- Tingli Chen
- Pearse A. Keane
- Ching-Yu Cheng
- Huating Li
- Bin Sheng
- Changchang Yin
- Siegfried K. Wagner
- Nan Jiang
- Jakob Grauslund
- Benjamin Sommer Thinggaard
- Ping Zhang
- Danqi Fang
- Haoxuan Li
Institutions
- University College Hospital (GB)
- Moorfields Eye Hospital NHS Foundation Trust (GB)
- National University of Singapore (SG)
- Chinese University of Hong Kong (HK)
- University of Southern Denmark (DK)
- Shanghai Jiao Tong University (CN)
- Shanghai University of Sport (CN)
- Hawassa University (ET)
- Singapore National Eye Center (SG)
- Odense University Hospital (DK)
- Shanghai Medical Information Center (CN)
- Singapore Eye Research Institute (SG)
- Shanghai Sixth People's Hospital (CN)
- Moorfields Eye Hospital (GB)
- Beijing Tsinghua Chang Gung Hospital (CN)
- University College London (GB)
- The Ohio State University (US)
- Tsinghua University (CN)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2026-03-14
- DOI
- https://doi.org/10.1038/s41746-026-02524-6
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- National Science and Technology Major Project
- Medical Research Council
- National Medical Research Council