Liver cancer knowledge graph construction based on dynamic entity replacement and masking strategies RoBERTa-wwm-large-BiLSTM-CRF model with clinical Chinese EMRs
The findings demonstrated the effectiveness of the proposed framework in constructing a comprehensive and clinically relevant liver cancer KG. The novel DERM-based NER model significantly improved entity extraction from complex medical texts. By successfully integrating real-world clinical data, this study addresses a critical gap in existing liver cancer-specific KGs, which are mostly derived from literature or public databases and lack integration with real-world clinical information.
Authors
- Yichi Zhang (ORCID: https://orcid.org/0000-0002-2267-5442)
- Xiaoyan Jiang (ORCID: https://orcid.org/0000-0001-8620-6488)
- Yunfei Fan (ORCID: https://orcid.org/0000-0002-1363-6433)
- Zhijun Fang (ORCID: https://orcid.org/0000-0001-8563-5678)
- Xiaojun Hu (ORCID: https://orcid.org/0000-0001-7092-2535)
- Peng Liu (ORCID: https://orcid.org/0000-0002-1667-6617)
- Yongbin Gao
- Hailing Wang
Institutions
- Shanghai University of Engineering Science (CN)
- Donghua University (CN)
- Capital Medical University (CN)
- Third Affiliated Hospital of Southern Medical University (CN)
- Beijing Anding Hospital (CN)
Publication Details
- Journal
- Frontiers in Artificial Intelligence
- Published
- 2025-10-17
- DOI
- https://doi.org/10.3389/frai.2025.1663877
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Southern Medical University