Search Articles

View query in Help articles search
e.g. John Smith or 0000-0001-6479-5330

Search Results (1 to 10 of 1608 Results)

Download search results: CSV END BibTex RIS

CSV download: Download all 1,608 search results (up to 5,000 articles maximum)
Named Entity Recognition for Chinese Cancer Electronic Health Records—Development and Evaluation of a Domain-Specific BERT Model: Quantitative Study

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

Chen et al [6] constructed a hybrid model combining MC-BERT, Bi LSTM, CNN, MHA, and CRF to achieve NER in Chinese EHRs. Most of these studies primarily applied their deep learning models to publicly available datasets such as CCKS2017 and CCKS2019, without further testing them on specific medical departments or diseases. Existing research indicates that using domain-specific text as training data, as opposed to general language models, can yield better performance.

Junbai Chen, Butian Zhao, Xiaohan Tian, Zhengkai Zou, Ruojia Wang, Jiarui Wu, Songxing Du, Fengying Guo

JMIR Med Inform 2025;13:e76912

Download Citation: END BibTex RIS

Download PDF Download XML

Identifying Stigma Phenotypes in Social Media Narratives of Substance Use: Observational Study

Identifying Stigma Phenotypes in Social Media Narratives of Substance Use: Observational Study

The posts in this dataset were sampled using the keyword sampling approach described by Chen et al [12] to select posts that likely contained stigma. Posts were annotated with substances and stigma mechanisms. Further details on the operationalization of the stigma mechanisms are provided in Multimedia Appendix 1. All the M1 models involved fine-tuning a pretrained Ro BERTa model [35].

Lexie Chenyue Wang, Kenneth C Pike, Mike Conway, Annie T Chen

J Med Internet Res 2025;27:e68695

Download Citation: END BibTex RIS

Download PDF Download XML