Unsupervised clustering based on a graph attention network reveals high-risk subgroups among ICU dementia patients for enhanced mortality prediction
This study demonstrates the effectiveness of GAT-based clustering for identifying high-risk subgroups among dementia patients in the ICU. By providing more granular risk stratification, these models can support clinical decision-making and improve patient management. These findings underscore the potential of advanced machine learning techniques in enhancing ICU care for dementia patients, with future research focusing on temporal validation and integration into clinical workflows to optimize outcomes.
Authors
- Chuanxiong Li (ORCID: https://orcid.org/0000-0002-7511-9933)
- Qianwen Ruan
- B H Wang (ORCID: https://orcid.org/0000-0003-4501-7685)
- Xiaoyu Zhang (ORCID: https://orcid.org/0009-0004-6009-4624)
- T. Sun (ORCID: https://orcid.org/0000-0003-0129-4103)
- Lei Pan (ORCID: https://orcid.org/0000-0002-6669-8144)
- Lei Zhang (ORCID: https://orcid.org/0000-0003-0529-1305)
- Meihua Qiu (ORCID: https://orcid.org/0000-0001-6803-5582)
Institutions
- Yunnan University (CN)
- Kunming Medical University (CN)
- Second People's Hospital of Yunnan Province (CN)
- Sichuan Provincial Hospital of Traditional Chinese Medicine (CN)
- Second Affiliated Hospital of Chengdu University of Traditional Chinese (CN)
- Yunnan University of Traditional Chinese Medicine (CN)
- Lanzhou University (CN)
Publication Details
- Journal
- European journal of medical research
- Published
- 2025-11-10
- DOI
- https://doi.org/10.1186/s40001-025-03336-2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Yunnan University
- Chengdu University of Traditional Chinese Medicine
- Chengdu University