Tools › Entity types

Redact medications from text, JSON, and CSV

Medication names reveal a condition by inference, so redacting a diagnosis while leaving the prescription visible defeats the purpose.

How Redactly detects medications

• Detected by the model rather than a drug dictionary, so brand and generic names are both covered.
• Spans are extended across contiguous word characters, which fixes the common failure where only part of a drug name is tagged.
• Dosages are left in place unless they are separately detected as an amount.

Why redact medications?

A prescription names the condition indirectly and is often easier to detect than the diagnosis itself.

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": "Current prescription: atorvastatin 20mg nightly.", "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

• Medical conditionsRedact diagnoses and medical conditions from clinical notes, claim narratives, 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.