Revolutionizing Wilson disease prognosis: a machine learning approach to predict acute-on-chronic liver failure
The ML-based model effectively predicts WD-ACLF risk, with XGBoost demonstrating superior performance. TBA, APTT, diagnosis age, onset age and Hb emerged as critical biomarkers, offering actionable insights for early clinical intervention.
Authors
- Yongsheng Han (ORCID: https://orcid.org/0000-0002-9292-2584)
- Si-Huan Zhu
- Shuzhen Fang
- Zhihong Rao (ORCID: https://orcid.org/0000-0002-2342-7256)
- Wenming Yang (ORCID: https://orcid.org/0000-0001-8509-2140)
- Yulong Yang (ORCID: https://orcid.org/0000-0003-3136-108X)
- Xiang Li (ORCID: https://orcid.org/0000-0002-0699-1904)
- Yuchen Li (ORCID: https://orcid.org/0009-0009-9141-9627)
- Yue Yang (ORCID: https://orcid.org/0000-0002-6201-8818)
- Hu Xi
- Wei He (ORCID: https://orcid.org/0000-0002-4113-4895)
- Shuxiang Lü (ORCID: https://orcid.org/0000-0003-2559-5779)
- Ke Diao
Institutions
- Wannan Medical College (CN)
- Ministry of Education of the People's Republic of China (CN)
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- Anhui University of Traditional Chinese Medicine (CN)
- Wangjing Hospital of China Academy of Chinese Medical Sciences (CN)
- National Science Centre (PL)
- China Academy of Chinese Medical Sciences (CN)
Publication Details
- Journal
- Journal of Translational Medicine
- Published
- 2025-09-24
- DOI
- https://doi.org/10.1186/s12967-025-06987-1
- Citations
- 2
- Primary Topic
- Trace Elements in Health
- Type
- article
- Field-Weighted Citation Impact
- 2.24
Funders
- Anhui University
- Anhui University of Chinese Medicine