Does BERT Pretrained on Clinical Notes Reveal Sensitive Data? • Large Transformers pretrained over clinical notes from Electronic Health Records (EHR) have afforded substantial gains in performance on predictive clinical tasks.
Paper arxiv.org/abs/2104.07762
GitHub
↓ 1/4
Paper arxiv.org/abs/2104.07762
GitHub
↓ 1/4
github.com/elehman16/expo…
The cost of training such models and the necessity of data access to do so is coupled with their utility motivates parameter sharing, i.e., the release of pretrained models such as ClinicalBERT.
↓ 2/4
The cost of training such models and the necessity of data access to do so is coupled with their utility motivates parameter sharing, i.e., the release of pretrained models such as ClinicalBERT.
↓ 2/4
While most efforts have used deidentified EHR, many researchers have access to large sets of sensitive, non-deidentified EHR with which they might train a BERT model (or similar).
Would it be safe to release the weights of such a model if they did?
↓ 3/4
Would it be safe to release the weights of such a model if they did?
↓ 3/4
In this work, they design a battery of approaches intended to recover Personal Health Information (PHI) from a trained BERT.
Specifically, they attempt to recover patient names and conditions with which they are associated.
4/4
Specifically, they attempt to recover patient names and conditions with which they are associated.
4/4
• • •
Missing some Tweet in this thread? You can try to
force a refresh
