Named Entity Recognition for Chinese Cancer Electronic Health Records—Development and Evaluation of a Domain-Specific BERT Model: Quantitative Study
The experiments demonstrate that the approach proposed in this study exhibits excellent performance in NER within breast cancer EHRs. This advancement will further contribute to clinical decision support for cancer treatment and research. In addition, the study reveals that incorporating domain-specific corpora in clinical NER tasks can further enhance the performance of BERT models in specialized domains.
Authors
- Butian Zhao (ORCID: https://orcid.org/0000-0001-9278-6685)
- Fengying Guo (ORCID: https://orcid.org/0000-0001-9982-3784)
- Xiaohan Tian (ORCID: https://orcid.org/0009-0001-9161-2701)
- Zhengkai Zou (ORCID: https://orcid.org/0009-0004-1303-2885)
- Jiarui Wu (ORCID: https://orcid.org/0000-0002-1617-6110)
- Ruojia Wang (ORCID: https://orcid.org/0000-0003-1806-0688)
- Shouyan Du (ORCID: https://orcid.org/0009-0001-8391-9412)
- J Chen (ORCID: https://orcid.org/0009-0004-3536-7811)
Institutions
- Beijing University of Chinese Medicine (CN)
- Peking University (CN)
- Dongfang Electric Corporation (China) (CN)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-11-14
- DOI
- https://doi.org/10.2196/76912
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00