This demo uses synthetic data. Annotation changes stay only in this browser tab and are never written to the server.

VTE-BERT-DeID

Disclaimer: This demo uses a standard set of generic semantic preprocessing rules. In production, these rules can be customized to align with institutional formatting requirements. The demo runs on CPU only, while production deployments can use GPU acceleration for significantly faster processing. The model is trained for precision, so if the result is negative, consider trying another note from the same encounter.

Input

Example 1 Example 2 Example 3 Example 4 Example 5 Example 6 Example 7

Output

Predicted label:
Model:
Execution: Local CPU

Resources

  • Publication: Jafari O, Ma S, Lam BD, et al. Development and validation of venous thromboembolism–bidirectional encoder representations from transformers (VTE-BERT) natural language processing model. J Thromb Haemost. 2026;24(7):2522–2531. doi:10.1016/j.jtha.2025.07.021
  • Model: VTE-BERT-DeID on is available on HuggingFace.