CancerBERT: a cancer domain-specific language model for extracting breast cancer phenotypes from electronic health records.
Sicheng ZhouNan WangLiwei WangHongfang LiuRui ZhangPublished in: J. Am. Medical Informatics Assoc. (2022)
Keyphrases
- breast cancer
- language model
- electronic health records
- domain specific
- related genes
- early detection
- clinical data
- probabilistic model
- information retrieval
- clinical trials
- health care
- logistic regression
- domain experts
- cancer patients
- medical records
- health information
- gene expression
- medical data
- outcome prediction
- machine learning
- cancer datasets
- bladder cancer
- microarray data
- data sets
- association rules
- breast cancer patients
- databases