Predicting the gastrointestinal bleeding of HBV-related acute-on-chronic liver failure based on machine learning
GIB has a significant effect on short-term survival in patients with HBV-ACLF. On this basis, five ML prediction models, LR, SVM, DT, RF, and KNN, were established to have better prediction ability for GIB, among which the RF model has the most robust prediction performance, which can help clinicians intervene in advance and improve the short-term survival rate of patients.
Authors
- Yuna Wang
- Yuyu Zeng (ORCID: https://orcid.org/0000-0002-4343-5560)
- Xiaoping Wu (ORCID: https://orcid.org/0000-0001-6776-6973)
- Ziwei Zhou (ORCID: https://orcid.org/0000-0002-5927-7835)
- Pei Shi (ORCID: https://orcid.org/0009-0005-8677-9012)
- Jiwei Fu (ORCID: https://orcid.org/0009-0004-8839-4813)
- Ahao Wu (ORCID: https://orcid.org/0000-0001-5078-8412)
- Wentao Zhu (ORCID: https://orcid.org/0000-0001-6371-7998)
- Mengyu Tao (ORCID: https://orcid.org/0000-0002-1500-304X)
- Ting Deng (ORCID: https://orcid.org/0000-0003-0708-8060)
- Yan Peng (ORCID: https://orcid.org/0000-0002-8273-5566)
Institutions
- Nanchang University (CN)
- First Affiliated Hospital of Jiangxi Medical College (CN)
- First Affiliated Hospital of Nanchang University (CN)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-11-25
- DOI
- https://doi.org/10.3389/fmed.2025.1516476
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China