Deep learning-based brain age predicts stroke recurrence in acute ischemic cerebrovascular disease
Acute ischemic cerebrovascular disease (AICVD) exhibits high recurrence rates, necessitating novel biomarkers for refined risk stratification. While MRI-derived brain age correlates with stroke incidence, its prognostic utility for recurrence is unestablished. We developed the Mask-based Brain Age estimation Network (MBA Net), a deep learning framework designed for AICVD patients. MBA Net predicts contextual brain age (CBA) in non-infarcted regions by masking acute infarcts on T2-FLAIR images, thereby mitigating the confounding effects of dynamic infarcts during acute-phase neuroimaging. The model was trained on data from 5353 healthy individuals and then applied to a multicenter cohort of 10,890 AICVD patients. Brain age gap (BAG), defined as the deviation between CBA and chronological age, independently predicted stroke recurrence at both 3 months and 5 years, outperforming chronological age. Incorporating BAG into established prediction models significantly improved discriminative performance. These findings support brain age's potential utility in AI-driven precision strategies for secondary stroke prevention.
Authors
- Jian Cheng (ORCID: https://orcid.org/0000-0003-1435-673X)
- Lingling Ding (ORCID: https://orcid.org/0000-0003-0114-8157)
- Tao Liu (ORCID: https://orcid.org/0000-0001-5756-6097)
- Hao Li (ORCID: https://orcid.org/0000-0002-8827-8351)
- Jinxin Zhao (ORCID: https://orcid.org/0000-0002-9086-0957)
- Hongyu Zhou (ORCID: https://orcid.org/0000-0002-9130-889X)
- Xuewei Xie (ORCID: https://orcid.org/0000-0001-8154-1957)
- Yilong Wang (ORCID: https://orcid.org/0000-0002-6870-4958)
- Zixiao Li (ORCID: https://orcid.org/0000-0002-4713-5418)
- Hongqiu Gu
- Ziyang Liu (ORCID: https://orcid.org/0000-0001-6828-7587)
- Jing Jing (ORCID: https://orcid.org/0000-0001-9822-5758)
- Zhe Zhang (ORCID: https://orcid.org/0009-0006-8199-7456)
- Yubo Fan (ORCID: https://orcid.org/0000-0002-8977-1965)
- Hao Liu (ORCID: https://orcid.org/0000-0002-3294-5450)
- Yong Jiang (ORCID: https://orcid.org/0000-0002-4260-1395)
- Xia Meng (ORCID: https://orcid.org/0000-0002-4918-0845)
- Xingquan Zhao
- Yingyu Jiang
- Wanlin Zhu (ORCID: https://orcid.org/0000-0002-0525-657X)
- Yuesong Pan
- Yongjun Wang (ORCID: https://orcid.org/0000-0002-1796-5576)
Institutions
- Capital Medical University (CN)
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- Beijing Tian Tan Hospital (CN)
- National Clinical Research Center for Digestive Diseases (CN)
- Beijing Academy of Artificial Intelligence (CN)
- Chinese Institute for Brain Research (CN)
- Beihang University (CN)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2025-12-08
- DOI
- https://doi.org/10.1038/s41746-025-02161-5
- Citations
- 1
- Primary Topic
- Acute Ischemic Stroke Management
- Type
- article
- Field-Weighted Citation Impact
- 1.35
Funders
- National Natural Science Foundation of China
- Chinese Academy of Medical Sciences
- National Key Research and Development Program of China