| Title: | A deep learning system for detecting silent brain infarction and predicting stroke risk |
| Journal: | Nature Biomedical Engineering |
| Published: | 6 Jun 2025 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/40481238/ |
| DOI: | https://doi.org/10.1038/s41551-025-01413-9 |
| URL: | https://www.nature.com/articles/s41551-025-01413-9.pdf |
Publication 15044
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Current brain imaging to detect silent brain infarctions (SBIs) is not feasible for the general population. Here, to overcome this challenge, we developed a retinal image-based deep learning system, DeepRETStroke, to detect SBI and refine stroke risk. We use 895,640 retinal photographs to pretrain the DeepRETStroke system, which encodes a domain-specific foundation model for representing eye-brain connections. Then, we validated the downstream clinical tasks of DeepRETStroke using 213,762 retinal photographs from diverse datasets across China, Singapore, Malaysia, the USA, the UK and Denmark to detect SBI and predict stroke events. DeepRETStroke performed well in internal validation datasets, with areas under the curve of 0.901 for predicting incident stroke and 0.769 for predicting recurrent stroke. External validations demonstrated consistent performances across diverse datasets. Finally, in a prospective study comprising 218 participants with stroke, we assessed the performance of DeepRETStroke compared with clinical traits in guiding strategies for stroke recurrence prevention. Altogether, the retinal image-based deep learning system, DeepRETStroke, is superior to clinical traits in predicting stroke events, especially by incorporating the detection of SBI, without the need for brain imaging.</p>
70 Authors
- Nan Jiang
- Hongwei Ji
- Zhouyu Guan
- Yuesong Pan
- Chenxin Deng
- Yuchen Guo
- Dan Liu
- Tingli Chen
- Shiyu Wang
- Yilan Wu
- Dawei Yang
- An Ran Ran
- Haslina Hamzah
- Miao Li Chee
- Changchang Yin
- Benjamin Sommer Thinggaard
- Frederik N. Pedersen
- Qingsheng Peng
- Ten Cheer Quek
- Jocelyn Hui Lin Goh
- Sarkaaj Singh
- Anis Syazwani Abd Raof
- Jian Wen Samuel Lee-Boey
- Yuwei Lu
- Shan Huang
- Jia Shu
- Shujie Yu
- Yixiao Jin
- Tingyao Li
- Yiming Qin
- Jing Wang
- Xiaolong Yang
- Tingting Hu
- Zheyuan Wang
- Yaoning Zhao
- Seungmin Lee
- Xiaoer Wei
- Haotian Zheng
- Yuehua Li
- Jie Shen
- Yan Zhou
- Shiqun Lin
- Chan Wu
- Rongping Dai
- Lei Ruan
- Ruth E. Hogg
- David Wright
- Ya Xing Wang
- Yingfeng Zheng
- Gavin Siew Wei Tan
- Charumathi Sabanayagam
- Yuqian Bao
- Cuntai Zhang
- Ping Zhang
- Weiwen Zou
- Minyi Guo
- Xiaokang Yang
- Gareth J. McKay
- Jakob Grauslund
- Lee-Ling Lim
- Zixiao Li
- Carol Y. Cheung
- Yih Chung Tham
- Ching-Yu Cheng
- Yongjun Wang
- Qionghai Dai
- Weiping Jia
- Huating Li
- Bin Sheng
- Tien Yin Wong
1 Application
| Application ID | Title |
|---|---|
| 104443 | The artificial intelligence supported system in the diagnosis and risk prediction of metabolic disorders based on multimodal data |
Enabling scientific discoveries that improve human health