Tools › Entity types

Redact medical conditions from text, JSON, and CSV

A condition is arguably the most sensitive health datum and the hardest to detect, because it is ordinary language rather than a pattern. This is a model-only type.

How Redactly detects medical conditions

• Detected by the model; there is no pattern or cue that reliably identifies a diagnosis.
• Spans are extended to whole words so a truncated term is not left half-visible.
• Medications named in the same sentence are reported separately as healthcare.medication.

Why redact medical conditions?

Health conditions are special-category data under GDPR Article 9 and protected health information under HIPAA.

Example request

curl -X POST https://api.bitbanger.in/v1/redact \
  -H "X-API-Key: rdct_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{"text": "Patient reports type 2 diabetes managed with metformin.", "style": "replace"}'

Every hit in the response carries entity, text, start, and end. The offsets index into the text you sent, so you can apply the redactions to your own copy of the document. The full response schema is in the API reference.

Questions

Related entity types

• MedicationsRedact drug names and prescriptions from clinical text and support transcripts.
• Health statusRedact statements about a person's health, disability, or medical status from free text.
• Medical record numbersRedact MRNs and patient record identifiers from clinical notes, referrals, and export files.