Pseudonymising GP Medical Notes and Referral Letters – UK GDPR-compliant anonymisation per UK GDPR Art. 9

GP medical notes and referral letters combine special-category health data with rich biographical detail: patient name, address, date of birth, NHS number, presenting complaint, medication history, and family background. anonym.legal pseudonymises these identifiers in free-text and structured fields alike, preserving the clinical assessment, referral rationale, and medication record for secondary review without disclosing individual patient identity.

When this applies

This task applies when GP notes or referral letters are shared with secondary-care clinicians, medicolegal advisers, or clinical governance teams for peer review, complaint investigation, or benchmarking, and those reviewers require the clinical content but not the patient's identity.

  1. Upload the GP notes or referral letter (PDF, DOCX, or plain text) to anonym.legal.
  2. The engine identifies patient identifiers in both structured fields and free-text body: name, address, date of birth, NHS number, GP registration number, and family member names mentioned in family history sections.
  3. Each named individual — patient, named family members, and referring clinician — is pseudonymised consistently throughout the document.
  4. Clinical assessment, medication history, diagnosis codes, and referral rationale are preserved in clear text.
  5. A reversible mapping table is produced with UK data residency.
  6. The pseudonymised note is released for the approved review purpose; re-identification uses the mapping key held by the Data Controller.

What you provide

  • GP medical notes or referral letter (PDF, DOCX, or text)
  • Any accompanying test results or correspondence naming the patient

Limitations & cautions

  • Handwritten GP notes require OCR pre-processing before entity detection; OCR accuracy affects coverage.
  • Highly specific clinical details — unusual diagnoses in small communities — may remain re-identifying even with names removed; apply additional care for rare-condition cases.
  • The tool does not assess clinical accuracy or medicolegal sufficiency of the notes.

FAQ

Are family members mentioned in family history sections pseudonymised?

Yes. Named family members appearing in family history or next-of-kin sections are detected as distinct individuals and each receives a unique pseudonym, preserving the family relationship structure without disclosing individual identities.

Can I pseudonymise a referral letter before sending it to a medicolegal expert?

Yes. This is a primary use case. The pseudonymised referral preserves the clinical narrative the expert requires for opinion while removing identifiers. Ensure you retain the mapping key to re-identify when issuing the final medico-legal report.

Does the tool handle letters written in a mix of structured and narrative formats?

Yes. The engine detects entities in both table-structured fields (patient demographics blocks) and free-text narrative paragraphs within the same document.

Healthcare Records

About this page

We update this page when our platform or the law changes.

Read our founder note for how we work.

Each change shows up in the timestamp at the top.

We follow these rules

  • GDPR (EU 2016/679).
  • ISO/IEC 27001:2022.
  • NIS2 (EU 2022/2555).
  • HIPAA safe harbor under 45 CFR § 164.514(b)(2).

Our promise

We do not sell your data.

We do not train models on your text.

We store your files in Germany.

You can delete your account at any time.

You own your work.

Where we run

Our servers live in Falkenstein, Germany.

We use Hetzner. They hold ISO 27001 certification.

All data stays in the EU.

Backups run every day.

Need help?

Email support@anonym.legal.

We reply within one business day.

How we test

We run a full check suite on every release.

Each surface gets its own sweep script and report.

Human reviewers spot-check the output each week.

We track recall and precision on a labelled set.

Bad runs block the deploy.

What we never do

  • We never sell your information to third parties.
  • We never train models on what you upload.
  • We never keep your work after you delete it.
  • We never share keys with any outside firm.
  • We never run ads inside the product.

Plans in plain words

We sell credits, not seats.

One credit covers one short job.

Long jobs use a few credits each.

You can top up at any time.

Unused credits roll over each month.

Read the plans page for current rates.

Who built this

A small team of engineers and lawyers built this.

We ship from Europe and work in the open.

Our founder note spells out why we started.

Where to start

How the parts fit

A browser add-on cleans text inside Chrome.

A Word plug-in handles drafts in Office.

A small desktop tool works on whole folders.

An agent protocol link feeds large models safely.

All four share one core engine and one rule set.

Words from our team

We started this work after a lunch about cookies.

One friend kept getting odd ads on her phone.

We asked why a court file leaked through a draft.

We sketched the first build on a napkin that week.

By month three we had a tiny demo for a friend.

She used it on her first case the next day.

Common questions we hear

Can the tool read scanned PDFs? Yes, with OCR.

Does it work on long files? Yes, in small chunks.

Can I roll my own rule set? Yes, save it as a preset.

Does it run offline? The desktop build runs offline.

Do you keep my files? No, the cloud build wipes after each run.

Will it learn from my work? No, we never train on inputs.

A short tour of the workflow

Upload a file or paste a snippet of prose.

Pick the entities you want gone from the draft.

Choose a method: replace, mask, hash, encrypt, or redact.

Press run and watch the side panel show each hit.

Skim the result and tweak any rule that misfired.

Save the cleaned file or send it to a teammate.