Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 14, 2025JMIR Medical InformaticsOpen Access

Named Entity Recognition for Chinese Cancer Electronic Health Records—Development and Evaluation of a Domain-Specific BERT Model: Quantitative Study

View Full Paper
Ask AI
Bookmark
Share

Authors

JCJunbai ChenBZButian ZhaoXTXiaohan Tian

Discussion

Loading...

Member takes

Overview

Quantitative study demonstrates Named Entity Recognition improves clinical decision support in breast cancer EHRs, indicating substantial benefits for treatment outcomes.

Key Points

  • The proposed model enhances clinical decision support for breast cancer, improving accuracy in medical entity recognition.
  • With a precision of 87.24% and an F1-score of 86.93%, the model significantly outperforms baseline approaches.
  • This observational analysis incorporates the ChCancerBERT model, utilizing specialized cancer corpora for effective NER in Chinese EHRs.
  • The findings highlight the potential for improved entity recognition in cancer records, emphasizing the importance of domain-specific data.

Cite This Study

Chen et al. (2025) studied this question.

synapsesocial.com/papers/69251999c0ce034ddc35399ehttps://doi.org/10.2196/76912
View Full Paper
Ask AI
Bookmark
Share