HANK_SAFEHARBOR
HIPAA Safe Harbor de-identification: detect the 18 identifiers in a
clinical note or PDF and replace each with a consistent, realistic fake
(not a [REDACTED] hole), so the document stays readable.
- Text & PDF. Both modalities: the native text layer, and an OCR pass for scans.
- Available under a BAA. Sign one to send protected health information. Without it, send synthetic or scrubbed text only.
- Consistent fakes. The same person gets the same surrogate document-wide.
Evaluated on synthetic clinical text so far; recall-first. Apache-2.0 engine.
Or try a sample document
Synthetic records with no PHI. Pick one and watch it redact live below.
Workspace
Pick a sample, paste a note, or drop a PDF.
Compare the original and de-identified
documents here: text side by side, and PDFs full size with a quick toggle.
Original
De-identified
Original
De-identified